diff --git "a/profile_trace/iteration_168960/rank3_trace.json" "b/profile_trace/iteration_168960/rank3_trace.json" new file mode 100644--- /dev/null +++ "b/profile_trace/iteration_168960/rank3_trace.json" @@ -0,0 +1,85443 @@ + +{ + "schemaVersion": 1, + "deviceProperties": [ + { + "id": 0, "name": "NVIDIA H200", "totalGlobalMem": 149631664128, + "computeMajor": 9, "computeMinor": 0, + "maxThreadsPerBlock": 1024, "maxThreadsPerMultiprocessor": 2048, + "regsPerBlock": 65536, "warpSize": 32, + "sharedMemPerBlock": 49152, "numSms": 132 + , "regsPerMultiprocessor": 65536, "sharedMemPerBlockOptin": 232448, "sharedMemPerMultiprocessor": 233472 + }, + { + "id": 1, "name": "NVIDIA H200", "totalGlobalMem": 149631664128, + "computeMajor": 9, "computeMinor": 0, + "maxThreadsPerBlock": 1024, "maxThreadsPerMultiprocessor": 2048, + "regsPerBlock": 65536, "warpSize": 32, + "sharedMemPerBlock": 49152, "numSms": 132 + , "regsPerMultiprocessor": 65536, "sharedMemPerBlockOptin": 232448, "sharedMemPerMultiprocessor": 233472 + }, + { + "id": 2, "name": "NVIDIA H200", "totalGlobalMem": 149631664128, + "computeMajor": 9, "computeMinor": 0, + "maxThreadsPerBlock": 1024, "maxThreadsPerMultiprocessor": 2048, + "regsPerBlock": 65536, "warpSize": 32, + "sharedMemPerBlock": 49152, "numSms": 132 + , "regsPerMultiprocessor": 65536, "sharedMemPerBlockOptin": 232448, "sharedMemPerMultiprocessor": 233472 + }, + { + "id": 3, "name": "NVIDIA H200", "totalGlobalMem": 149631664128, + "computeMajor": 9, "computeMinor": 0, + "maxThreadsPerBlock": 1024, "maxThreadsPerMultiprocessor": 2048, + "regsPerBlock": 65536, "warpSize": 32, + "sharedMemPerBlock": 49152, "numSms": 132 + , "regsPerMultiprocessor": 65536, "sharedMemPerBlockOptin": 232448, "sharedMemPerMultiprocessor": 233472 + }, + { + "id": 4, "name": "NVIDIA H200", "totalGlobalMem": 149631664128, + "computeMajor": 9, "computeMinor": 0, + "maxThreadsPerBlock": 1024, "maxThreadsPerMultiprocessor": 2048, + "regsPerBlock": 65536, "warpSize": 32, + "sharedMemPerBlock": 49152, "numSms": 132 + , "regsPerMultiprocessor": 65536, "sharedMemPerBlockOptin": 232448, "sharedMemPerMultiprocessor": 233472 + }, + { + "id": 5, "name": "NVIDIA H200", "totalGlobalMem": 149631664128, + "computeMajor": 9, "computeMinor": 0, + "maxThreadsPerBlock": 1024, "maxThreadsPerMultiprocessor": 2048, + "regsPerBlock": 65536, "warpSize": 32, + "sharedMemPerBlock": 49152, "numSms": 132 + , "regsPerMultiprocessor": 65536, "sharedMemPerBlockOptin": 232448, "sharedMemPerMultiprocessor": 233472 + }, + { + "id": 6, "name": "NVIDIA H200", "totalGlobalMem": 149631664128, + "computeMajor": 9, "computeMinor": 0, + "maxThreadsPerBlock": 1024, "maxThreadsPerMultiprocessor": 2048, + "regsPerBlock": 65536, "warpSize": 32, + "sharedMemPerBlock": 49152, "numSms": 132 + , "regsPerMultiprocessor": 65536, "sharedMemPerBlockOptin": 232448, "sharedMemPerMultiprocessor": 233472 + }, + { + "id": 7, "name": "NVIDIA H200", "totalGlobalMem": 149631664128, + "computeMajor": 9, "computeMinor": 0, + "maxThreadsPerBlock": 1024, "maxThreadsPerMultiprocessor": 2048, + "regsPerBlock": 65536, "warpSize": 32, + "sharedMemPerBlock": 49152, "numSms": 132 + , "regsPerMultiprocessor": 65536, "sharedMemPerBlockOptin": 232448, "sharedMemPerMultiprocessor": 233472 + } + ], + "cupti_version": 22, + "cuda_runtime_version": 12040, + "cuda_driver_version": 12080, + "distributedInfo": {"backend": "nccl", "rank": 3, "world_size": 8, "pg_count": 1, "pg_config": [{"pg_name": "0", "pg_desc": "default_pg", "backend_config": "cuda:nccl", "pg_size": 8, "ranks": [0, 1, 2, 3, 4, 5, 6, 7]}], "nccl_version": "2.21.5"}, + "record_shapes": 1, + "trace_id": "9A16499BD789430880D3C5E7E7D497DD", + "traceEvents": [ + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: DivBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274488690.636, "dur": 112.148, + "args": { + "External id": 4052993,"Record function id": 0, "Sequence number": 40618582, "Fwd thread id": 1, "Ev Idx": 0 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "DivBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274488714.110, "dur": 76.635, + "args": { + "External id": 4052994,"Sequence number": 40618582, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[1]], "Ev Idx": 1 + } + }, + { + "ph": "f", "id": 1, "pid": 1336756, "tid": 1381189, "ts": 1655274488714.110, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::div", "pid": 1336756, "tid": 1381189, + "ts": 1655274488722.136, "dur": 66.146, + "args": { + "External id": 4052995,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "long int"], "Input Strides": [[1], []], "Input Dims": [[1], []], "Ev Idx": 2 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: AddBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274488826.334, "dur": 330.420, + "args": { + "External id": 4052996,"Record function id": 0, "Ev Idx": 3 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward", "pid": 1336756, "tid": 1381189, + "ts": 1655274488880.362, "dur": 165.281, + "args": { + "External id": 4052997,"Record function id": 0, "Ev Idx": 4 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::backward_prefetch for model.layers.27", "pid": 1336756, "tid": 1381189, + "ts": 1655274488915.193, "dur": 49.930, + "args": { + "External id": 4052998,"Record function id": 0, "Ev Idx": 5 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "AddBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274489060.119, "dur": 2.599, + "args": { + "External id": 4052999,"Sequence number": 40618581, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[1]], "Ev Idx": 6 + } + }, + { + "ph": "f", "id": 2, "pid": 1336756, "tid": 1381189, "ts": 1655274489060.119, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 1336756, "tid": 1381189, + "ts": 1655274489068.979, "dur": 79.890, + "args": { + "External id": 4053000,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", ""], "Input Strides": [[1], []], "Input Dims": [[1], []], "Ev Idx": 7 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 1336756, "tid": 1381189, + "ts": 1655274489079.143, "dur": 68.556, + "args": { + "External id": 4053001,"Record function id": 0, "Concrete Inputs": ["", "[]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[1], [], [], []], "Ev Idx": 8 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274489096.925, "dur": 4.682, + "args": { + "External id": 4053002,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 9 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: FusedLinearCrossEntropyFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1655274489179.029, "dur": 36616.521, + "args": { + "External id": 4053003,"Record function id": 0, "Sequence number": 40618579, "Fwd thread id": 1, "Ev Idx": 10 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "FusedLinearCrossEntropyFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1655274489182.802, "dur": 36599.580, + "args": { + "External id": 4053004,"Sequence number": 40618579, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 11 + } + }, + { + "ph": "f", "id": 3, "pid": 1336756, "tid": 1381189, "ts": 1655274489182.802, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655274489234.970, "dur": 4.366, + "args": { + "External id": 4053005,"Record function id": 0, "Concrete Inputs": ["[]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 12 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1381189, + "ts": 1655274489246.264, "dur": 36383.405, + "args": { + "External id": 4053006,"Record function id": 0, "Concrete Inputs": ["", "", "6", "False", "False", ""], "Input type": ["float", "", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 13 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336756, "tid": 1381189, + "ts": 1655274489249.049, "dur": 36379.653, + "args": { + "External id": 4053007,"Record function id": 0, "Concrete Inputs": ["", "6", "", "", "", "False", ""], "Input type": ["float", "Scalar", "", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], []], "Ev Idx": 14 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274489255.489, "dur": 11.716, + "args": { + "External id": 4053008,"Record function id": 0, "Concrete Inputs": ["[]", "[]", "6", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 15 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1381189, + "ts": 1655274489269.672, "dur": 36352.544, + "args": { + "External id": 4053009,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[], [], []], "Input Dims": [[], [], []], "Ev Idx": 16 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::lift_fresh", "pid": 1336756, "tid": 1381189, + "ts": 1655274525641.881, "dur": 1.089, + "args": { + "External id": 4053010,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 17 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach_", "pid": 1336756, "tid": 1381189, + "ts": 1655274525646.249, "dur": 4.183, + "args": { + "External id": 4053011,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 18 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach_", "pid": 1336756, "tid": 1381189, + "ts": 1655274525648.559, "dur": 1.550, + "args": { + "External id": 4053012,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 19 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::ne", "pid": 1336756, "tid": 1381189, + "ts": 1655274525660.714, "dur": 45.813, + "args": { + "External id": 4053013,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 20 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::is_nonzero", "pid": 1336756, "tid": 1381189, + "ts": 1655274525717.015, "dur": 51.567, + "args": { + "External id": 4053014,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["bool"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 21 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::item", "pid": 1336756, "tid": 1381189, + "ts": 1655274525718.683, "dur": 49.698, + "args": { + "External id": 4053015,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["bool"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 22 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_local_scalar_dense", "pid": 1336756, "tid": 1381189, + "ts": 1655274525720.711, "dur": 47.271, + "args": { + "External id": 4053016,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["bool"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 23 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274525817.675, "dur": 21.124, + "args": { + "External id": 4053017,"Record function id": 0, "Sequence number": 40618578, "Fwd thread id": 1, "Ev Idx": 24 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274525819.901, "dur": 16.441, + "args": { + "External id": 4053018,"Sequence number": 40618578, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[65536, 2048]], "Ev Idx": 25 + } + }, + { + "ph": "f", "id": 4, "pid": 1336756, "tid": 1381189, "ts": 1655274525819.901, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1381189, + "ts": 1655274525825.385, "dur": 10.670, + "args": { + "External id": 4053019,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 26 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274525829.392, "dur": 6.402, + "args": { + "External id": 4053020,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 27 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: SliceBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274525844.985, "dur": 95.135, + "args": { + "External id": 4053021,"Record function id": 0, "Sequence number": 40618577, "Fwd thread id": 1, "Ev Idx": 28 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SliceBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274525846.267, "dur": 87.280, + "args": { + "External id": 4053022,"Sequence number": 40618577, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 29 + } + }, + { + "ph": "f", "id": 5, "pid": 1336756, "tid": 1381189, "ts": 1655274525846.267, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 1336756, "tid": 1381189, + "ts": 1655274525850.604, "dur": 82.253, + "args": { + "External id": 4053023,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]", "2", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 2048], [], [], [], [], []], "Ev Idx": 30 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros", "pid": 1336756, "tid": 1381189, + "ts": 1655274525856.781, "dur": 32.651, + "args": { + "External id": 4053024,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 2048]", "15", "0", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 31 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655274525861.450, "dur": 4.860, + "args": { + "External id": 4053025,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 2048]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 32 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 1336756, "tid": 1381189, + "ts": 1655274525867.824, "dur": 21.263, + "args": { + "External id": 4053026,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 33 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 1336756, "tid": 1381189, + "ts": 1655274525870.391, "dur": 18.118, + "args": { + "External id": 4053027,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 34 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1381189, + "ts": 1655274525894.529, "dur": 4.874, + "args": { + "External id": 4053028,"Record function id": 0, "Concrete Inputs": ["", "2", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 1], [], [], [], []], "Input Dims": [[16, 4096, 2048], [], [], [], []], "Ev Idx": 35 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274525897.169, "dur": 1.779, + "args": { + "External id": 4053029,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]", "[8388608, 2048, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[8388608, 2048, 1], [], [], []], "Input Dims": [[16, 4096, 2048], [], [], []], "Ev Idx": 36 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1381189, + "ts": 1655274525900.977, "dur": 30.998, + "args": { + "External id": 4053030,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[8388608, 2048, 1], [8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], [16, 4096, 2048], []], "Ev Idx": 37 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: SelectBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274525944.680, "dur": 93.730, + "args": { + "External id": 4053031,"Record function id": 0, "Sequence number": 40618576, "Fwd thread id": 1, "Ev Idx": 38 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SelectBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274525945.881, "dur": 88.167, + "args": { + "External id": 4053032,"Sequence number": 40618576, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 39 + } + }, + { + "ph": "f", "id": 6, "pid": 1336756, "tid": 1381189, "ts": 1655274525945.881, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select_backward", "pid": 1336756, "tid": 1381189, + "ts": 1655274525948.724, "dur": 85.024, + "args": { + "External id": 4053033,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 4, 2048]", "2", "3"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 1], [], [], []], "Input Dims": [[16, 4096, 2048], [], [], []], "Ev Idx": 40 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros", "pid": 1336756, "tid": 1381189, + "ts": 1655274525954.335, "dur": 18.909, + "args": { + "External id": 4053034,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 4, 2048]", "15", "0", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 41 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655274525955.489, "dur": 2.917, + "args": { + "External id": 4053035,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 4, 2048]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 42 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 1336756, "tid": 1381189, + "ts": 1655274525959.137, "dur": 13.804, + "args": { + "External id": 4053036,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[33554432, 8192, 2048, 1]], "Input Dims": [[16, 4096, 4, 2048]], "Ev Idx": 43 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 1336756, "tid": 1381189, + "ts": 1655274525962.569, "dur": 9.870, + "args": { + "External id": 4053037,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[33554432, 8192, 2048, 1], []], "Input Dims": [[16, 4096, 4, 2048], []], "Ev Idx": 44 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select", "pid": 1336756, "tid": 1381189, + "ts": 1655274525976.782, "dur": 33.787, + "args": { + "External id": 4053038,"Record function id": 0, "Concrete Inputs": ["", "2", "3"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[33554432, 8192, 2048, 1], [], []], "Input Dims": [[16, 4096, 4, 2048], [], []], "Ev Idx": 45 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274525980.608, "dur": 28.668, + "args": { + "External id": 4053039,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]", "[33554432, 8192, 1]", "6144"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[33554432, 8192, 2048, 1], [], [], []], "Input Dims": [[16, 4096, 4, 2048], [], [], []], "Ev Idx": 46 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1381189, + "ts": 1655274526012.339, "dur": 20.528, + "args": { + "External id": 4053040,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[33554432, 8192, 1], [8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], [16, 4096, 2048], []], "Ev Idx": 47 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: SliceBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274526044.009, "dur": 107.205, + "args": { + "External id": 4053041,"Record function id": 0, "Sequence number": 40618575, "Fwd thread id": 1, "Ev Idx": 48 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SliceBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274526045.054, "dur": 103.057, + "args": { + "External id": 4053042,"Sequence number": 40618575, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[33554432, 8192, 2048, 1]], "Input Dims": [[16, 4096, 4, 2048]], "Ev Idx": 49 + } + }, + { + "ph": "f", "id": 7, "pid": 1336756, "tid": 1381189, "ts": 1655274526045.054, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 1336756, "tid": 1381189, + "ts": 1655274526049.592, "dur": 97.986, + "args": { + "External id": 4053043,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 4, 2048]", "1", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[33554432, 8192, 2048, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 4, 2048], [], [], [], [], []], "Ev Idx": 50 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros", "pid": 1336756, "tid": 1381189, + "ts": 1655274526053.856, "dur": 17.001, + "args": { + "External id": 4053044,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 4, 2048]", "15", "0", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 51 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655274526055.103, "dur": 2.756, + "args": { + "External id": 4053045,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 4, 2048]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 52 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 1336756, "tid": 1381189, + "ts": 1655274526058.636, "dur": 11.920, + "args": { + "External id": 4053046,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[33554432, 8192, 2048, 1]], "Input Dims": [[16, 4096, 4, 2048]], "Ev Idx": 53 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 1336756, "tid": 1381189, + "ts": 1655274526059.894, "dur": 10.269, + "args": { + "External id": 4053047,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[33554432, 8192, 2048, 1], []], "Input Dims": [[16, 4096, 4, 2048], []], "Ev Idx": 54 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1381189, + "ts": 1655274526074.248, "dur": 2.384, + "args": { + "External id": 4053048,"Record function id": 0, "Concrete Inputs": ["", "1", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[33554432, 8192, 2048, 1], [], [], [], []], "Input Dims": [[16, 4096, 4, 2048], [], [], [], []], "Ev Idx": 55 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274526075.622, "dur": 0.791, + "args": { + "External id": 4053049,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 4, 2048]", "[33554432, 8192, 2048, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[33554432, 8192, 2048, 1], [], [], []], "Input Dims": [[16, 4096, 4, 2048], [], [], []], "Ev Idx": 56 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1381189, + "ts": 1655274526077.384, "dur": 69.562, + "args": { + "External id": 4053050,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[33554432, 8192, 2048, 1], [33554432, 8192, 2048, 1], []], "Input Dims": [[16, 4096, 4, 2048], [16, 4096, 4, 2048], []], "Ev Idx": 57 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: SliceBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274526155.308, "dur": 89.326, + "args": { + "External id": 4053051,"Record function id": 0, "Sequence number": 40618574, "Fwd thread id": 1, "Ev Idx": 58 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SliceBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274526156.088, "dur": 85.730, + "args": { + "External id": 4053052,"Sequence number": 40618574, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[33554432, 8192, 2048, 1]], "Input Dims": [[16, 4096, 4, 2048]], "Ev Idx": 59 + } + }, + { + "ph": "f", "id": 8, "pid": 1336756, "tid": 1381189, "ts": 1655274526156.088, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 1336756, "tid": 1381189, + "ts": 1655274526157.322, "dur": 84.212, + "args": { + "External id": 4053053,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 4, 2048]", "0", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[33554432, 8192, 2048, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 4, 2048], [], [], [], [], []], "Ev Idx": 60 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros", "pid": 1336756, "tid": 1381189, + "ts": 1655274526160.638, "dur": 17.824, + "args": { + "External id": 4053054,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 4, 2048]", "15", "0", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 61 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655274526161.575, "dur": 5.276, + "args": { + "External id": 4053055,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 4, 2048]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 62 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 1336756, "tid": 1381189, + "ts": 1655274526167.834, "dur": 10.385, + "args": { + "External id": 4053056,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[33554432, 8192, 2048, 1]], "Input Dims": [[16, 4096, 4, 2048]], "Ev Idx": 63 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 1336756, "tid": 1381189, + "ts": 1655274526168.610, "dur": 9.247, + "args": { + "External id": 4053057,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[33554432, 8192, 2048, 1], []], "Input Dims": [[16, 4096, 4, 2048], []], "Ev Idx": 64 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1381189, + "ts": 1655274526179.425, "dur": 3.993, + "args": { + "External id": 4053058,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[33554432, 8192, 2048, 1], [], [], [], []], "Input Dims": [[16, 4096, 4, 2048], [], [], [], []], "Ev Idx": 65 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274526182.610, "dur": 0.680, + "args": { + "External id": 4053059,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 4, 2048]", "[33554432, 8192, 2048, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[33554432, 8192, 2048, 1], [], [], []], "Input Dims": [[16, 4096, 4, 2048], [], [], []], "Ev Idx": 66 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1381189, + "ts": 1655274526186.015, "dur": 54.810, + "args": { + "External id": 4053060,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[33554432, 8192, 2048, 1], [33554432, 8192, 2048, 1], []], "Input Dims": [[16, 4096, 4, 2048], [16, 4096, 4, 2048], []], "Ev Idx": 67 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: AddBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274526248.860, "dur": 37.911, + "args": { + "External id": 4053061,"Record function id": 0, "Sequence number": 40618573, "Fwd thread id": 1, "Ev Idx": 68 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "AddBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274526250.737, "dur": 0.913, + "args": { + "External id": 4053062,"Sequence number": 40618573, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[1]], "Ev Idx": 69 + } + }, + { + "ph": "f", "id": 9, "pid": 1336756, "tid": 1381189, "ts": 1655274526250.737, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 1336756, "tid": 1381189, + "ts": 1655274526254.326, "dur": 29.637, + "args": { + "External id": 4053063,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", ""], "Input Strides": [[1], []], "Input Dims": [[1], []], "Ev Idx": 70 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 1336756, "tid": 1381189, + "ts": 1655274526256.621, "dur": 26.897, + "args": { + "External id": 4053064,"Record function id": 0, "Concrete Inputs": ["", "[]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[1], [], [], []], "Ev Idx": 71 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274526266.452, "dur": 0.525, + "args": { + "External id": 4053065,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 72 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: FusedLinearCrossEntropyFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1655274526292.298, "dur": 2274.768, + "args": { + "External id": 4053066,"Record function id": 0, "Sequence number": 40618571, "Fwd thread id": 1, "Ev Idx": 73 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "FusedLinearCrossEntropyFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1655274526293.754, "dur": 2243.455, + "args": { + "External id": 4053067,"Sequence number": 40618571, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 74 + } + }, + { + "ph": "f", "id": 10, "pid": 1336756, "tid": 1381189, "ts": 1655274526293.754, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655274526338.254, "dur": 2.998, + "args": { + "External id": 4053068,"Record function id": 0, "Concrete Inputs": ["[]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 75 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1381189, + "ts": 1655274526344.023, "dur": 2101.350, + "args": { + "External id": 4053069,"Record function id": 0, "Concrete Inputs": ["", "", "6", "False", "False", ""], "Input type": ["float", "", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 76 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336756, "tid": 1381189, + "ts": 1655274526346.041, "dur": 2099.092, + "args": { + "External id": 4053070,"Record function id": 0, "Concrete Inputs": ["", "6", "", "", "", "False", ""], "Input type": ["float", "Scalar", "", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], []], "Ev Idx": 77 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274526348.995, "dur": 4.965, + "args": { + "External id": 4053071,"Record function id": 0, "Concrete Inputs": ["[]", "[]", "6", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 78 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1381189, + "ts": 1655274526354.971, "dur": 2088.944, + "args": { + "External id": 4053072,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[], [], []], "Input Dims": [[], [], []], "Ev Idx": 79 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::lift_fresh", "pid": 1336756, "tid": 1381189, + "ts": 1655274528448.823, "dur": 0.325, + "args": { + "External id": 4053073,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 80 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach_", "pid": 1336756, "tid": 1381189, + "ts": 1655274528452.802, "dur": 2.419, + "args": { + "External id": 4053074,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 81 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach_", "pid": 1336756, "tid": 1381189, + "ts": 1655274528454.117, "dur": 0.990, + "args": { + "External id": 4053075,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 82 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::ne", "pid": 1336756, "tid": 1381189, + "ts": 1655274528459.683, "dur": 21.376, + "args": { + "External id": 4053076,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 83 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::is_nonzero", "pid": 1336756, "tid": 1381189, + "ts": 1655274528486.522, "dur": 43.057, + "args": { + "External id": 4053077,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["bool"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 84 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::item", "pid": 1336756, "tid": 1381189, + "ts": 1655274528488.032, "dur": 41.374, + "args": { + "External id": 4053078,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["bool"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 85 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_local_scalar_dense", "pid": 1336756, "tid": 1381189, + "ts": 1655274528489.228, "dur": 39.880, + "args": { + "External id": 4053079,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["bool"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 86 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336756, "tid": 1381189, + "ts": 1655274528546.262, "dur": 17.499, + "args": { + "External id": 4053080,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[32000, 2048], [32000, 2048], []], "Ev Idx": 87 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274528575.423, "dur": 14.699, + "args": { + "External id": 4053081,"Record function id": 0, "Sequence number": 40618570, "Fwd thread id": 1, "Ev Idx": 88 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274528576.770, "dur": 11.564, + "args": { + "External id": 4053082,"Sequence number": 40618570, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[65536, 2048]], "Ev Idx": 89 + } + }, + { + "ph": "f", "id": 11, "pid": 1336756, "tid": 1381189, "ts": 1655274528576.770, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1381189, + "ts": 1655274528582.912, "dur": 5.235, + "args": { + "External id": 4053083,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 90 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274528584.348, "dur": 3.642, + "args": { + "External id": 4053084,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 91 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: SliceBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274528593.420, "dur": 59.445, + "args": { + "External id": 4053085,"Record function id": 0, "Sequence number": 40618569, "Fwd thread id": 1, "Ev Idx": 92 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SliceBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274528594.506, "dur": 54.290, + "args": { + "External id": 4053086,"Sequence number": 40618569, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 93 + } + }, + { + "ph": "f", "id": 12, "pid": 1336756, "tid": 1381189, "ts": 1655274528594.506, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 1336756, "tid": 1381189, + "ts": 1655274528596.081, "dur": 52.287, + "args": { + "External id": 4053087,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]", "2", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 2048], [], [], [], [], []], "Ev Idx": 94 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros", "pid": 1336756, "tid": 1381189, + "ts": 1655274528599.693, "dur": 18.492, + "args": { + "External id": 4053088,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 2048]", "15", "0", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 95 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655274528601.067, "dur": 2.900, + "args": { + "External id": 4053089,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 2048]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 96 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 1336756, "tid": 1381189, + "ts": 1655274528604.706, "dur": 13.200, + "args": { + "External id": 4053090,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 97 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 1336756, "tid": 1381189, + "ts": 1655274528606.025, "dur": 11.480, + "args": { + "External id": 4053091,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 98 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1381189, + "ts": 1655274528619.882, "dur": 4.996, + "args": { + "External id": 4053092,"Record function id": 0, "Concrete Inputs": ["", "2", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 1], [], [], [], []], "Input Dims": [[16, 4096, 2048], [], [], [], []], "Ev Idx": 99 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274528621.542, "dur": 3.059, + "args": { + "External id": 4053093,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]", "[8388608, 2048, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[8388608, 2048, 1], [], [], []], "Input Dims": [[16, 4096, 2048], [], [], []], "Ev Idx": 100 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1381189, + "ts": 1655274528625.746, "dur": 21.644, + "args": { + "External id": 4053094,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[8388608, 2048, 1], [8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], [16, 4096, 2048], []], "Ev Idx": 101 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: SelectBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274528659.345, "dur": 51.374, + "args": { + "External id": 4053095,"Record function id": 0, "Sequence number": 40618568, "Fwd thread id": 1, "Ev Idx": 102 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SelectBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274528660.437, "dur": 47.762, + "args": { + "External id": 4053096,"Sequence number": 40618568, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 103 + } + }, + { + "ph": "f", "id": 13, "pid": 1336756, "tid": 1381189, "ts": 1655274528660.437, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select_backward", "pid": 1336756, "tid": 1381189, + "ts": 1655274528664.230, "dur": 43.708, + "args": { + "External id": 4053097,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 4, 2048]", "2", "2"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 1], [], [], []], "Input Dims": [[16, 4096, 2048], [], [], []], "Ev Idx": 104 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros", "pid": 1336756, "tid": 1381189, + "ts": 1655274528665.605, "dur": 19.684, + "args": { + "External id": 4053098,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 4, 2048]", "15", "0", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 105 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655274528666.556, "dur": 2.330, + "args": { + "External id": 4053099,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 4, 2048]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 106 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 1336756, "tid": 1381189, + "ts": 1655274528669.325, "dur": 15.646, + "args": { + "External id": 4053100,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[33554432, 8192, 2048, 1]], "Input Dims": [[16, 4096, 4, 2048]], "Ev Idx": 107 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 1336756, "tid": 1381189, + "ts": 1655274528670.225, "dur": 14.394, + "args": { + "External id": 4053101,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[33554432, 8192, 2048, 1], []], "Input Dims": [[16, 4096, 4, 2048], []], "Ev Idx": 108 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select", "pid": 1336756, "tid": 1381189, + "ts": 1655274528686.451, "dur": 6.699, + "args": { + "External id": 4053102,"Record function id": 0, "Concrete Inputs": ["", "2", "2"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[33554432, 8192, 2048, 1], [], []], "Input Dims": [[16, 4096, 4, 2048], [], []], "Ev Idx": 109 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274528691.821, "dur": 0.833, + "args": { + "External id": 4053103,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]", "[33554432, 8192, 1]", "4096"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[33554432, 8192, 2048, 1], [], [], []], "Input Dims": [[16, 4096, 4, 2048], [], [], []], "Ev Idx": 110 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1381189, + "ts": 1655274528693.727, "dur": 13.564, + "args": { + "External id": 4053104,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[33554432, 8192, 1], [8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], [16, 4096, 2048], []], "Ev Idx": 111 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: SliceBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274528716.767, "dur": 91.381, + "args": { + "External id": 4053105,"Record function id": 0, "Sequence number": 40618567, "Fwd thread id": 1, "Ev Idx": 112 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SliceBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274528719.825, "dur": 85.531, + "args": { + "External id": 4053106,"Sequence number": 40618567, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[33554432, 8192, 2048, 1]], "Input Dims": [[16, 4096, 4, 2048]], "Ev Idx": 113 + } + }, + { + "ph": "f", "id": 14, "pid": 1336756, "tid": 1381189, "ts": 1655274528719.825, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 1336756, "tid": 1381189, + "ts": 1655274528721.175, "dur": 83.831, + "args": { + "External id": 4053107,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 4, 2048]", "1", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[33554432, 8192, 2048, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 4, 2048], [], [], [], [], []], "Ev Idx": 114 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros", "pid": 1336756, "tid": 1381189, + "ts": 1655274528722.257, "dur": 15.252, + "args": { + "External id": 4053108,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 4, 2048]", "15", "0", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 115 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655274528723.420, "dur": 2.122, + "args": { + "External id": 4053109,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 4, 2048]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 116 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 1336756, "tid": 1381189, + "ts": 1655274528725.955, "dur": 11.279, + "args": { + "External id": 4053110,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[33554432, 8192, 2048, 1]], "Input Dims": [[16, 4096, 4, 2048]], "Ev Idx": 117 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 1336756, "tid": 1381189, + "ts": 1655274528726.862, "dur": 10.084, + "args": { + "External id": 4053111,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[33554432, 8192, 2048, 1], []], "Input Dims": [[16, 4096, 4, 2048], []], "Ev Idx": 118 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1381189, + "ts": 1655274528738.501, "dur": 4.334, + "args": { + "External id": 4053112,"Record function id": 0, "Concrete Inputs": ["", "1", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[33554432, 8192, 2048, 1], [], [], [], []], "Input Dims": [[16, 4096, 4, 2048], [], [], [], []], "Ev Idx": 119 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274528742.195, "dur": 0.511, + "args": { + "External id": 4053113,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 4, 2048]", "[33554432, 8192, 2048, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[33554432, 8192, 2048, 1], [], [], []], "Input Dims": [[16, 4096, 4, 2048], [], [], []], "Ev Idx": 120 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1381189, + "ts": 1655274528743.571, "dur": 60.618, + "args": { + "External id": 4053114,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[33554432, 8192, 2048, 1], [33554432, 8192, 2048, 1], []], "Input Dims": [[16, 4096, 4, 2048], [16, 4096, 4, 2048], []], "Ev Idx": 121 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: SliceBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274528811.953, "dur": 90.369, + "args": { + "External id": 4053115,"Record function id": 0, "Sequence number": 40618566, "Fwd thread id": 1, "Ev Idx": 122 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SliceBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274528814.877, "dur": 70.552, + "args": { + "External id": 4053116,"Sequence number": 40618566, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[33554432, 8192, 2048, 1]], "Input Dims": [[16, 4096, 4, 2048]], "Ev Idx": 123 + } + }, + { + "ph": "f", "id": 15, "pid": 1336756, "tid": 1381189, "ts": 1655274528814.877, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 1336756, "tid": 1381189, + "ts": 1655274528818.127, "dur": 67.005, + "args": { + "External id": 4053117,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 4, 2048]", "0", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[33554432, 8192, 2048, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 4, 2048], [], [], [], [], []], "Ev Idx": 124 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros", "pid": 1336756, "tid": 1381189, + "ts": 1655274528819.195, "dur": 14.306, + "args": { + "External id": 4053118,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 4, 2048]", "15", "0", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 125 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655274528820.288, "dur": 1.706, + "args": { + "External id": 4053119,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 4, 2048]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 126 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 1336756, "tid": 1381189, + "ts": 1655274528822.460, "dur": 10.810, + "args": { + "External id": 4053120,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[33554432, 8192, 2048, 1]], "Input Dims": [[16, 4096, 4, 2048]], "Ev Idx": 127 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 1336756, "tid": 1381189, + "ts": 1655274528823.341, "dur": 9.635, + "args": { + "External id": 4053121,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[33554432, 8192, 2048, 1], []], "Input Dims": [[16, 4096, 4, 2048], []], "Ev Idx": 128 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1381189, + "ts": 1655274528834.241, "dur": 1.667, + "args": { + "External id": 4053122,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[33554432, 8192, 2048, 1], [], [], [], []], "Input Dims": [[16, 4096, 4, 2048], [], [], [], []], "Ev Idx": 129 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274528835.250, "dur": 0.536, + "args": { + "External id": 4053123,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 4, 2048]", "[33554432, 8192, 2048, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[33554432, 8192, 2048, 1], [], [], []], "Input Dims": [[16, 4096, 4, 2048], [], [], []], "Ev Idx": 130 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1381189, + "ts": 1655274528836.484, "dur": 48.045, + "args": { + "External id": 4053124,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[33554432, 8192, 2048, 1], [33554432, 8192, 2048, 1], []], "Input Dims": [[16, 4096, 4, 2048], [16, 4096, 4, 2048], []], "Ev Idx": 131 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336756, "tid": 1381189, + "ts": 1655274528888.670, "dur": 12.469, + "args": { + "External id": 4053125,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[33554432, 8192, 2048, 1], [33554432, 8192, 2048, 1], []], "Input Dims": [[16, 4096, 4, 2048], [16, 4096, 4, 2048], []], "Ev Idx": 132 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: AddBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274528906.418, "dur": 34.896, + "args": { + "External id": 4053126,"Record function id": 0, "Sequence number": 40618565, "Fwd thread id": 1, "Ev Idx": 133 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "AddBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274528909.214, "dur": 0.976, + "args": { + "External id": 4053127,"Sequence number": 40618565, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[1]], "Ev Idx": 134 + } + }, + { + "ph": "f", "id": 16, "pid": 1336756, "tid": 1381189, "ts": 1655274528909.214, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 1336756, "tid": 1381189, + "ts": 1655274528912.049, "dur": 26.856, + "args": { + "External id": 4053128,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", ""], "Input Strides": [[1], []], "Input Dims": [[1], []], "Ev Idx": 135 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 1336756, "tid": 1381189, + "ts": 1655274528913.955, "dur": 24.528, + "args": { + "External id": 4053129,"Record function id": 0, "Concrete Inputs": ["", "[]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[1], [], [], []], "Ev Idx": 136 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274528920.796, "dur": 2.579, + "args": { + "External id": 4053130,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 137 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: FusedLinearCrossEntropyFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1655274528945.906, "dur": 3146.761, + "args": { + "External id": 4053131,"Record function id": 0, "Sequence number": 40618563, "Fwd thread id": 1, "Ev Idx": 138 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "FusedLinearCrossEntropyFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1655274528948.841, "dur": 3118.914, + "args": { + "External id": 4053132,"Sequence number": 40618563, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 139 + } + }, + { + "ph": "f", "id": 17, "pid": 1336756, "tid": 1381189, "ts": 1655274528948.841, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655274528976.433, "dur": 3.998, + "args": { + "External id": 4053133,"Record function id": 0, "Concrete Inputs": ["[]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 140 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1381189, + "ts": 1655274529011.832, "dur": 2947.312, + "args": { + "External id": 4053134,"Record function id": 0, "Concrete Inputs": ["", "", "6", "False", "False", ""], "Input type": ["float", "", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 141 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336756, "tid": 1381189, + "ts": 1655274529013.487, "dur": 2945.403, + "args": { + "External id": 4053135,"Record function id": 0, "Concrete Inputs": ["", "6", "", "", "", "False", ""], "Input type": ["float", "Scalar", "", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], []], "Ev Idx": 142 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274529015.980, "dur": 4.784, + "args": { + "External id": 4053136,"Record function id": 0, "Concrete Inputs": ["[]", "[]", "6", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 143 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1381189, + "ts": 1655274529021.984, "dur": 2935.771, + "args": { + "External id": 4053137,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[], [], []], "Input Dims": [[], [], []], "Ev Idx": 144 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::lift_fresh", "pid": 1336756, "tid": 1381189, + "ts": 1655274531962.134, "dur": 0.419, + "args": { + "External id": 4053138,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 145 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach_", "pid": 1336756, "tid": 1381189, + "ts": 1655274531963.907, "dur": 2.051, + "args": { + "External id": 4053139,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 146 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach_", "pid": 1336756, "tid": 1381189, + "ts": 1655274531964.954, "dur": 0.883, + "args": { + "External id": 4053140,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 147 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::ne", "pid": 1336756, "tid": 1381189, + "ts": 1655274531969.523, "dur": 42.342, + "args": { + "External id": 4053141,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 148 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::is_nonzero", "pid": 1336756, "tid": 1381189, + "ts": 1655274532022.160, "dur": 38.951, + "args": { + "External id": 4053142,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["bool"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 149 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::item", "pid": 1336756, "tid": 1381189, + "ts": 1655274532023.449, "dur": 37.449, + "args": { + "External id": 4053143,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["bool"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 150 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_local_scalar_dense", "pid": 1336756, "tid": 1381189, + "ts": 1655274532024.610, "dur": 36.001, + "args": { + "External id": 4053144,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["bool"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 151 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336756, "tid": 1381189, + "ts": 1655274532075.712, "dur": 14.410, + "args": { + "External id": 4053145,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[32000, 2048], [32000, 2048], []], "Ev Idx": 152 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274532100.569, "dur": 9.787, + "args": { + "External id": 4053146,"Record function id": 0, "Sequence number": 40618562, "Fwd thread id": 1, "Ev Idx": 153 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274532101.985, "dur": 6.429, + "args": { + "External id": 4053147,"Sequence number": 40618562, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[65536, 2048]], "Ev Idx": 154 + } + }, + { + "ph": "f", "id": 18, "pid": 1336756, "tid": 1381189, "ts": 1655274532101.985, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1381189, + "ts": 1655274532104.169, "dur": 4.050, + "args": { + "External id": 4053148,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 155 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274532105.235, "dur": 2.847, + "args": { + "External id": 4053149,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 156 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: SliceBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274532113.758, "dur": 61.210, + "args": { + "External id": 4053150,"Record function id": 0, "Sequence number": 40618561, "Fwd thread id": 1, "Ev Idx": 157 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SliceBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274532114.917, "dur": 56.238, + "args": { + "External id": 4053151,"Sequence number": 40618561, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 158 + } + }, + { + "ph": "f", "id": 19, "pid": 1336756, "tid": 1381189, "ts": 1655274532114.917, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 1336756, "tid": 1381189, + "ts": 1655274532118.595, "dur": 52.207, + "args": { + "External id": 4053152,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]", "2", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 2048], [], [], [], [], []], "Ev Idx": 159 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros", "pid": 1336756, "tid": 1381189, + "ts": 1655274532122.580, "dur": 19.162, + "args": { + "External id": 4053153,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 2048]", "15", "0", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 160 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655274532123.785, "dur": 2.754, + "args": { + "External id": 4053154,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 2048]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 161 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 1336756, "tid": 1381189, + "ts": 1655274532127.526, "dur": 13.924, + "args": { + "External id": 4053155,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 162 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 1336756, "tid": 1381189, + "ts": 1655274532128.959, "dur": 12.020, + "args": { + "External id": 4053156,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 163 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1381189, + "ts": 1655274532142.825, "dur": 4.548, + "args": { + "External id": 4053157,"Record function id": 0, "Concrete Inputs": ["", "2", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 1], [], [], [], []], "Input Dims": [[16, 4096, 2048], [], [], [], []], "Ev Idx": 164 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274532146.193, "dur": 0.981, + "args": { + "External id": 4053158,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]", "[8388608, 2048, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[8388608, 2048, 1], [], [], []], "Input Dims": [[16, 4096, 2048], [], [], []], "Ev Idx": 165 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1381189, + "ts": 1655274532148.081, "dur": 21.882, + "args": { + "External id": 4053159,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[8388608, 2048, 1], [8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], [16, 4096, 2048], []], "Ev Idx": 166 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: SelectBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274532179.020, "dur": 50.094, + "args": { + "External id": 4053160,"Record function id": 0, "Sequence number": 40618560, "Fwd thread id": 1, "Ev Idx": 167 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SelectBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274532180.226, "dur": 46.182, + "args": { + "External id": 4053161,"Sequence number": 40618560, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 168 + } + }, + { + "ph": "f", "id": 20, "pid": 1336756, "tid": 1381189, "ts": 1655274532180.226, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select_backward", "pid": 1336756, "tid": 1381189, + "ts": 1655274532181.722, "dur": 44.357, + "args": { + "External id": 4053162,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 4, 2048]", "2", "1"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 1], [], [], []], "Input Dims": [[16, 4096, 2048], [], [], []], "Ev Idx": 169 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros", "pid": 1336756, "tid": 1381189, + "ts": 1655274532183.171, "dur": 17.583, + "args": { + "External id": 4053163,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 4, 2048]", "15", "0", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 170 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655274532186.135, "dur": 2.179, + "args": { + "External id": 4053164,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 4, 2048]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 171 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 1336756, "tid": 1381189, + "ts": 1655274532188.858, "dur": 11.615, + "args": { + "External id": 4053165,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[33554432, 8192, 2048, 1]], "Input Dims": [[16, 4096, 4, 2048]], "Ev Idx": 172 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 1336756, "tid": 1381189, + "ts": 1655274532189.565, "dur": 10.542, + "args": { + "External id": 4053166,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[33554432, 8192, 2048, 1], []], "Input Dims": [[16, 4096, 4, 2048], []], "Ev Idx": 173 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select", "pid": 1336756, "tid": 1381189, + "ts": 1655274532201.753, "dur": 8.857, + "args": { + "External id": 4053167,"Record function id": 0, "Concrete Inputs": ["", "2", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[33554432, 8192, 2048, 1], [], []], "Input Dims": [[16, 4096, 4, 2048], [], []], "Ev Idx": 174 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274532206.942, "dur": 3.226, + "args": { + "External id": 4053168,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]", "[33554432, 8192, 1]", "2048"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[33554432, 8192, 2048, 1], [], [], []], "Input Dims": [[16, 4096, 4, 2048], [], [], []], "Ev Idx": 175 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1381189, + "ts": 1655274532211.310, "dur": 14.292, + "args": { + "External id": 4053169,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[33554432, 8192, 1], [8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], [16, 4096, 2048], []], "Ev Idx": 176 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: SliceBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274532233.062, "dur": 90.197, + "args": { + "External id": 4053170,"Record function id": 0, "Sequence number": 40618559, "Fwd thread id": 1, "Ev Idx": 177 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SliceBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274532234.149, "dur": 86.349, + "args": { + "External id": 4053171,"Sequence number": 40618559, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[33554432, 8192, 2048, 1]], "Input Dims": [[16, 4096, 4, 2048]], "Ev Idx": 178 + } + }, + { + "ph": "f", "id": 21, "pid": 1336756, "tid": 1381189, "ts": 1655274532234.149, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 1336756, "tid": 1381189, + "ts": 1655274532235.549, "dur": 84.647, + "args": { + "External id": 4053172,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 4, 2048]", "1", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[33554432, 8192, 2048, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 4, 2048], [], [], [], [], []], "Ev Idx": 179 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros", "pid": 1336756, "tid": 1381189, + "ts": 1655274532236.490, "dur": 18.488, + "args": { + "External id": 4053173,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 4, 2048]", "15", "0", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 180 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655274532237.302, "dur": 2.041, + "args": { + "External id": 4053174,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 4, 2048]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 181 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 1336756, "tid": 1381189, + "ts": 1655274532241.928, "dur": 12.772, + "args": { + "External id": 4053175,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[33554432, 8192, 2048, 1]], "Input Dims": [[16, 4096, 4, 2048]], "Ev Idx": 182 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 1336756, "tid": 1381189, + "ts": 1655274532242.678, "dur": 11.642, + "args": { + "External id": 4053176,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[33554432, 8192, 2048, 1], []], "Input Dims": [[16, 4096, 4, 2048], []], "Ev Idx": 183 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1381189, + "ts": 1655274532255.927, "dur": 4.419, + "args": { + "External id": 4053177,"Record function id": 0, "Concrete Inputs": ["", "1", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[33554432, 8192, 2048, 1], [], [], [], []], "Input Dims": [[16, 4096, 4, 2048], [], [], [], []], "Ev Idx": 184 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274532259.401, "dur": 0.805, + "args": { + "External id": 4053178,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 4, 2048]", "[33554432, 8192, 2048, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[33554432, 8192, 2048, 1], [], [], []], "Input Dims": [[16, 4096, 4, 2048], [], [], []], "Ev Idx": 185 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1381189, + "ts": 1655274532261.131, "dur": 58.285, + "args": { + "External id": 4053179,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[33554432, 8192, 2048, 1], [33554432, 8192, 2048, 1], []], "Input Dims": [[16, 4096, 4, 2048], [16, 4096, 4, 2048], []], "Ev Idx": 186 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: SliceBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274532327.186, "dur": 112.191, + "args": { + "External id": 4053180,"Record function id": 0, "Sequence number": 40618558, "Fwd thread id": 1, "Ev Idx": 187 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SliceBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274532328.137, "dur": 79.028, + "args": { + "External id": 4053181,"Sequence number": 40618558, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[33554432, 8192, 2048, 1]], "Input Dims": [[16, 4096, 4, 2048]], "Ev Idx": 188 + } + }, + { + "ph": "f", "id": 22, "pid": 1336756, "tid": 1381189, "ts": 1655274532328.137, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 1336756, "tid": 1381189, + "ts": 1655274532331.310, "dur": 75.484, + "args": { + "External id": 4053182,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 4, 2048]", "0", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[33554432, 8192, 2048, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 4, 2048], [], [], [], [], []], "Ev Idx": 189 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros", "pid": 1336756, "tid": 1381189, + "ts": 1655274532332.409, "dur": 16.637, + "args": { + "External id": 4053183,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 4, 2048]", "15", "0", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 190 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655274532333.150, "dur": 1.893, + "args": { + "External id": 4053184,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 4, 2048]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 191 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 1336756, "tid": 1381189, + "ts": 1655274532335.733, "dur": 13.033, + "args": { + "External id": 4053185,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[33554432, 8192, 2048, 1]], "Input Dims": [[16, 4096, 4, 2048]], "Ev Idx": 192 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 1336756, "tid": 1381189, + "ts": 1655274532338.763, "dur": 9.673, + "args": { + "External id": 4053186,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[33554432, 8192, 2048, 1], []], "Input Dims": [[16, 4096, 4, 2048], []], "Ev Idx": 193 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1381189, + "ts": 1655274532350.143, "dur": 3.832, + "args": { + "External id": 4053187,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[33554432, 8192, 2048, 1], [], [], [], []], "Input Dims": [[16, 4096, 4, 2048], [], [], [], []], "Ev Idx": 194 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274532353.101, "dur": 0.715, + "args": { + "External id": 4053188,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 4, 2048]", "[33554432, 8192, 2048, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[33554432, 8192, 2048, 1], [], [], []], "Input Dims": [[16, 4096, 4, 2048], [], [], []], "Ev Idx": 195 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1381189, + "ts": 1655274532354.823, "dur": 51.364, + "args": { + "External id": 4053189,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[33554432, 8192, 2048, 1], [33554432, 8192, 2048, 1], []], "Input Dims": [[16, 4096, 4, 2048], [16, 4096, 4, 2048], []], "Ev Idx": 196 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336756, "tid": 1381189, + "ts": 1655274532410.343, "dur": 27.096, + "args": { + "External id": 4053190,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[33554432, 8192, 2048, 1], [33554432, 8192, 2048, 1], []], "Input Dims": [[16, 4096, 4, 2048], [16, 4096, 4, 2048], []], "Ev Idx": 197 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: AddBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274532447.815, "dur": 30.675, + "args": { + "External id": 4053191,"Record function id": 0, "Sequence number": 40618557, "Fwd thread id": 1, "Ev Idx": 198 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "AddBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274532449.103, "dur": 1.123, + "args": { + "External id": 4053192,"Sequence number": 40618557, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[1]], "Ev Idx": 199 + } + }, + { + "ph": "f", "id": 23, "pid": 1336756, "tid": 1381189, "ts": 1655274532449.103, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 1336756, "tid": 1381189, + "ts": 1655274532451.964, "dur": 22.059, + "args": { + "External id": 4053193,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", ""], "Input Strides": [[1], []], "Input Dims": [[1], []], "Ev Idx": 200 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 1336756, "tid": 1381189, + "ts": 1655274532453.688, "dur": 19.968, + "args": { + "External id": 4053194,"Record function id": 0, "Concrete Inputs": ["", "[]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[1], [], [], []], "Ev Idx": 201 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274532458.300, "dur": 0.583, + "args": { + "External id": 4053195,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 202 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: FusedLinearCrossEntropyFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1655274532482.779, "dur": 3104.907, + "args": { + "External id": 4053196,"Record function id": 0, "Sequence number": 40618556, "Fwd thread id": 1, "Ev Idx": 203 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "FusedLinearCrossEntropyFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1655274532493.732, "dur": 3068.529, + "args": { + "External id": 4053197,"Sequence number": 40618556, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 204 + } + }, + { + "ph": "f", "id": 24, "pid": 1336756, "tid": 1381189, "ts": 1655274532493.732, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655274532519.434, "dur": 2.155, + "args": { + "External id": 4053198,"Record function id": 0, "Concrete Inputs": ["[]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 205 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1381189, + "ts": 1655274532523.892, "dur": 2959.843, + "args": { + "External id": 4053199,"Record function id": 0, "Concrete Inputs": ["", "", "6", "False", "False", ""], "Input type": ["float", "", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 206 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336756, "tid": 1381189, + "ts": 1655274532525.340, "dur": 2958.018, + "args": { + "External id": 4053200,"Record function id": 0, "Concrete Inputs": ["", "6", "", "", "", "False", ""], "Input type": ["float", "Scalar", "", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], []], "Ev Idx": 207 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274532529.340, "dur": 3.300, + "args": { + "External id": 4053201,"Record function id": 0, "Concrete Inputs": ["[]", "[]", "6", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 208 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1381189, + "ts": 1655274532533.587, "dur": 2948.575, + "args": { + "External id": 4053202,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[], [], []], "Input Dims": [[], [], []], "Ev Idx": 209 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::lift_fresh", "pid": 1336756, "tid": 1381189, + "ts": 1655274535486.779, "dur": 0.285, + "args": { + "External id": 4053203,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 210 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach_", "pid": 1336756, "tid": 1381189, + "ts": 1655274535488.025, "dur": 1.843, + "args": { + "External id": 4053204,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 211 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach_", "pid": 1336756, "tid": 1381189, + "ts": 1655274535488.851, "dur": 0.914, + "args": { + "External id": 4053205,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 212 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::ne", "pid": 1336756, "tid": 1381189, + "ts": 1655274535493.024, "dur": 20.598, + "args": { + "External id": 4053206,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 213 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::is_nonzero", "pid": 1336756, "tid": 1381189, + "ts": 1655274535517.731, "dur": 38.584, + "args": { + "External id": 4053207,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["bool"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 214 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::item", "pid": 1336756, "tid": 1381189, + "ts": 1655274535518.703, "dur": 37.453, + "args": { + "External id": 4053208,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["bool"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 215 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_local_scalar_dense", "pid": 1336756, "tid": 1381189, + "ts": 1655274535519.913, "dur": 35.911, + "args": { + "External id": 4053209,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["bool"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 216 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336756, "tid": 1381189, + "ts": 1655274535571.394, "dur": 12.432, + "args": { + "External id": 4053210,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[32000, 2048], [32000, 2048], []], "Ev Idx": 217 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274535603.419, "dur": 11.865, + "args": { + "External id": 4053211,"Record function id": 0, "Ev Idx": 218 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274535606.018, "dur": 7.503, + "args": { + "External id": 4053212,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[32000, 2048]], "Ev Idx": 219 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274535608.888, "dur": 3.681, + "args": { + "External id": 4053213,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[32000, 2048]], "Ev Idx": 220 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274535609.472, "dur": 3.008, + "args": { + "External id": 4053214,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[32000, 2048]], "Ev Idx": 221 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274535618.892, "dur": 10.960, + "args": { + "External id": 4053215,"Record function id": 0, "Sequence number": 40618555, "Fwd thread id": 1, "Ev Idx": 222 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274535620.158, "dur": 7.737, + "args": { + "External id": 4053216,"Sequence number": 40618555, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[65536, 2048]], "Ev Idx": 223 + } + }, + { + "ph": "f", "id": 25, "pid": 1336756, "tid": 1381189, "ts": 1655274535620.158, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1381189, + "ts": 1655274535622.158, "dur": 5.532, + "args": { + "External id": 4053217,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 224 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274535625.085, "dur": 2.479, + "args": { + "External id": 4053218,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 225 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: SliceBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274535633.112, "dur": 60.730, + "args": { + "External id": 4053219,"Record function id": 0, "Sequence number": 40618554, "Fwd thread id": 1, "Ev Idx": 226 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SliceBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274535634.202, "dur": 55.655, + "args": { + "External id": 4053220,"Sequence number": 40618554, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 227 + } + }, + { + "ph": "f", "id": 26, "pid": 1336756, "tid": 1381189, "ts": 1655274535634.202, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 1336756, "tid": 1381189, + "ts": 1655274535635.668, "dur": 53.844, + "args": { + "External id": 4053221,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]", "2", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 2048], [], [], [], [], []], "Ev Idx": 228 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros", "pid": 1336756, "tid": 1381189, + "ts": 1655274535639.509, "dur": 21.293, + "args": { + "External id": 4053222,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 2048]", "15", "0", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 229 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655274535640.831, "dur": 2.572, + "args": { + "External id": 4053223,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 2048]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 230 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 1336756, "tid": 1381189, + "ts": 1655274535644.123, "dur": 16.375, + "args": { + "External id": 4053224,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 231 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 1336756, "tid": 1381189, + "ts": 1655274535645.160, "dur": 14.876, + "args": { + "External id": 4053225,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 232 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1381189, + "ts": 1655274535662.135, "dur": 5.173, + "args": { + "External id": 4053226,"Record function id": 0, "Concrete Inputs": ["", "2", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 1], [], [], [], []], "Input Dims": [[16, 4096, 2048], [], [], [], []], "Ev Idx": 233 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274535666.341, "dur": 0.740, + "args": { + "External id": 4053227,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]", "[8388608, 2048, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[8388608, 2048, 1], [], [], []], "Input Dims": [[16, 4096, 2048], [], [], []], "Ev Idx": 234 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1381189, + "ts": 1655274535667.944, "dur": 20.838, + "args": { + "External id": 4053228,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[8388608, 2048, 1], [8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], [16, 4096, 2048], []], "Ev Idx": 235 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: SelectBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274535697.960, "dur": 49.040, + "args": { + "External id": 4053229,"Record function id": 0, "Sequence number": 40618553, "Fwd thread id": 1, "Ev Idx": 236 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SelectBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274535699.021, "dur": 45.960, + "args": { + "External id": 4053230,"Sequence number": 40618553, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 237 + } + }, + { + "ph": "f", "id": 27, "pid": 1336756, "tid": 1381189, "ts": 1655274535699.021, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select_backward", "pid": 1336756, "tid": 1381189, + "ts": 1655274535700.840, "dur": 43.887, + "args": { + "External id": 4053231,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 4, 2048]", "2", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 1], [], [], []], "Input Dims": [[16, 4096, 2048], [], [], []], "Ev Idx": 238 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros", "pid": 1336756, "tid": 1381189, + "ts": 1655274535702.467, "dur": 21.955, + "args": { + "External id": 4053232,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 4, 2048]", "15", "0", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 239 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655274535709.527, "dur": 2.078, + "args": { + "External id": 4053233,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 4, 2048]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 240 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 1336756, "tid": 1381189, + "ts": 1655274535712.189, "dur": 11.978, + "args": { + "External id": 4053234,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[33554432, 8192, 2048, 1]], "Input Dims": [[16, 4096, 4, 2048]], "Ev Idx": 241 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 1336756, "tid": 1381189, + "ts": 1655274535713.117, "dur": 10.708, + "args": { + "External id": 4053235,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[33554432, 8192, 2048, 1], []], "Input Dims": [[16, 4096, 4, 2048], []], "Ev Idx": 242 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select", "pid": 1336756, "tid": 1381189, + "ts": 1655274535725.487, "dur": 4.283, + "args": { + "External id": 4053236,"Record function id": 0, "Concrete Inputs": ["", "2", "0"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[33554432, 8192, 2048, 1], [], []], "Input Dims": [[16, 4096, 4, 2048], [], []], "Ev Idx": 243 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274535728.370, "dur": 0.936, + "args": { + "External id": 4053237,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]", "[33554432, 8192, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[33554432, 8192, 2048, 1], [], [], []], "Input Dims": [[16, 4096, 4, 2048], [], [], []], "Ev Idx": 244 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1381189, + "ts": 1655274535730.432, "dur": 13.805, + "args": { + "External id": 4053238,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[33554432, 8192, 1], [8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], [16, 4096, 2048], []], "Ev Idx": 245 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: SliceBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274535751.021, "dur": 93.106, + "args": { + "External id": 4053239,"Record function id": 0, "Sequence number": 40618552, "Fwd thread id": 1, "Ev Idx": 246 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SliceBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274535752.043, "dur": 89.227, + "args": { + "External id": 4053240,"Sequence number": 40618552, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[33554432, 8192, 2048, 1]], "Input Dims": [[16, 4096, 4, 2048]], "Ev Idx": 247 + } + }, + { + "ph": "f", "id": 28, "pid": 1336756, "tid": 1381189, "ts": 1655274535752.043, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 1336756, "tid": 1381189, + "ts": 1655274535753.166, "dur": 87.785, + "args": { + "External id": 4053241,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 4, 2048]", "1", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[33554432, 8192, 2048, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 4, 2048], [], [], [], [], []], "Ev Idx": 248 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros", "pid": 1336756, "tid": 1381189, + "ts": 1655274535756.195, "dur": 16.721, + "args": { + "External id": 4053242,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 4, 2048]", "15", "0", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 249 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655274535757.214, "dur": 1.958, + "args": { + "External id": 4053243,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 4, 2048]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 250 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 1336756, "tid": 1381189, + "ts": 1655274535761.802, "dur": 10.860, + "args": { + "External id": 4053244,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[33554432, 8192, 2048, 1]], "Input Dims": [[16, 4096, 4, 2048]], "Ev Idx": 251 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 1336756, "tid": 1381189, + "ts": 1655274535762.579, "dur": 9.637, + "args": { + "External id": 4053245,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[33554432, 8192, 2048, 1], []], "Input Dims": [[16, 4096, 4, 2048], []], "Ev Idx": 252 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1381189, + "ts": 1655274535774.069, "dur": 3.987, + "args": { + "External id": 4053246,"Record function id": 0, "Concrete Inputs": ["", "1", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[33554432, 8192, 2048, 1], [], [], [], []], "Input Dims": [[16, 4096, 4, 2048], [], [], [], []], "Ev Idx": 253 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274535775.291, "dur": 2.638, + "args": { + "External id": 4053247,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 4, 2048]", "[33554432, 8192, 2048, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[33554432, 8192, 2048, 1], [], [], []], "Input Dims": [[16, 4096, 4, 2048], [], [], []], "Ev Idx": 254 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1381189, + "ts": 1655274535778.829, "dur": 61.474, + "args": { + "External id": 4053248,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[33554432, 8192, 2048, 1], [33554432, 8192, 2048, 1], []], "Input Dims": [[16, 4096, 4, 2048], [16, 4096, 4, 2048], []], "Ev Idx": 255 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: SliceBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274535848.388, "dur": 101.207, + "args": { + "External id": 4053249,"Record function id": 0, "Sequence number": 40618551, "Fwd thread id": 1, "Ev Idx": 256 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SliceBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274535849.111, "dur": 84.970, + "args": { + "External id": 4053250,"Sequence number": 40618551, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[33554432, 8192, 2048, 1]], "Input Dims": [[16, 4096, 4, 2048]], "Ev Idx": 257 + } + }, + { + "ph": "f", "id": 29, "pid": 1336756, "tid": 1381189, "ts": 1655274535849.111, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 1336756, "tid": 1381189, + "ts": 1655274535850.434, "dur": 83.323, + "args": { + "External id": 4053251,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 4, 2048]", "0", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[33554432, 8192, 2048, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 4, 2048], [], [], [], [], []], "Ev Idx": 258 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros", "pid": 1336756, "tid": 1381189, + "ts": 1655274535851.678, "dur": 31.032, + "args": { + "External id": 4053252,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 4, 2048]", "15", "0", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 259 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655274535856.262, "dur": 1.740, + "args": { + "External id": 4053253,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 4, 2048]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 260 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 1336756, "tid": 1381189, + "ts": 1655274535862.304, "dur": 20.069, + "args": { + "External id": 4053254,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[33554432, 8192, 2048, 1]], "Input Dims": [[16, 4096, 4, 2048]], "Ev Idx": 261 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 1336756, "tid": 1381189, + "ts": 1655274535867.731, "dur": 14.317, + "args": { + "External id": 4053255,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[33554432, 8192, 2048, 1], []], "Input Dims": [[16, 4096, 4, 2048], []], "Ev Idx": 262 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1381189, + "ts": 1655274535883.464, "dur": 1.665, + "args": { + "External id": 4053256,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[33554432, 8192, 2048, 1], [], [], [], []], "Input Dims": [[16, 4096, 4, 2048], [], [], [], []], "Ev Idx": 263 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274535884.528, "dur": 0.463, + "args": { + "External id": 4053257,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 4, 2048]", "[33554432, 8192, 2048, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[33554432, 8192, 2048, 1], [], [], []], "Input Dims": [[16, 4096, 4, 2048], [], [], []], "Ev Idx": 264 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1381189, + "ts": 1655274535885.870, "dur": 47.298, + "args": { + "External id": 4053258,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[33554432, 8192, 2048, 1], [33554432, 8192, 2048, 1], []], "Input Dims": [[16, 4096, 4, 2048], [16, 4096, 4, 2048], []], "Ev Idx": 265 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336756, "tid": 1381189, + "ts": 1655274535937.547, "dur": 10.354, + "args": { + "External id": 4053259,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[33554432, 8192, 2048, 1], [33554432, 8192, 2048, 1], []], "Input Dims": [[16, 4096, 4, 2048], [16, 4096, 4, 2048], []], "Ev Idx": 266 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: CompiledFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1655274535954.421, "dur": 349.450, + "args": { + "External id": 4053260,"Record function id": 0, "Sequence number": 40618550, "Fwd thread id": 1, "Ev Idx": 267 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1655274535956.202, "dur": 338.166, + "args": { + "External id": 4053261,"Sequence number": 40618550, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[33554432, 8192, 2048, 1]], "Input Dims": [[16, 4096, 4, 2048]], "Ev Idx": 268 + } + }, + { + "ph": "f", "id": 30, "pid": 1336756, "tid": 1381189, "ts": 1655274535956.202, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 1336756, "tid": 1381189, + "ts": 1655274536142.772, "dur": 38.677, + "args": { + "External id": 4053262,"kernel_hash": "coj6y6gy5rvprivwlbvxp47673cukqlcygvp5cpbrgwb4yp2fdt6", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "262144", "2048", "1", "1986", "132", "True", "2048", "False", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/oj/coj6y6gy5rvprivwlbvxp47673cukqlcygvp5cpbrgwb4yp2fdt6.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [1], [2048, 1], [2048, 1], [2048, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[262144, 2048], [2048], [262144, 2048], [262144, 2048], [132, 2048], [262144], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 269 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_0", "pid": 1336756, "tid": 1381189, + "ts": 1655274536215.194, "dur": 25.081, + "args": { + "External id": 4053263,"kernel_hash": "crljzlkpbfozvboy2akosvc2vfrg5cb56xolbkj7jk22iz5mrjtx", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "66"], "kernel_file": "/tmp/torchinductor_cvm/rl/crljzlkpbfozvboy2akosvc2vfrg5cb56xolbkj7jk22iz5mrjtx.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [4096, 1, 2048], [], []], "Input Dims": [[132, 2048], [1, 2048, 2], [], []], "Ev Idx": 270 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_1", "pid": 1336756, "tid": 1381189, + "ts": 1655274536256.599, "dur": 16.309, + "args": { + "External id": 4053264,"kernel_hash": "cwikyxkzux4tjcfntxriioajhoy22fwo4vn7g7obctqs5aqrtd3v", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "2"], "kernel_file": "/tmp/torchinductor_cvm/wi/cwikyxkzux4tjcfntxriioajhoy22fwo4vn7g7obctqs5aqrtd3v.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1, 2048], [2048, 1], [], []], "Input Dims": [[1, 2048, 2], [1, 2048], [], []], "Ev Idx": 271 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274536314.940, "dur": 12.453, + "args": { + "External id": 4053265,"Record function id": 0, "Ev Idx": 272 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274536316.871, "dur": 9.759, + "args": { + "External id": 4053266,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 273 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274536319.916, "dur": 5.951, + "args": { + "External id": 4053267,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 274 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274536322.807, "dur": 2.941, + "args": { + "External id": 4053268,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 275 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: StackBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274536331.386, "dur": 33.573, + "args": { + "External id": 4053269,"Record function id": 0, "Sequence number": 40618549, "Fwd thread id": 1, "Ev Idx": 276 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "StackBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274536332.516, "dur": 26.468, + "args": { + "External id": 4053270,"Sequence number": 40618549, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[33554432, 8192, 2048, 1]], "Input Dims": [[16, 4096, 4, 2048]], "Ev Idx": 277 + } + }, + { + "ph": "f", "id": 31, "pid": 1336756, "tid": 1381189, "ts": 1655274536332.516, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select", "pid": 1336756, "tid": 1381189, + "ts": 1655274536334.743, "dur": 7.564, + "args": { + "External id": 4053271,"Record function id": 0, "Concrete Inputs": ["", "-2", "0"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[33554432, 8192, 2048, 1], [], []], "Input Dims": [[16, 4096, 4, 2048], [], []], "Ev Idx": 278 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274536339.437, "dur": 1.234, + "args": { + "External id": 4053272,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]", "[33554432, 8192, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[33554432, 8192, 2048, 1], [], [], []], "Input Dims": [[16, 4096, 4, 2048], [], [], []], "Ev Idx": 279 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select", "pid": 1336756, "tid": 1381189, + "ts": 1655274536343.126, "dur": 6.647, + "args": { + "External id": 4053273,"Record function id": 0, "Concrete Inputs": ["", "-2", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[33554432, 8192, 2048, 1], [], []], "Input Dims": [[16, 4096, 4, 2048], [], []], "Ev Idx": 280 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274536348.709, "dur": 0.508, + "args": { + "External id": 4053274,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]", "[33554432, 8192, 1]", "2048"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[33554432, 8192, 2048, 1], [], [], []], "Input Dims": [[16, 4096, 4, 2048], [], [], []], "Ev Idx": 281 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select", "pid": 1336756, "tid": 1381189, + "ts": 1655274536350.576, "dur": 2.488, + "args": { + "External id": 4053275,"Record function id": 0, "Concrete Inputs": ["", "-2", "2"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[33554432, 8192, 2048, 1], [], []], "Input Dims": [[16, 4096, 4, 2048], [], []], "Ev Idx": 282 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274536351.932, "dur": 0.400, + "args": { + "External id": 4053276,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]", "[33554432, 8192, 1]", "4096"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[33554432, 8192, 2048, 1], [], [], []], "Input Dims": [[16, 4096, 4, 2048], [], [], []], "Ev Idx": 283 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select", "pid": 1336756, "tid": 1381189, + "ts": 1655274536353.837, "dur": 4.441, + "args": { + "External id": 4053277,"Record function id": 0, "Concrete Inputs": ["", "-2", "3"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[33554432, 8192, 2048, 1], [], []], "Input Dims": [[16, 4096, 4, 2048], [], []], "Ev Idx": 284 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274536357.023, "dur": 0.536, + "args": { + "External id": 4053278,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]", "[33554432, 8192, 1]", "6144"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[33554432, 8192, 2048, 1], [], [], []], "Input Dims": [[16, 4096, 4, 2048], [], [], []], "Ev Idx": 285 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: AddBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274536368.581, "dur": 4.623, + "args": { + "External id": 4053279,"Record function id": 0, "Sequence number": 40618548, "Fwd thread id": 1, "Ev Idx": 286 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "AddBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274536369.571, "dur": 0.994, + "args": { + "External id": 4053280,"Sequence number": 40618548, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[33554432, 8192, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 287 + } + }, + { + "ph": "f", "id": 32, "pid": 1336756, "tid": 1381189, "ts": 1655274536369.571, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: SwiGLULinearFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1655274536377.112, "dur": 487.276, + "args": { + "External id": 4053281,"Record function id": 0, "Sequence number": 40618547, "Fwd thread id": 1, "Ev Idx": 288 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SwiGLULinearFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1655274536378.151, "dur": 474.462, + "args": { + "External id": 4053282,"Sequence number": 40618547, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[33554432, 8192, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 289 + } + }, + { + "ph": "f", "id": 33, "pid": 1336756, "tid": 1381189, "ts": 1655274536378.151, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1381189, + "ts": 1655274536411.032, "dur": 28.048, + "args": { + "External id": 4053283,"Record function id": 0, "Concrete Inputs": ["", "[-1, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[33554432, 8192, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 290 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_reshape_alias", "pid": 1336756, "tid": 1381189, + "ts": 1655274536433.949, "dur": 4.506, + "args": { + "External id": 4053284,"Record function id": 0, "Concrete Inputs": ["", "[65536, 2048]", "[8192, 1]"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList"], "Input Strides": [[33554432, 8192, 1], [], []], "Input Dims": [[16, 4096, 2048], [], []], "Ev Idx": 291 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1381189, + "ts": 1655274536444.558, "dur": 6.144, + "args": { + "External id": 4053285,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 292 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1381189, + "ts": 1655274536447.247, "dur": 2.586, + "args": { + "External id": 4053286,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[5632, 1], [], []], "Input Dims": [[2048, 5632], [], []], "Ev Idx": 293 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274536448.900, "dur": 0.702, + "args": { + "External id": 4053287,"Record function id": 0, "Concrete Inputs": ["", "[5632, 2048]", "[1, 5632]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[5632, 1], [], [], []], "Input Dims": [[2048, 5632], [], [], []], "Ev Idx": 294 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336756, "tid": 1381189, + "ts": 1655274536457.106, "dur": 121.000, + "args": { + "External id": 4053288,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[8192, 1], [1, 5632], []], "Input Dims": [[65536, 2048], [5632, 2048], []], "Ev Idx": 295 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1381189, + "ts": 1655274536458.089, "dur": 7.123, + "args": { + "External id": 4053289,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 5632]], "Input Dims": [[5632, 2048]], "Ev Idx": 296 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1381189, + "ts": 1655274536458.783, "dur": 5.633, + "args": { + "External id": 4053290,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 5632], [], []], "Input Dims": [[5632, 2048], [], []], "Ev Idx": 297 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274536461.793, "dur": 2.476, + "args": { + "External id": 4053291,"Record function id": 0, "Concrete Inputs": ["", "[2048, 5632]", "[5632, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 5632], [], [], []], "Input Dims": [[5632, 2048], [], [], []], "Ev Idx": 298 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336756, "tid": 1381189, + "ts": 1655274536466.805, "dur": 110.499, + "args": { + "External id": 4053292,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[8192, 1], [5632, 1]], "Input Dims": [[65536, 2048], [2048, 5632]], "Ev Idx": 299 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655274536468.614, "dur": 107.558, + "args": { + "External id": 4053293,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[8192, 1], [5632, 1]], "Input Dims": [[65536, 2048], [2048, 5632]], "Ev Idx": 300 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 1336756, "tid": 1381189, + "ts": 1655274536582.782, "dur": 6.978, + "args": { + "External id": 4053294,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [23068672, 5632, 1]], "Input Dims": [[65536, 5632], [16, 4096, 5632]], "Ev Idx": 301 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274536587.119, "dur": 2.527, + "args": { + "External id": 4053295,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 5632]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[5632, 1], []], "Input Dims": [[65536, 5632], []], "Ev Idx": 302 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655274536620.540, "dur": 5.055, + "args": { + "External id": 4053296,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 5632]", "15", "", "", "", "0"], "Input type": ["ScalarList", "Scalar", "", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 303 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655274536626.896, "dur": 2.748, + "args": { + "External id": 4053297,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 5632]", "15", "", "", "", "0"], "Input type": ["ScalarList", "Scalar", "", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 304 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655274536632.350, "dur": 1.580, + "args": { + "External id": 4053298,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 5632]", "15", "", "", "", "0"], "Input type": ["ScalarList", "Scalar", "", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 305 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1381189, + "ts": 1655274536667.496, "dur": 2.169, + "args": { + "External id": 4053299,"Record function id": 0, "Concrete Inputs": ["", "[-1, 5632]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[23068672, 5632, 1], []], "Input Dims": [[16, 4096, 5632], []], "Ev Idx": 306 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274536668.205, "dur": 1.294, + "args": { + "External id": 4053300,"Record function id": 0, "Concrete Inputs": ["", "[-1, 5632]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[23068672, 5632, 1], []], "Input Dims": [[16, 4096, 5632], []], "Ev Idx": 307 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::einsum", "pid": 1336756, "tid": 1381189, + "ts": 1655274536694.690, "dur": 137.227, + "args": { + "External id": 4053301,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["", "TensorList", ""], "Input Strides": [[], [[8192, 1], [5632, 1]], []], "Input Dims": [[], [[65536, 2048], [65536, 5632]], []], "Ev Idx": 308 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1381189, + "ts": 1655274536701.723, "dur": 8.195, + "args": { + "External id": 4053302,"Record function id": 0, "Concrete Inputs": ["", "2"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[8192, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 309 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274536706.887, "dur": 0.920, + "args": { + "External id": 4053303,"Record function id": 0, "Concrete Inputs": ["", "[65536, 2048, 1]", "[8192, 1, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[8192, 1], [], [], []], "Input Dims": [[65536, 2048], [], [], []], "Ev Idx": 310 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::permute", "pid": 1336756, "tid": 1381189, + "ts": 1655274536711.799, "dur": 7.383, + "args": { + "External id": 4053304,"Record function id": 0, "Concrete Inputs": ["", "[1, 2, 0]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8192, 1, 1], []], "Input Dims": [[65536, 2048, 1], []], "Ev Idx": 311 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274536716.034, "dur": 2.476, + "args": { + "External id": 4053305,"Record function id": 0, "Concrete Inputs": ["", "[2048, 1, 65536]", "[1, 1, 8192]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[8192, 1, 1], [], [], []], "Input Dims": [[65536, 2048, 1], [], [], []], "Ev Idx": 312 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1381189, + "ts": 1655274536720.925, "dur": 4.061, + "args": { + "External id": 4053306,"Record function id": 0, "Concrete Inputs": ["", "2"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[5632, 1], []], "Input Dims": [[65536, 5632], []], "Ev Idx": 313 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274536724.064, "dur": 0.572, + "args": { + "External id": 4053307,"Record function id": 0, "Concrete Inputs": ["", "[65536, 5632, 1]", "[5632, 1, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[5632, 1], [], [], []], "Input Dims": [[65536, 5632], [], [], []], "Ev Idx": 314 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::permute", "pid": 1336756, "tid": 1381189, + "ts": 1655274536725.776, "dur": 4.416, + "args": { + "External id": 4053308,"Record function id": 0, "Concrete Inputs": ["", "[2, 1, 0]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[5632, 1, 1], []], "Input Dims": [[65536, 5632, 1], []], "Ev Idx": 315 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274536728.999, "dur": 0.675, + "args": { + "External id": 4053309,"Record function id": 0, "Concrete Inputs": ["", "[1, 5632, 65536]", "[1, 1, 5632]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[5632, 1, 1], [], [], []], "Input Dims": [[65536, 5632, 1], [], [], []], "Ev Idx": 316 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::permute", "pid": 1336756, "tid": 1381189, + "ts": 1655274536734.553, "dur": 4.421, + "args": { + "External id": 4053310,"Record function id": 0, "Concrete Inputs": ["", "[0, 2, 1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1, 1, 8192], []], "Input Dims": [[2048, 1, 65536], []], "Ev Idx": 317 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274536738.034, "dur": 0.644, + "args": { + "External id": 4053311,"Record function id": 0, "Concrete Inputs": ["", "[2048, 65536, 1]", "[1, 8192, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1, 8192], [], [], []], "Input Dims": [[2048, 1, 65536], [], [], []], "Ev Idx": 318 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1381189, + "ts": 1655274536741.771, "dur": 7.160, + "args": { + "External id": 4053312,"Record function id": 0, "Concrete Inputs": ["", "[1, 2048, 65536]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1, 8192, 1], []], "Input Dims": [[2048, 65536, 1], []], "Ev Idx": 319 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_reshape_alias", "pid": 1336756, "tid": 1381189, + "ts": 1655274536747.176, "dur": 1.561, + "args": { + "External id": 4053313,"Record function id": 0, "Concrete Inputs": ["", "[1, 2048, 65536]", "[2048, 1, 8192]"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList"], "Input Strides": [[1, 8192, 1], [], []], "Input Dims": [[2048, 65536, 1], [], []], "Ev Idx": 320 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::permute", "pid": 1336756, "tid": 1381189, + "ts": 1655274536749.733, "dur": 3.966, + "args": { + "External id": 4053314,"Record function id": 0, "Concrete Inputs": ["", "[2, 1, 0]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1, 1, 5632], []], "Input Dims": [[1, 5632, 65536], []], "Ev Idx": 321 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274536752.828, "dur": 0.557, + "args": { + "External id": 4053315,"Record function id": 0, "Concrete Inputs": ["", "[65536, 5632, 1]", "[5632, 1, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1, 5632], [], [], []], "Input Dims": [[1, 5632, 65536], [], [], []], "Ev Idx": 322 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1381189, + "ts": 1655274536754.571, "dur": 1.968, + "args": { + "External id": 4053316,"Record function id": 0, "Concrete Inputs": ["", "[1, 65536, 5632]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[5632, 1, 1], []], "Input Dims": [[65536, 5632, 1], []], "Ev Idx": 323 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274536755.304, "dur": 1.144, + "args": { + "External id": 4053317,"Record function id": 0, "Concrete Inputs": ["", "[1, 65536, 5632]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[5632, 1, 1], []], "Input Dims": [[65536, 5632, 1], []], "Ev Idx": 324 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 1336756, "tid": 1381189, + "ts": 1655274536758.300, "dur": 58.184, + "args": { + "External id": 4053318,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1, 8192], [369098752, 5632, 1]], "Input Dims": [[1, 2048, 65536], [1, 65536, 5632]], "Ev Idx": 325 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274536818.655, "dur": 3.363, + "args": { + "External id": 4053319,"Record function id": 0, "Concrete Inputs": ["", "[2048, 1, 5632]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[11534336, 5632, 1], []], "Input Dims": [[1, 2048, 5632], []], "Ev Idx": 326 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::permute", "pid": 1336756, "tid": 1381189, + "ts": 1655274536825.120, "dur": 2.373, + "args": { + "External id": 4053320,"Record function id": 0, "Concrete Inputs": ["", "[0, 2, 1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[5632, 5632, 1], []], "Input Dims": [[2048, 1, 5632], []], "Ev Idx": 327 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274536826.342, "dur": 0.654, + "args": { + "External id": 4053321,"Record function id": 0, "Concrete Inputs": ["", "[2048, 5632, 1]", "[5632, 1, 5632]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[5632, 5632, 1], [], [], []], "Input Dims": [[2048, 1, 5632], [], [], []], "Ev Idx": 328 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274536829.660, "dur": 0.924, + "args": { + "External id": 4053322,"Record function id": 0, "Concrete Inputs": ["", "[2048, 5632]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[5632, 1, 5632], []], "Input Dims": [[2048, 5632, 1], []], "Ev Idx": 329 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274536876.438, "dur": 9.924, + "args": { + "External id": 4053323,"Record function id": 0, "Ev Idx": 330 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274536878.594, "dur": 6.990, + "args": { + "External id": 4053324,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 331 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274536881.103, "dur": 3.697, + "args": { + "External id": 4053325,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 332 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274536882.232, "dur": 2.439, + "args": { + "External id": 4053326,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 333 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: UnsafeViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274536890.586, "dur": 8.629, + "args": { + "External id": 4053327,"Record function id": 0, "Sequence number": 40618546, "Fwd thread id": 1, "Ev Idx": 334 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274536891.518, "dur": 5.651, + "args": { + "External id": 4053328,"Sequence number": 40618546, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[23068672, 5632, 1]], "Input Dims": [[16, 4096, 5632]], "Ev Idx": 335 + } + }, + { + "ph": "f", "id": 34, "pid": 1336756, "tid": 1381189, "ts": 1655274536891.518, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1381189, + "ts": 1655274536895.101, "dur": 1.889, + "args": { + "External id": 4053329,"Record function id": 0, "Concrete Inputs": ["", "[65536, 5632]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[23068672, 5632, 1], []], "Input Dims": [[16, 4096, 5632], []], "Ev Idx": 336 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274536896.042, "dur": 0.815, + "args": { + "External id": 4053330,"Record function id": 0, "Concrete Inputs": ["", "[65536, 5632]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[23068672, 5632, 1], []], "Input Dims": [[16, 4096, 5632], []], "Ev Idx": 337 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: MmBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274536903.402, "dur": 215.975, + "args": { + "External id": 4053331,"Record function id": 0, "Sequence number": 40618545, "Fwd thread id": 1, "Ev Idx": 338 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274536904.213, "dur": 206.672, + "args": { + "External id": 4053332,"Sequence number": 40618545, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[65536, 5632]], "Ev Idx": 339 + } + }, + { + "ph": "f", "id": 35, "pid": 1336756, "tid": 1381189, "ts": 1655274536904.213, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1381189, + "ts": 1655274536909.723, "dur": 4.409, + "args": { + "External id": 4053333,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[65536, 5632]], "Ev Idx": 340 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1381189, + "ts": 1655274536911.319, "dur": 2.261, + "args": { + "External id": 4053334,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[5632, 1], [], []], "Input Dims": [[65536, 5632], [], []], "Ev Idx": 341 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274536912.591, "dur": 0.802, + "args": { + "External id": 4053335,"Record function id": 0, "Concrete Inputs": ["", "[5632, 65536]", "[1, 5632]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[5632, 1], [], [], []], "Input Dims": [[65536, 5632], [], [], []], "Ev Idx": 342 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655274536915.514, "dur": 56.679, + "args": { + "External id": 4053336,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 5632], [2048, 1]], "Input Dims": [[5632, 65536], [65536, 2048]], "Ev Idx": 343 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1381189, + "ts": 1655274536973.509, "dur": 6.250, + "args": { + "External id": 4053337,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 344 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1381189, + "ts": 1655274536974.519, "dur": 4.543, + "args": { + "External id": 4053338,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[5632, 2048], [], []], "Ev Idx": 345 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274536977.847, "dur": 1.026, + "args": { + "External id": 4053339,"Record function id": 0, "Concrete Inputs": ["", "[2048, 5632]", "[1, 2048]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[5632, 2048], [], [], []], "Ev Idx": 346 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1381189, + "ts": 1655274537019.320, "dur": 6.168, + "args": { + "External id": 4053340,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 2048]], "Input Dims": [[2048, 5632]], "Ev Idx": 347 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1381189, + "ts": 1655274537020.417, "dur": 4.408, + "args": { + "External id": 4053341,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 2048], [], []], "Input Dims": [[2048, 5632], [], []], "Ev Idx": 348 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274537023.879, "dur": 0.657, + "args": { + "External id": 4053342,"Record function id": 0, "Concrete Inputs": ["", "[5632, 2048]", "[2048, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 2048], [], [], []], "Input Dims": [[2048, 5632], [], [], []], "Ev Idx": 349 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655274537026.281, "dur": 83.419, + "args": { + "External id": 4053343,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [2048, 1]], "Input Dims": [[65536, 5632], [5632, 2048]], "Ev Idx": 350 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274537126.103, "dur": 6.945, + "args": { + "External id": 4053344,"Record function id": 0, "Sequence number": 40618544, "Fwd thread id": 1, "Ev Idx": 351 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274537127.388, "dur": 4.074, + "args": { + "External id": 4053345,"Sequence number": 40618544, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[65536, 2048]], "Ev Idx": 352 + } + }, + { + "ph": "f", "id": 36, "pid": 1336756, "tid": 1381189, "ts": 1655274537127.388, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1381189, + "ts": 1655274537128.966, "dur": 2.345, + "args": { + "External id": 4053346,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 353 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274537129.878, "dur": 1.249, + "args": { + "External id": 4053347,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 354 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: TBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274537136.594, "dur": 10.816, + "args": { + "External id": 4053348,"Record function id": 0, "Sequence number": 40618543, "Fwd thread id": 1, "Ev Idx": 355 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274537139.361, "dur": 5.974, + "args": { + "External id": 4053349,"Sequence number": 40618543, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 2048]], "Input Dims": [[2048, 5632]], "Ev Idx": 356 + } + }, + { + "ph": "f", "id": 37, "pid": 1336756, "tid": 1381189, "ts": 1655274537139.361, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1381189, + "ts": 1655274537140.237, "dur": 4.878, + "args": { + "External id": 4053350,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 2048]], "Input Dims": [[2048, 5632]], "Ev Idx": 357 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1381189, + "ts": 1655274537141.031, "dur": 3.619, + "args": { + "External id": 4053351,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 2048], [], []], "Input Dims": [[2048, 5632], [], []], "Ev Idx": 358 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274537143.918, "dur": 0.653, + "args": { + "External id": 4053352,"Record function id": 0, "Concrete Inputs": ["", "[5632, 2048]", "[2048, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 2048], [], [], []], "Input Dims": [[2048, 5632], [], [], []], "Ev Idx": 359 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274537151.517, "dur": 6.113, + "args": { + "External id": 4053353,"Record function id": 0, "Ev Idx": 360 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274537152.716, "dur": 4.384, + "args": { + "External id": 4053354,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 361 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274537154.202, "dur": 2.622, + "args": { + "External id": 4053355,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 362 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274537154.958, "dur": 1.725, + "args": { + "External id": 4053356,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 363 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: UnsafeViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274537162.632, "dur": 7.224, + "args": { + "External id": 4053357,"Record function id": 0, "Sequence number": 40618542, "Fwd thread id": 1, "Ev Idx": 364 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274537163.538, "dur": 4.406, + "args": { + "External id": 4053358,"Sequence number": 40618542, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[23068672, 5632, 1]], "Input Dims": [[16, 4096, 5632]], "Ev Idx": 365 + } + }, + { + "ph": "f", "id": 38, "pid": 1336756, "tid": 1381189, "ts": 1655274537163.538, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1381189, + "ts": 1655274537164.503, "dur": 3.300, + "args": { + "External id": 4053359,"Record function id": 0, "Concrete Inputs": ["", "[65536, 5632]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[23068672, 5632, 1], []], "Input Dims": [[16, 4096, 5632], []], "Ev Idx": 366 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274537166.785, "dur": 0.911, + "args": { + "External id": 4053360,"Record function id": 0, "Concrete Inputs": ["", "[65536, 5632]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[23068672, 5632, 1], []], "Input Dims": [[16, 4096, 5632], []], "Ev Idx": 367 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: MmBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274537173.159, "dur": 153.629, + "args": { + "External id": 4053361,"Record function id": 0, "Sequence number": 40618541, "Fwd thread id": 1, "Ev Idx": 368 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274537173.982, "dur": 145.788, + "args": { + "External id": 4053362,"Sequence number": 40618541, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[65536, 5632]], "Ev Idx": 369 + } + }, + { + "ph": "f", "id": 39, "pid": 1336756, "tid": 1381189, "ts": 1655274537173.982, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1381189, + "ts": 1655274537176.182, "dur": 2.685, + "args": { + "External id": 4053363,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[65536, 5632]], "Ev Idx": 370 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1381189, + "ts": 1655274537177.007, "dur": 1.457, + "args": { + "External id": 4053364,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[5632, 1], [], []], "Input Dims": [[65536, 5632], [], []], "Ev Idx": 371 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274537177.863, "dur": 0.495, + "args": { + "External id": 4053365,"Record function id": 0, "Concrete Inputs": ["", "[5632, 65536]", "[1, 5632]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[5632, 1], [], [], []], "Input Dims": [[65536, 5632], [], [], []], "Ev Idx": 372 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655274537181.879, "dur": 49.007, + "args": { + "External id": 4053366,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 5632], [2048, 1]], "Input Dims": [[5632, 65536], [65536, 2048]], "Ev Idx": 373 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1381189, + "ts": 1655274537231.802, "dur": 5.405, + "args": { + "External id": 4053367,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 374 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1381189, + "ts": 1655274537232.479, "dur": 4.242, + "args": { + "External id": 4053368,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[5632, 2048], [], []], "Ev Idx": 375 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274537235.719, "dur": 0.884, + "args": { + "External id": 4053369,"Record function id": 0, "Concrete Inputs": ["", "[2048, 5632]", "[1, 2048]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[5632, 2048], [], [], []], "Ev Idx": 376 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1381189, + "ts": 1655274537238.458, "dur": 6.705, + "args": { + "External id": 4053370,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 2048]], "Input Dims": [[2048, 5632]], "Ev Idx": 377 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1381189, + "ts": 1655274537239.364, "dur": 5.386, + "args": { + "External id": 4053371,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 2048], [], []], "Input Dims": [[2048, 5632], [], []], "Ev Idx": 378 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274537242.361, "dur": 2.316, + "args": { + "External id": 4053372,"Record function id": 0, "Concrete Inputs": ["", "[5632, 2048]", "[2048, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 2048], [], [], []], "Input Dims": [[2048, 5632], [], [], []], "Ev Idx": 379 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655274537245.897, "dur": 73.274, + "args": { + "External id": 4053373,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [2048, 1]], "Input Dims": [[65536, 5632], [5632, 2048]], "Ev Idx": 380 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274537331.230, "dur": 34.602, + "args": { + "External id": 4053374,"Record function id": 0, "Sequence number": 40618540, "Fwd thread id": 1, "Ev Idx": 381 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274537332.145, "dur": 5.295, + "args": { + "External id": 4053375,"Sequence number": 40618540, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[65536, 2048]], "Ev Idx": 382 + } + }, + { + "ph": "f", "id": 40, "pid": 1336756, "tid": 1381189, "ts": 1655274537332.145, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1381189, + "ts": 1655274537333.320, "dur": 3.974, + "args": { + "External id": 4053376,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 383 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274537336.135, "dur": 1.032, + "args": { + "External id": 4053377,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 384 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add", "pid": 1336756, "tid": 1381189, + "ts": 1655274537340.487, "dur": 22.730, + "args": { + "External id": 4053378,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[8388608, 2048, 1], [8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], [16, 4096, 2048], []], "Ev Idx": 385 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: TBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274537369.489, "dur": 8.908, + "args": { + "External id": 4053379,"Record function id": 0, "Sequence number": 40618539, "Fwd thread id": 1, "Ev Idx": 386 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274537370.465, "dur": 6.109, + "args": { + "External id": 4053380,"Sequence number": 40618539, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 2048]], "Input Dims": [[2048, 5632]], "Ev Idx": 387 + } + }, + { + "ph": "f", "id": 41, "pid": 1336756, "tid": 1381189, "ts": 1655274537370.465, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1381189, + "ts": 1655274537371.395, "dur": 4.952, + "args": { + "External id": 4053381,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 2048]], "Input Dims": [[2048, 5632]], "Ev Idx": 388 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1381189, + "ts": 1655274537374.094, "dur": 1.784, + "args": { + "External id": 4053382,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 2048], [], []], "Input Dims": [[2048, 5632], [], []], "Ev Idx": 389 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274537375.323, "dur": 0.446, + "args": { + "External id": 4053383,"Record function id": 0, "Concrete Inputs": ["", "[5632, 2048]", "[2048, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 2048], [], [], []], "Input Dims": [[2048, 5632], [], [], []], "Ev Idx": 390 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274537382.465, "dur": 5.345, + "args": { + "External id": 4053384,"Record function id": 0, "Ev Idx": 391 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274537383.725, "dur": 3.464, + "args": { + "External id": 4053385,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 392 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274537384.730, "dur": 1.960, + "args": { + "External id": 4053386,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 393 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274537385.268, "dur": 1.340, + "args": { + "External id": 4053387,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 394 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: LayerNormFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1655274537392.019, "dur": 435.615, + "args": { + "External id": 4053388,"Record function id": 0, "Sequence number": 40618538, "Fwd thread id": 1, "Ev Idx": 395 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1655274537393.311, "dur": 420.173, + "args": { + "External id": 4053389,"Sequence number": 40618538, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[8388608, 2048, 1], [33554432, 8192, 1]], "Input Dims": [[16, 4096, 2048], [16, 4096, 2048]], "Ev Idx": 396 + } + }, + { + "ph": "f", "id": 42, "pid": 1336756, "tid": 1381189, "ts": 1655274537393.311, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::contiguous", "pid": 1336756, "tid": 1381189, + "ts": 1655274537435.178, "dur": 38.692, + "args": { + "External id": 4053390,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[33554432, 8192, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 397 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 1336756, "tid": 1381189, + "ts": 1655274537436.914, "dur": 36.695, + "args": { + "External id": 4053391,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[33554432, 8192, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 398 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336756, "tid": 1381189, + "ts": 1655274537440.097, "dur": 7.118, + "args": { + "External id": 4053392,"Record function id": 0, "Concrete Inputs": ["", "15", "0", "", "", "0"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[33554432, 8192, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 2048], [], [], [], [], []], "Ev Idx": 399 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655274537442.820, "dur": 3.667, + "args": { + "External id": 4053393,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 2048]", "15", "0", "", "", "0"], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 400 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1381189, + "ts": 1655274537448.582, "dur": 24.484, + "args": { + "External id": 4053394,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[8388608, 2048, 1], [33554432, 8192, 1], []], "Input Dims": [[16, 4096, 2048], [16, 4096, 2048], []], "Ev Idx": 401 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1381189, + "ts": 1655274537485.533, "dur": 4.539, + "args": { + "External id": 4053395,"Record function id": 0, "Concrete Inputs": ["", "[-1, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 402 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274537488.301, "dur": 1.641, + "args": { + "External id": 4053396,"Record function id": 0, "Concrete Inputs": ["", "[-1, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 403 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1381189, + "ts": 1655274537493.865, "dur": 3.723, + "args": { + "External id": 4053397,"Record function id": 0, "Concrete Inputs": ["", "[-1, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 404 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274537494.606, "dur": 2.881, + "args": { + "External id": 4053398,"Record function id": 0, "Concrete Inputs": ["", "[-1, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 405 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655274537512.351, "dur": 2.388, + "args": { + "External id": 4053399,"Record function id": 0, "Concrete Inputs": ["[65536, 2048]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 406 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655274537528.079, "dur": 3.330, + "args": { + "External id": 4053400,"Record function id": 0, "Concrete Inputs": ["[132, 2048]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 407 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274537701.710, "dur": 3.067, + "args": { + "External id": 4053401,"Record function id": 0, "Concrete Inputs": ["", "[1, -1, 2048]"], "Input type": ["float", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[132, 2048], []], "Ev Idx": 408 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 1336756, "tid": 1381189, + "ts": 1655274537708.890, "dur": 36.715, + "args": { + "External id": 4053402,"Record function id": 0, "Concrete Inputs": ["", "[1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", ""], "Input Strides": [[270336, 2048, 1], [], [], []], "Input Dims": [[1, 132, 2048], [], [], []], "Ev Idx": 409 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274537720.355, "dur": 1.241, + "args": { + "External id": 4053403,"Record function id": 0, "Concrete Inputs": ["", "[1, 1, 2048]", "[2048, 0, 1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[1, 2048], [], [], []], "Ev Idx": 410 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1381189, + "ts": 1655274537751.300, "dur": 27.588, + "args": { + "External id": 4053404,"Record function id": 0, "Concrete Inputs": ["", "", "15", "False", "False", ""], "Input type": ["float", "", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[2048, 1], [], [], [], [], []], "Input Dims": [[1, 2048], [], [], [], [], []], "Ev Idx": 411 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336756, "tid": 1381189, + "ts": 1655274537753.017, "dur": 25.680, + "args": { + "External id": 4053405,"Record function id": 0, "Concrete Inputs": ["", "15", "", "", "", "False", ""], "Input type": ["float", "Scalar", "", "", "", "Scalar", ""], "Input Strides": [[2048, 1], [], [], [], [], [], []], "Input Dims": [[1, 2048], [], [], [], [], [], []], "Ev Idx": 412 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274537756.848, "dur": 3.793, + "args": { + "External id": 4053406,"Record function id": 0, "Concrete Inputs": ["[1, 2048]", "[2048, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 413 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1381189, + "ts": 1655274537762.887, "dur": 15.190, + "args": { + "External id": 4053407,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "float", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[1, 2048], [1, 2048], []], "Ev Idx": 414 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 1336756, "tid": 1381189, + "ts": 1655274537786.082, "dur": 2.454, + "args": { + "External id": 4053408,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1]], "Input Dims": [[1, 2048], [2048]], "Ev Idx": 415 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274537787.283, "dur": 1.087, + "args": { + "External id": 4053409,"Record function id": 0, "Concrete Inputs": ["", "[2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[1, 2048], []], "Ev Idx": 416 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1381189, + "ts": 1655274537794.744, "dur": 4.287, + "args": { + "External id": 4053410,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 417 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274537797.579, "dur": 1.338, + "args": { + "External id": 4053411,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 418 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1381189, + "ts": 1655274537800.983, "dur": 3.633, + "args": { + "External id": 4053412,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 419 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274537801.739, "dur": 2.778, + "args": { + "External id": 4053413,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 420 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274537841.700, "dur": 10.157, + "args": { + "External id": 4053414,"Record function id": 0, "Ev Idx": 421 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274537844.353, "dur": 6.754, + "args": { + "External id": 4053415,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 422 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274537846.744, "dur": 3.476, + "args": { + "External id": 4053416,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 423 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274537847.963, "dur": 2.132, + "args": { + "External id": 4053417,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 424 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: UnsafeViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274537855.685, "dur": 10.167, + "args": { + "External id": 4053418,"Record function id": 0, "Sequence number": 40618537, "Fwd thread id": 1, "Ev Idx": 425 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274537856.671, "dur": 5.829, + "args": { + "External id": 4053419,"Sequence number": 40618537, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 426 + } + }, + { + "ph": "f", "id": 43, "pid": 1336756, "tid": 1381189, "ts": 1655274537856.671, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1381189, + "ts": 1655274537860.117, "dur": 2.220, + "args": { + "External id": 4053420,"Record function id": 0, "Concrete Inputs": ["", "[65536, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 427 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274537860.937, "dur": 1.269, + "args": { + "External id": 4053421,"Record function id": 0, "Concrete Inputs": ["", "[65536, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 428 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: MmBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274537871.423, "dur": 185.346, + "args": { + "External id": 4053422,"Record function id": 0, "Sequence number": 40618536, "Fwd thread id": 1, "Ev Idx": 429 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274537872.207, "dur": 179.407, + "args": { + "External id": 4053423,"Sequence number": 40618536, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[65536, 2048]], "Ev Idx": 430 + } + }, + { + "ph": "f", "id": 44, "pid": 1336756, "tid": 1381189, "ts": 1655274537872.207, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1381189, + "ts": 1655274537875.579, "dur": 4.329, + "args": { + "External id": 4053424,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[65536, 2048]], "Ev Idx": 431 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1381189, + "ts": 1655274537877.090, "dur": 2.215, + "args": { + "External id": 4053425,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[65536, 2048], [], []], "Ev Idx": 432 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274537878.430, "dur": 0.693, + "args": { + "External id": 4053426,"Record function id": 0, "Concrete Inputs": ["", "[2048, 65536]", "[1, 2048]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[65536, 2048], [], [], []], "Ev Idx": 433 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655274537881.132, "dur": 59.080, + "args": { + "External id": 4053427,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048]], "Ev Idx": 434 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1381189, + "ts": 1655274537941.453, "dur": 6.660, + "args": { + "External id": 4053428,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 435 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1381189, + "ts": 1655274537944.219, "dur": 3.315, + "args": { + "External id": 4053429,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[2048, 2048], [], []], "Ev Idx": 436 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274537945.548, "dur": 1.818, + "args": { + "External id": 4053430,"Record function id": 0, "Concrete Inputs": ["", "[2048, 2048]", "[1, 2048]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[2048, 2048], [], [], []], "Ev Idx": 437 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1381189, + "ts": 1655274537949.715, "dur": 4.550, + "args": { + "External id": 4053431,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 2048]], "Input Dims": [[2048, 2048]], "Ev Idx": 438 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1381189, + "ts": 1655274537950.687, "dur": 3.172, + "args": { + "External id": 4053432,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 2048], [], []], "Input Dims": [[2048, 2048], [], []], "Ev Idx": 439 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274537953.472, "dur": 0.307, + "args": { + "External id": 4053433,"Record function id": 0, "Concrete Inputs": ["", "[2048, 2048]", "[2048, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 2048], [], [], []], "Input Dims": [[2048, 2048], [], [], []], "Ev Idx": 440 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655274537954.779, "dur": 94.890, + "args": { + "External id": 4053434,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048]], "Ev Idx": 441 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274538064.922, "dur": 13.061, + "args": { + "External id": 4053435,"Record function id": 0, "Sequence number": 40618535, "Fwd thread id": 1, "Ev Idx": 442 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274538066.469, "dur": 9.194, + "args": { + "External id": 4053436,"Sequence number": 40618535, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[65536, 2048]], "Ev Idx": 443 + } + }, + { + "ph": "f", "id": 45, "pid": 1336756, "tid": 1381189, "ts": 1655274538066.469, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1381189, + "ts": 1655274538070.749, "dur": 4.761, + "args": { + "External id": 4053437,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 444 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274538071.734, "dur": 3.678, + "args": { + "External id": 4053438,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 445 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: TBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274538081.579, "dur": 9.810, + "args": { + "External id": 4053439,"Record function id": 0, "Sequence number": 40618534, "Fwd thread id": 1, "Ev Idx": 446 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274538082.715, "dur": 6.633, + "args": { + "External id": 4053440,"Sequence number": 40618534, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 2048]], "Input Dims": [[2048, 2048]], "Ev Idx": 447 + } + }, + { + "ph": "f", "id": 46, "pid": 1336756, "tid": 1381189, "ts": 1655274538082.715, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1381189, + "ts": 1655274538083.570, "dur": 5.557, + "args": { + "External id": 4053441,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 2048]], "Input Dims": [[2048, 2048]], "Ev Idx": 448 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1381189, + "ts": 1655274538084.358, "dur": 4.269, + "args": { + "External id": 4053442,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 2048], [], []], "Input Dims": [[2048, 2048], [], []], "Ev Idx": 449 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274538087.861, "dur": 0.650, + "args": { + "External id": 4053443,"Record function id": 0, "Concrete Inputs": ["", "[2048, 2048]", "[2048, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 2048], [], [], []], "Input Dims": [[2048, 2048], [], [], []], "Ev Idx": 450 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274538095.893, "dur": 8.052, + "args": { + "External id": 4053444,"Record function id": 0, "Ev Idx": 451 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274538097.207, "dur": 6.048, + "args": { + "External id": 4053445,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 452 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274538098.669, "dur": 4.315, + "args": { + "External id": 4053446,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 453 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274538101.413, "dur": 1.447, + "args": { + "External id": 4053447,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 454 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274538107.150, "dur": 6.615, + "args": { + "External id": 4053448,"Record function id": 0, "Sequence number": 40618533, "Fwd thread id": 1, "Ev Idx": 455 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274538108.294, "dur": 3.579, + "args": { + "External id": 4053449,"Sequence number": 40618533, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 456 + } + }, + { + "ph": "f", "id": 47, "pid": 1336756, "tid": 1381189, "ts": 1655274538108.294, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1381189, + "ts": 1655274538109.504, "dur": 2.230, + "args": { + "External id": 4053450,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 32, 64]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 457 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274538110.448, "dur": 1.141, + "args": { + "External id": 4053451,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 32, 64]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 458 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: FlashAttnFuncBackward", "pid": 1336756, "tid": 1381189, + "ts": 1655274538120.040, "dur": 321.548, + "args": { + "External id": 4053452,"Record function id": 0, "Sequence number": 40618532, "Fwd thread id": 1, "Ev Idx": 459 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "FlashAttnFuncBackward", "pid": 1336756, "tid": 1381189, + "ts": 1655274538121.327, "dur": 282.970, + "args": { + "External id": 4053453,"Sequence number": 40618532, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 64, 1]], "Input Dims": [[16, 4096, 32, 64]], "Ev Idx": 460 + } + }, + { + "ph": "f", "id": 48, "pid": 1336756, "tid": 1381189, "ts": 1655274538121.327, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336756, "tid": 1381189, + "ts": 1655274538138.394, "dur": 11.486, + "args": { + "External id": 4053454,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[8388608, 2048, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [], [], [], [], []], "Ev Idx": 461 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274538144.913, "dur": 4.463, + "args": { + "External id": 4053455,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "[8388608, 2048, 64, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 462 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336756, "tid": 1381189, + "ts": 1655274538151.924, "dur": 3.212, + "args": { + "External id": 4053456,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[8388608, 2048, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [], [], [], [], []], "Ev Idx": 463 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274538153.055, "dur": 1.829, + "args": { + "External id": 4053457,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "[8388608, 2048, 64, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 464 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336756, "tid": 1381189, + "ts": 1655274538156.426, "dur": 5.996, + "args": { + "External id": 4053458,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[8388608, 2048, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [], [], [], [], []], "Ev Idx": 465 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274538159.327, "dur": 2.915, + "args": { + "External id": 4053459,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "[8388608, 2048, 64, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 466 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 1336756, "tid": 1381189, + "ts": 1655274538190.863, "dur": 187.816, + "args": { + "External id": 4053460,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.125", "True", "-1", "-1", "0.", "", "False", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar", "long int"], "Input Strides": [[8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [131072, 4096, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 32, 4096], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 467 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655274538273.296, "dur": 3.540, + "args": { + "External id": 4053461,"Record function id": 0, "Concrete Inputs": ["[16, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 468 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655274538278.766, "dur": 3.813, + "args": { + "External id": 4053462,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 469 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::alias", "pid": 1336756, "tid": 1381189, + "ts": 1655274538392.026, "dur": 3.123, + "args": { + "External id": 4053463,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 64, 1]], "Input Dims": [[16, 4096, 32, 64]], "Ev Idx": 470 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::alias", "pid": 1336756, "tid": 1381189, + "ts": 1655274538398.227, "dur": 0.576, + "args": { + "External id": 4053464,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 64, 1]], "Input Dims": [[16, 4096, 32, 64]], "Ev Idx": 471 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::alias", "pid": 1336756, "tid": 1381189, + "ts": 1655274538400.899, "dur": 0.665, + "args": { + "External id": 4053465,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 64, 1]], "Input Dims": [[16, 4096, 32, 64]], "Ev Idx": 472 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RotaryEmbeddingFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1655274538452.287, "dur": 231.357, + "args": { + "External id": 4053466,"Record function id": 0, "Sequence number": 40618531, "Fwd thread id": 1, "Ev Idx": 473 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1655274538453.884, "dur": 222.985, + "args": { + "External id": 4053467,"Sequence number": 40618531, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 64, 1]], "Input Dims": [[16, 4096, 32, 64]], "Ev Idx": 474 + } + }, + { + "ph": "f", "id": 49, "pid": 1336756, "tid": 1381189, "ts": 1655274538453.884, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 1336756, "tid": 1381189, + "ts": 1655274538475.742, "dur": 51.860, + "args": { + "External id": 4053468,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", ""], "Input Strides": [[8388608, 2048, 64, 1], []], "Input Dims": [[16, 4096, 32, 64], []], "Ev Idx": 475 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274538482.592, "dur": 3.543, + "args": { + "External id": 4053469,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "[8388608, 2048, 64, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 476 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1381189, + "ts": 1655274538487.555, "dur": 39.392, + "args": { + "External id": 4053470,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [8388608, 2048, 64, 1], []], "Input Dims": [[16, 4096, 32, 64], [16, 4096, 32, 64], []], "Ev Idx": 477 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336756, "tid": 1381189, + "ts": 1655274538537.537, "dur": 3.825, + "args": { + "External id": 4053471,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[8388608, 2048, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [], [], [], [], []], "Ev Idx": 478 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274538538.881, "dur": 2.107, + "args": { + "External id": 4053472,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "[8388608, 2048, 64, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 479 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RotaryEmbeddingFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1655274538690.442, "dur": 145.359, + "args": { + "External id": 4053473,"Record function id": 0, "Sequence number": 40618530, "Fwd thread id": 1, "Ev Idx": 480 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1655274538691.919, "dur": 138.533, + "args": { + "External id": 4053474,"Sequence number": 40618530, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 64, 1]], "Input Dims": [[16, 4096, 32, 64]], "Ev Idx": 481 + } + }, + { + "ph": "f", "id": 50, "pid": 1336756, "tid": 1381189, "ts": 1655274538691.919, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 1336756, "tid": 1381189, + "ts": 1655274538703.985, "dur": 34.084, + "args": { + "External id": 4053475,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", ""], "Input Strides": [[8388608, 2048, 64, 1], []], "Input Dims": [[16, 4096, 32, 64], []], "Ev Idx": 482 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274538709.319, "dur": 2.619, + "args": { + "External id": 4053476,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "[8388608, 2048, 64, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 483 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1381189, + "ts": 1655274538713.030, "dur": 24.403, + "args": { + "External id": 4053477,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [8388608, 2048, 64, 1], []], "Input Dims": [[16, 4096, 32, 64], [16, 4096, 32, 64], []], "Ev Idx": 484 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336756, "tid": 1381189, + "ts": 1655274538745.136, "dur": 3.618, + "args": { + "External id": 4053478,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[8388608, 2048, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [], [], [], [], []], "Ev Idx": 485 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274538746.296, "dur": 2.140, + "args": { + "External id": 4053479,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "[8388608, 2048, 64, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 486 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274538843.360, "dur": 14.687, + "args": { + "External id": 4053480,"Record function id": 0, "Sequence number": 40618529, "Fwd thread id": 1, "Ev Idx": 487 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274538844.961, "dur": 9.853, + "args": { + "External id": 4053481,"Sequence number": 40618529, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 64, 1]], "Input Dims": [[16, 4096, 32, 64]], "Ev Idx": 488 + } + }, + { + "ph": "f", "id": 51, "pid": 1336756, "tid": 1381189, "ts": 1655274538844.961, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1381189, + "ts": 1655274538846.881, "dur": 7.706, + "args": { + "External id": 4053482,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 64, 1], []], "Input Dims": [[16, 4096, 32, 64], []], "Ev Idx": 489 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274538848.272, "dur": 6.120, + "args": { + "External id": 4053483,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 64, 1], []], "Input Dims": [[16, 4096, 32, 64], []], "Ev Idx": 490 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274538861.359, "dur": 7.694, + "args": { + "External id": 4053484,"Record function id": 0, "Sequence number": 40618528, "Fwd thread id": 1, "Ev Idx": 491 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274538862.460, "dur": 4.695, + "args": { + "External id": 4053485,"Sequence number": 40618528, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 64, 1]], "Input Dims": [[16, 4096, 32, 64]], "Ev Idx": 492 + } + }, + { + "ph": "f", "id": 52, "pid": 1336756, "tid": 1381189, "ts": 1655274538862.460, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1381189, + "ts": 1655274538865.128, "dur": 1.885, + "args": { + "External id": 4053486,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 64, 1], []], "Input Dims": [[16, 4096, 32, 64], []], "Ev Idx": 493 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274538865.800, "dur": 1.030, + "args": { + "External id": 4053487,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 64, 1], []], "Input Dims": [[16, 4096, 32, 64], []], "Ev Idx": 494 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274538872.060, "dur": 7.095, + "args": { + "External id": 4053488,"Record function id": 0, "Sequence number": 40618527, "Fwd thread id": 1, "Ev Idx": 495 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274538872.950, "dur": 4.555, + "args": { + "External id": 4053489,"Sequence number": 40618527, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 64, 1]], "Input Dims": [[16, 4096, 32, 64]], "Ev Idx": 496 + } + }, + { + "ph": "f", "id": 53, "pid": 1336756, "tid": 1381189, "ts": 1655274538872.950, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1381189, + "ts": 1655274538875.799, "dur": 1.567, + "args": { + "External id": 4053490,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 64, 1], []], "Input Dims": [[16, 4096, 32, 64], []], "Ev Idx": 497 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274538876.492, "dur": 0.745, + "args": { + "External id": 4053491,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 64, 1], []], "Input Dims": [[16, 4096, 32, 64], []], "Ev Idx": 498 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: UnsafeViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274538884.597, "dur": 6.103, + "args": { + "External id": 4053492,"Record function id": 0, "Sequence number": 40618526, "Fwd thread id": 1, "Ev Idx": 499 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274538885.691, "dur": 2.824, + "args": { + "External id": 4053493,"Sequence number": 40618526, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 500 + } + }, + { + "ph": "f", "id": 54, "pid": 1336756, "tid": 1381189, "ts": 1655274538885.691, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1381189, + "ts": 1655274538886.672, "dur": 1.698, + "args": { + "External id": 4053494,"Record function id": 0, "Concrete Inputs": ["", "[65536, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 501 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274538887.326, "dur": 0.929, + "args": { + "External id": 4053495,"Record function id": 0, "Concrete Inputs": ["", "[65536, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 502 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: MmBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274538894.038, "dur": 252.024, + "args": { + "External id": 4053496,"Record function id": 0, "Sequence number": 40618525, "Fwd thread id": 1, "Ev Idx": 503 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274538894.930, "dur": 240.241, + "args": { + "External id": 4053497,"Sequence number": 40618525, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[65536, 2048]], "Ev Idx": 504 + } + }, + { + "ph": "f", "id": 55, "pid": 1336756, "tid": 1381189, "ts": 1655274538894.930, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1381189, + "ts": 1655274538898.335, "dur": 7.585, + "args": { + "External id": 4053498,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[65536, 2048]], "Ev Idx": 505 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1381189, + "ts": 1655274538902.086, "dur": 3.246, + "args": { + "External id": 4053499,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[65536, 2048], [], []], "Ev Idx": 506 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274538903.723, "dur": 1.339, + "args": { + "External id": 4053500,"Record function id": 0, "Concrete Inputs": ["", "[2048, 65536]", "[1, 2048]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[65536, 2048], [], [], []], "Ev Idx": 507 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655274538907.625, "dur": 71.609, + "args": { + "External id": 4053501,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048]], "Ev Idx": 508 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1381189, + "ts": 1655274538980.299, "dur": 58.844, + "args": { + "External id": 4053502,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 509 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1381189, + "ts": 1655274538981.192, "dur": 56.699, + "args": { + "External id": 4053503,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[2048, 2048], [], []], "Ev Idx": 510 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274539035.324, "dur": 1.928, + "args": { + "External id": 4053504,"Record function id": 0, "Concrete Inputs": ["", "[2048, 2048]", "[1, 2048]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[2048, 2048], [], [], []], "Ev Idx": 511 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1381189, + "ts": 1655274539064.835, "dur": 5.942, + "args": { + "External id": 4053505,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 2048]], "Input Dims": [[2048, 2048]], "Ev Idx": 512 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1381189, + "ts": 1655274539068.752, "dur": 1.477, + "args": { + "External id": 4053506,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 2048], [], []], "Input Dims": [[2048, 2048], [], []], "Ev Idx": 513 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274539069.688, "dur": 0.475, + "args": { + "External id": 4053507,"Record function id": 0, "Concrete Inputs": ["", "[2048, 2048]", "[2048, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 2048], [], [], []], "Input Dims": [[2048, 2048], [], [], []], "Ev Idx": 514 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655274539071.669, "dur": 62.485, + "args": { + "External id": 4053508,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048]], "Ev Idx": 515 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274539155.388, "dur": 6.951, + "args": { + "External id": 4053509,"Record function id": 0, "Sequence number": 40618524, "Fwd thread id": 1, "Ev Idx": 516 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274539156.571, "dur": 3.931, + "args": { + "External id": 4053510,"Sequence number": 40618524, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[65536, 2048]], "Ev Idx": 517 + } + }, + { + "ph": "f", "id": 56, "pid": 1336756, "tid": 1381189, "ts": 1655274539156.571, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1381189, + "ts": 1655274539158.133, "dur": 2.231, + "args": { + "External id": 4053511,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 518 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274539158.842, "dur": 1.411, + "args": { + "External id": 4053512,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 519 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: TBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274539165.528, "dur": 10.982, + "args": { + "External id": 4053513,"Record function id": 0, "Sequence number": 40618523, "Fwd thread id": 1, "Ev Idx": 520 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274539168.671, "dur": 5.649, + "args": { + "External id": 4053514,"Sequence number": 40618523, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 2048]], "Input Dims": [[2048, 2048]], "Ev Idx": 521 + } + }, + { + "ph": "f", "id": 57, "pid": 1336756, "tid": 1381189, "ts": 1655274539168.671, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1381189, + "ts": 1655274539169.323, "dur": 4.764, + "args": { + "External id": 4053515,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 2048]], "Input Dims": [[2048, 2048]], "Ev Idx": 522 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1381189, + "ts": 1655274539170.075, "dur": 3.532, + "args": { + "External id": 4053516,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 2048], [], []], "Input Dims": [[2048, 2048], [], []], "Ev Idx": 523 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274539173.079, "dur": 0.365, + "args": { + "External id": 4053517,"Record function id": 0, "Concrete Inputs": ["", "[2048, 2048]", "[2048, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 2048], [], [], []], "Input Dims": [[2048, 2048], [], [], []], "Ev Idx": 524 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274539182.750, "dur": 8.712, + "args": { + "External id": 4053518,"Record function id": 0, "Ev Idx": 525 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274539184.043, "dur": 6.670, + "args": { + "External id": 4053519,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 526 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274539186.810, "dur": 3.506, + "args": { + "External id": 4053520,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 527 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274539187.597, "dur": 2.645, + "args": { + "External id": 4053521,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 528 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: UnsafeViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274539196.846, "dur": 7.132, + "args": { + "External id": 4053522,"Record function id": 0, "Sequence number": 40618522, "Fwd thread id": 1, "Ev Idx": 529 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274539197.547, "dur": 4.402, + "args": { + "External id": 4053523,"Sequence number": 40618522, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 530 + } + }, + { + "ph": "f", "id": 58, "pid": 1336756, "tid": 1381189, "ts": 1655274539197.547, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1381189, + "ts": 1655274539198.424, "dur": 3.371, + "args": { + "External id": 4053524,"Record function id": 0, "Concrete Inputs": ["", "[65536, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 531 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274539200.999, "dur": 0.700, + "args": { + "External id": 4053525,"Record function id": 0, "Concrete Inputs": ["", "[65536, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 532 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: MmBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274539207.370, "dur": 91.424, + "args": { + "External id": 4053526,"Record function id": 0, "Sequence number": 40618521, "Fwd thread id": 1, "Ev Idx": 533 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274539208.202, "dur": 85.397, + "args": { + "External id": 4053527,"Sequence number": 40618521, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[65536, 2048]], "Ev Idx": 534 + } + }, + { + "ph": "f", "id": 59, "pid": 1336756, "tid": 1381189, "ts": 1655274539208.202, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1381189, + "ts": 1655274539210.365, "dur": 4.217, + "args": { + "External id": 4053528,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[65536, 2048]], "Ev Idx": 535 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1381189, + "ts": 1655274539210.915, "dur": 3.273, + "args": { + "External id": 4053529,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[65536, 2048], [], []], "Ev Idx": 536 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274539213.725, "dur": 0.347, + "args": { + "External id": 4053530,"Record function id": 0, "Concrete Inputs": ["", "[2048, 65536]", "[1, 2048]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[65536, 2048], [], [], []], "Ev Idx": 537 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655274539216.904, "dur": 29.072, + "args": { + "External id": 4053531,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048]], "Ev Idx": 538 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1381189, + "ts": 1655274539246.903, "dur": 2.497, + "args": { + "External id": 4053532,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 539 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1381189, + "ts": 1655274539247.486, "dur": 1.397, + "args": { + "External id": 4053533,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[2048, 2048], [], []], "Ev Idx": 540 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274539248.206, "dur": 0.562, + "args": { + "External id": 4053534,"Record function id": 0, "Concrete Inputs": ["", "[2048, 2048]", "[1, 2048]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[2048, 2048], [], [], []], "Ev Idx": 541 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1381189, + "ts": 1655274539250.563, "dur": 6.335, + "args": { + "External id": 4053535,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 2048]], "Input Dims": [[2048, 2048]], "Ev Idx": 542 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1381189, + "ts": 1655274539251.180, "dur": 5.318, + "args": { + "External id": 4053536,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 2048], [], []], "Input Dims": [[2048, 2048], [], []], "Ev Idx": 543 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274539254.246, "dur": 2.185, + "args": { + "External id": 4053537,"Record function id": 0, "Concrete Inputs": ["", "[2048, 2048]", "[2048, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 2048], [], [], []], "Input Dims": [[2048, 2048], [], [], []], "Ev Idx": 544 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655274539257.341, "dur": 35.362, + "args": { + "External id": 4053538,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048]], "Ev Idx": 545 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274539303.198, "dur": 33.831, + "args": { + "External id": 4053539,"Record function id": 0, "Sequence number": 40618520, "Fwd thread id": 1, "Ev Idx": 546 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274539304.184, "dur": 5.403, + "args": { + "External id": 4053540,"Sequence number": 40618520, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[65536, 2048]], "Ev Idx": 547 + } + }, + { + "ph": "f", "id": 60, "pid": 1336756, "tid": 1381189, "ts": 1655274539304.184, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1381189, + "ts": 1655274539307.897, "dur": 1.548, + "args": { + "External id": 4053541,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 548 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274539308.457, "dur": 0.893, + "args": { + "External id": 4053542,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 549 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add", "pid": 1336756, "tid": 1381189, + "ts": 1655274539312.521, "dur": 22.088, + "args": { + "External id": 4053543,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[8388608, 2048, 1], [8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], [16, 4096, 2048], []], "Ev Idx": 550 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: TBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274539340.759, "dur": 8.770, + "args": { + "External id": 4053544,"Record function id": 0, "Sequence number": 40618519, "Fwd thread id": 1, "Ev Idx": 551 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274539341.607, "dur": 6.115, + "args": { + "External id": 4053545,"Sequence number": 40618519, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 2048]], "Input Dims": [[2048, 2048]], "Ev Idx": 552 + } + }, + { + "ph": "f", "id": 61, "pid": 1336756, "tid": 1381189, "ts": 1655274539341.607, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1381189, + "ts": 1655274539342.767, "dur": 4.768, + "args": { + "External id": 4053546,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 2048]], "Input Dims": [[2048, 2048]], "Ev Idx": 553 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1381189, + "ts": 1655274539343.387, "dur": 3.627, + "args": { + "External id": 4053547,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 2048], [], []], "Input Dims": [[2048, 2048], [], []], "Ev Idx": 554 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274539346.394, "dur": 0.534, + "args": { + "External id": 4053548,"Record function id": 0, "Concrete Inputs": ["", "[2048, 2048]", "[2048, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 2048], [], [], []], "Input Dims": [[2048, 2048], [], [], []], "Ev Idx": 555 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274539353.472, "dur": 7.413, + "args": { + "External id": 4053549,"Record function id": 0, "Ev Idx": 556 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274539357.204, "dur": 3.142, + "args": { + "External id": 4053550,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 557 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274539358.309, "dur": 1.755, + "args": { + "External id": 4053551,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 558 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274539358.754, "dur": 1.213, + "args": { + "External id": 4053552,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 559 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: UnsafeViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274539363.974, "dur": 5.708, + "args": { + "External id": 4053553,"Record function id": 0, "Sequence number": 40618518, "Fwd thread id": 1, "Ev Idx": 560 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274539364.842, "dur": 2.528, + "args": { + "External id": 4053554,"Sequence number": 40618518, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 561 + } + }, + { + "ph": "f", "id": 62, "pid": 1336756, "tid": 1381189, "ts": 1655274539364.842, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1381189, + "ts": 1655274539365.705, "dur": 1.517, + "args": { + "External id": 4053555,"Record function id": 0, "Concrete Inputs": ["", "[65536, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 562 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274539366.292, "dur": 0.797, + "args": { + "External id": 4053556,"Record function id": 0, "Concrete Inputs": ["", "[65536, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 563 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: MmBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274539372.689, "dur": 110.258, + "args": { + "External id": 4053557,"Record function id": 0, "Sequence number": 40618517, "Fwd thread id": 1, "Ev Idx": 564 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274539375.479, "dur": 99.333, + "args": { + "External id": 4053558,"Sequence number": 40618517, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[65536, 2048]], "Ev Idx": 565 + } + }, + { + "ph": "f", "id": 63, "pid": 1336756, "tid": 1381189, "ts": 1655274539375.479, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1381189, + "ts": 1655274539377.287, "dur": 2.155, + "args": { + "External id": 4053559,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[65536, 2048]], "Ev Idx": 566 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1381189, + "ts": 1655274539377.700, "dur": 1.320, + "args": { + "External id": 4053560,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[65536, 2048], [], []], "Ev Idx": 567 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274539378.376, "dur": 0.498, + "args": { + "External id": 4053561,"Record function id": 0, "Concrete Inputs": ["", "[2048, 65536]", "[1, 2048]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[65536, 2048], [], [], []], "Ev Idx": 568 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655274539380.124, "dur": 27.032, + "args": { + "External id": 4053562,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048]], "Ev Idx": 569 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1381189, + "ts": 1655274539408.133, "dur": 6.206, + "args": { + "External id": 4053563,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 570 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1381189, + "ts": 1655274539408.633, "dur": 5.216, + "args": { + "External id": 4053564,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[2048, 2048], [], []], "Ev Idx": 571 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274539413.289, "dur": 0.437, + "args": { + "External id": 4053565,"Record function id": 0, "Concrete Inputs": ["", "[2048, 2048]", "[1, 2048]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[2048, 2048], [], [], []], "Ev Idx": 572 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1381189, + "ts": 1655274539430.908, "dur": 3.387, + "args": { + "External id": 4053566,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 2048]], "Input Dims": [[2048, 2048]], "Ev Idx": 573 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1381189, + "ts": 1655274539431.952, "dur": 1.763, + "args": { + "External id": 4053567,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 2048], [], []], "Input Dims": [[2048, 2048], [], []], "Ev Idx": 574 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274539432.991, "dur": 0.501, + "args": { + "External id": 4053568,"Record function id": 0, "Concrete Inputs": ["", "[2048, 2048]", "[2048, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 2048], [], [], []], "Input Dims": [[2048, 2048], [], [], []], "Ev Idx": 575 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655274539434.797, "dur": 39.443, + "args": { + "External id": 4053569,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048]], "Ev Idx": 576 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274539489.051, "dur": 26.412, + "args": { + "External id": 4053570,"Record function id": 0, "Sequence number": 40618516, "Fwd thread id": 1, "Ev Idx": 577 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274539490.123, "dur": 5.265, + "args": { + "External id": 4053571,"Sequence number": 40618516, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[65536, 2048]], "Ev Idx": 578 + } + }, + { + "ph": "f", "id": 64, "pid": 1336756, "tid": 1381189, "ts": 1655274539490.123, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1381189, + "ts": 1655274539493.435, "dur": 1.781, + "args": { + "External id": 4053572,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 579 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274539493.932, "dur": 1.190, + "args": { + "External id": 4053573,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 580 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336756, "tid": 1381189, + "ts": 1655274539497.639, "dur": 15.642, + "args": { + "External id": 4053574,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[8388608, 2048, 1], [8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], [16, 4096, 2048], []], "Ev Idx": 581 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: TBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274539519.159, "dur": 11.616, + "args": { + "External id": 4053575,"Record function id": 0, "Sequence number": 40618515, "Fwd thread id": 1, "Ev Idx": 582 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274539520.437, "dur": 8.295, + "args": { + "External id": 4053576,"Sequence number": 40618515, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 2048]], "Input Dims": [[2048, 2048]], "Ev Idx": 583 + } + }, + { + "ph": "f", "id": 65, "pid": 1336756, "tid": 1381189, "ts": 1655274539520.437, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1381189, + "ts": 1655274539521.273, "dur": 7.259, + "args": { + "External id": 4053577,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 2048]], "Input Dims": [[2048, 2048]], "Ev Idx": 584 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1381189, + "ts": 1655274539523.951, "dur": 4.064, + "args": { + "External id": 4053578,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 2048], [], []], "Input Dims": [[2048, 2048], [], []], "Ev Idx": 585 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274539527.332, "dur": 0.530, + "args": { + "External id": 4053579,"Record function id": 0, "Concrete Inputs": ["", "[2048, 2048]", "[2048, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 2048], [], [], []], "Input Dims": [[2048, 2048], [], [], []], "Ev Idx": 586 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274539534.884, "dur": 8.010, + "args": { + "External id": 4053580,"Record function id": 0, "Ev Idx": 587 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274539536.212, "dur": 6.172, + "args": { + "External id": 4053581,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 588 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274539537.651, "dur": 4.421, + "args": { + "External id": 4053582,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 589 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274539540.473, "dur": 1.484, + "args": { + "External id": 4053583,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 590 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: LayerNormFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1655274539546.848, "dur": 347.858, + "args": { + "External id": 4053584,"Record function id": 0, "Sequence number": 40618514, "Fwd thread id": 1, "Ev Idx": 591 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1655274539548.114, "dur": 317.967, + "args": { + "External id": 4053585,"Sequence number": 40618514, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 592 + } + }, + { + "ph": "f", "id": 66, "pid": 1336756, "tid": 1381189, "ts": 1655274539548.114, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1381189, + "ts": 1655274539580.671, "dur": 2.163, + "args": { + "External id": 4053586,"Record function id": 0, "Concrete Inputs": ["", "[-1, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 593 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274539581.356, "dur": 1.310, + "args": { + "External id": 4053587,"Record function id": 0, "Concrete Inputs": ["", "[-1, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 594 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655274539599.722, "dur": 5.968, + "args": { + "External id": 4053588,"Record function id": 0, "Concrete Inputs": ["[65536, 2048]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 595 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655274539615.407, "dur": 1.772, + "args": { + "External id": 4053589,"Record function id": 0, "Concrete Inputs": ["[132, 2048]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 596 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274539765.766, "dur": 1.797, + "args": { + "External id": 4053590,"Record function id": 0, "Concrete Inputs": ["", "[1, -1, 2048]"], "Input type": ["float", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[132, 2048], []], "Ev Idx": 597 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 1336756, "tid": 1381189, + "ts": 1655274539771.886, "dur": 35.247, + "args": { + "External id": 4053591,"Record function id": 0, "Concrete Inputs": ["", "[1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", ""], "Input Strides": [[270336, 2048, 1], [], [], []], "Input Dims": [[1, 132, 2048], [], [], []], "Ev Idx": 598 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274539784.795, "dur": 1.000, + "args": { + "External id": 4053592,"Record function id": 0, "Concrete Inputs": ["", "[1, 1, 2048]", "[2048, 0, 1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[1, 2048], [], [], []], "Ev Idx": 599 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1381189, + "ts": 1655274539812.527, "dur": 28.546, + "args": { + "External id": 4053593,"Record function id": 0, "Concrete Inputs": ["", "", "15", "False", "False", ""], "Input type": ["float", "", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[2048, 1], [], [], [], [], []], "Input Dims": [[1, 2048], [], [], [], [], []], "Ev Idx": 600 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336756, "tid": 1381189, + "ts": 1655274539814.310, "dur": 26.519, + "args": { + "External id": 4053594,"Record function id": 0, "Concrete Inputs": ["", "15", "", "", "", "False", ""], "Input type": ["float", "Scalar", "", "", "", "Scalar", ""], "Input Strides": [[2048, 1], [], [], [], [], [], []], "Input Dims": [[1, 2048], [], [], [], [], [], []], "Ev Idx": 601 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274539817.810, "dur": 4.954, + "args": { + "External id": 4053595,"Record function id": 0, "Concrete Inputs": ["[1, 2048]", "[2048, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 602 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1381189, + "ts": 1655274539824.575, "dur": 15.773, + "args": { + "External id": 4053596,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "float", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[1, 2048], [1, 2048], []], "Ev Idx": 603 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 1336756, "tid": 1381189, + "ts": 1655274539845.366, "dur": 2.747, + "args": { + "External id": 4053597,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1]], "Input Dims": [[1, 2048], [2048]], "Ev Idx": 604 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274539846.770, "dur": 1.243, + "args": { + "External id": 4053598,"Record function id": 0, "Concrete Inputs": ["", "[2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[1, 2048], []], "Ev Idx": 605 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1381189, + "ts": 1655274539855.301, "dur": 3.823, + "args": { + "External id": 4053599,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 606 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274539858.186, "dur": 0.837, + "args": { + "External id": 4053600,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 607 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add", "pid": 1336756, "tid": 1381189, + "ts": 1655274539874.960, "dur": 14.964, + "args": { + "External id": 4053601,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[8388608, 2048, 1], [8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], [16, 4096, 2048], []], "Ev Idx": 608 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274539903.423, "dur": 7.082, + "args": { + "External id": 4053602,"Record function id": 0, "Ev Idx": 609 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274539905.153, "dur": 4.637, + "args": { + "External id": 4053603,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 610 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274539906.716, "dur": 2.176, + "args": { + "External id": 4053604,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 611 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274539907.652, "dur": 1.136, + "args": { + "External id": 4053605,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 612 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: AddBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274539916.653, "dur": 5.013, + "args": { + "External id": 4053606,"Record function id": 0, "Sequence number": 40618513, "Fwd thread id": 1, "Ev Idx": 613 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "AddBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274539917.978, "dur": 1.076, + "args": { + "External id": 4053607,"Sequence number": 40618513, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[33554432, 8192, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 614 + } + }, + { + "ph": "f", "id": 67, "pid": 1336756, "tid": 1381189, "ts": 1655274539917.978, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: SwiGLULinearFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1655274539925.150, "dur": 440.255, + "args": { + "External id": 4053608,"Record function id": 0, "Sequence number": 40618512, "Fwd thread id": 1, "Ev Idx": 615 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SwiGLULinearFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1655274539926.193, "dur": 428.716, + "args": { + "External id": 4053609,"Sequence number": 40618512, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[33554432, 8192, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 616 + } + }, + { + "ph": "f", "id": 68, "pid": 1336756, "tid": 1381189, "ts": 1655274539926.193, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1381189, + "ts": 1655274539954.783, "dur": 7.806, + "args": { + "External id": 4053610,"Record function id": 0, "Concrete Inputs": ["", "[-1, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[33554432, 8192, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 617 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_reshape_alias", "pid": 1336756, "tid": 1381189, + "ts": 1655274539959.441, "dur": 2.921, + "args": { + "External id": 4053611,"Record function id": 0, "Concrete Inputs": ["", "[65536, 2048]", "[8192, 1]"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList"], "Input Strides": [[33554432, 8192, 1], [], []], "Input Dims": [[16, 4096, 2048], [], []], "Ev Idx": 618 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1381189, + "ts": 1655274539965.755, "dur": 5.587, + "args": { + "External id": 4053612,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 619 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1381189, + "ts": 1655274539966.791, "dur": 4.061, + "args": { + "External id": 4053613,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[5632, 1], [], []], "Input Dims": [[2048, 5632], [], []], "Ev Idx": 620 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274539970.072, "dur": 0.659, + "args": { + "External id": 4053614,"Record function id": 0, "Concrete Inputs": ["", "[5632, 2048]", "[1, 5632]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[5632, 1], [], [], []], "Input Dims": [[2048, 5632], [], [], []], "Ev Idx": 621 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336756, "tid": 1381189, + "ts": 1655274539976.905, "dur": 126.241, + "args": { + "External id": 4053615,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[8192, 1], [1, 5632], []], "Input Dims": [[65536, 2048], [5632, 2048], []], "Ev Idx": 622 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1381189, + "ts": 1655274539977.752, "dur": 4.343, + "args": { + "External id": 4053616,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 5632]], "Input Dims": [[5632, 2048]], "Ev Idx": 623 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1381189, + "ts": 1655274539978.261, "dur": 3.426, + "args": { + "External id": 4053617,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 5632], [], []], "Input Dims": [[5632, 2048], [], []], "Ev Idx": 624 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274539978.956, "dur": 2.632, + "args": { + "External id": 4053618,"Record function id": 0, "Concrete Inputs": ["", "[2048, 5632]", "[5632, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 5632], [], [], []], "Input Dims": [[5632, 2048], [], [], []], "Ev Idx": 625 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336756, "tid": 1381189, + "ts": 1655274539983.376, "dur": 119.185, + "args": { + "External id": 4053619,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[8192, 1], [5632, 1]], "Input Dims": [[65536, 2048], [2048, 5632]], "Ev Idx": 626 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655274540022.814, "dur": 78.754, + "args": { + "External id": 4053620,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[8192, 1], [5632, 1]], "Input Dims": [[65536, 2048], [2048, 5632]], "Ev Idx": 627 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 1336756, "tid": 1381189, + "ts": 1655274540108.049, "dur": 6.052, + "args": { + "External id": 4053621,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [23068672, 5632, 1]], "Input Dims": [[65536, 5632], [16, 4096, 5632]], "Ev Idx": 628 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274540112.360, "dur": 1.607, + "args": { + "External id": 4053622,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 5632]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[5632, 1], []], "Input Dims": [[65536, 5632], []], "Ev Idx": 629 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655274540147.796, "dur": 4.921, + "args": { + "External id": 4053623,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 5632]", "15", "", "", "", "0"], "Input type": ["ScalarList", "Scalar", "", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 630 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655274540153.688, "dur": 1.642, + "args": { + "External id": 4053624,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 5632]", "15", "", "", "", "0"], "Input type": ["ScalarList", "Scalar", "", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 631 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655274540156.124, "dur": 1.577, + "args": { + "External id": 4053625,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 5632]", "15", "", "", "", "0"], "Input type": ["ScalarList", "Scalar", "", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 632 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1381189, + "ts": 1655274540189.704, "dur": 2.088, + "args": { + "External id": 4053626,"Record function id": 0, "Concrete Inputs": ["", "[-1, 5632]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[23068672, 5632, 1], []], "Input Dims": [[16, 4096, 5632], []], "Ev Idx": 633 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274540190.350, "dur": 1.294, + "args": { + "External id": 4053627,"Record function id": 0, "Concrete Inputs": ["", "[-1, 5632]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[23068672, 5632, 1], []], "Input Dims": [[16, 4096, 5632], []], "Ev Idx": 634 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::einsum", "pid": 1336756, "tid": 1381189, + "ts": 1655274540215.636, "dur": 119.976, + "args": { + "External id": 4053628,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["", "TensorList", ""], "Input Strides": [[], [[8192, 1], [5632, 1]], []], "Input Dims": [[], [[65536, 2048], [65536, 5632]], []], "Ev Idx": 635 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1381189, + "ts": 1655274540220.640, "dur": 4.962, + "args": { + "External id": 4053629,"Record function id": 0, "Concrete Inputs": ["", "2"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[8192, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 636 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274540223.541, "dur": 1.284, + "args": { + "External id": 4053630,"Record function id": 0, "Concrete Inputs": ["", "[65536, 2048, 1]", "[8192, 1, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[8192, 1], [], [], []], "Input Dims": [[65536, 2048], [], [], []], "Ev Idx": 637 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::permute", "pid": 1336756, "tid": 1381189, + "ts": 1655274540226.839, "dur": 10.289, + "args": { + "External id": 4053631,"Record function id": 0, "Concrete Inputs": ["", "[1, 2, 0]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8192, 1, 1], []], "Input Dims": [[65536, 2048, 1], []], "Ev Idx": 638 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274540233.970, "dur": 2.538, + "args": { + "External id": 4053632,"Record function id": 0, "Concrete Inputs": ["", "[2048, 1, 65536]", "[1, 1, 8192]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[8192, 1, 1], [], [], []], "Input Dims": [[65536, 2048, 1], [], [], []], "Ev Idx": 639 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1381189, + "ts": 1655274540238.525, "dur": 3.629, + "args": { + "External id": 4053633,"Record function id": 0, "Concrete Inputs": ["", "2"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[5632, 1], []], "Input Dims": [[65536, 5632], []], "Ev Idx": 640 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274540241.183, "dur": 0.615, + "args": { + "External id": 4053634,"Record function id": 0, "Concrete Inputs": ["", "[65536, 5632, 1]", "[5632, 1, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[5632, 1], [], [], []], "Input Dims": [[65536, 5632], [], [], []], "Ev Idx": 641 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::permute", "pid": 1336756, "tid": 1381189, + "ts": 1655274540242.750, "dur": 3.764, + "args": { + "External id": 4053635,"Record function id": 0, "Concrete Inputs": ["", "[2, 1, 0]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[5632, 1, 1], []], "Input Dims": [[65536, 5632, 1], []], "Ev Idx": 642 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274540245.466, "dur": 0.608, + "args": { + "External id": 4053636,"Record function id": 0, "Concrete Inputs": ["", "[1, 5632, 65536]", "[1, 1, 5632]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[5632, 1, 1], [], [], []], "Input Dims": [[65536, 5632, 1], [], [], []], "Ev Idx": 643 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::permute", "pid": 1336756, "tid": 1381189, + "ts": 1655274540249.920, "dur": 2.187, + "args": { + "External id": 4053637,"Record function id": 0, "Concrete Inputs": ["", "[0, 2, 1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1, 1, 8192], []], "Input Dims": [[2048, 1, 65536], []], "Ev Idx": 644 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274540251.154, "dur": 0.647, + "args": { + "External id": 4053638,"Record function id": 0, "Concrete Inputs": ["", "[2048, 65536, 1]", "[1, 8192, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1, 8192], [], [], []], "Input Dims": [[2048, 1, 65536], [], [], []], "Ev Idx": 645 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1381189, + "ts": 1655274540256.843, "dur": 5.217, + "args": { + "External id": 4053639,"Record function id": 0, "Concrete Inputs": ["", "[1, 2048, 65536]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1, 8192, 1], []], "Input Dims": [[2048, 65536, 1], []], "Ev Idx": 646 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_reshape_alias", "pid": 1336756, "tid": 1381189, + "ts": 1655274540260.094, "dur": 1.763, + "args": { + "External id": 4053640,"Record function id": 0, "Concrete Inputs": ["", "[1, 2048, 65536]", "[2048, 1, 8192]"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList"], "Input Strides": [[1, 8192, 1], [], []], "Input Dims": [[2048, 65536, 1], [], []], "Ev Idx": 647 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::permute", "pid": 1336756, "tid": 1381189, + "ts": 1655274540264.927, "dur": 1.496, + "args": { + "External id": 4053641,"Record function id": 0, "Concrete Inputs": ["", "[2, 1, 0]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1, 1, 5632], []], "Input Dims": [[1, 5632, 65536], []], "Ev Idx": 648 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274540265.823, "dur": 0.317, + "args": { + "External id": 4053642,"Record function id": 0, "Concrete Inputs": ["", "[65536, 5632, 1]", "[5632, 1, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1, 5632], [], [], []], "Input Dims": [[1, 5632, 65536], [], [], []], "Ev Idx": 649 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1381189, + "ts": 1655274540267.172, "dur": 5.163, + "args": { + "External id": 4053643,"Record function id": 0, "Concrete Inputs": ["", "[1, 65536, 5632]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[5632, 1, 1], []], "Input Dims": [[65536, 5632, 1], []], "Ev Idx": 650 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274540269.805, "dur": 2.442, + "args": { + "External id": 4053644,"Record function id": 0, "Concrete Inputs": ["", "[1, 65536, 5632]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[5632, 1, 1], []], "Input Dims": [[65536, 5632, 1], []], "Ev Idx": 651 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 1336756, "tid": 1381189, + "ts": 1655274540273.435, "dur": 48.812, + "args": { + "External id": 4053645,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1, 8192], [369098752, 5632, 1]], "Input Dims": [[1, 2048, 65536], [1, 65536, 5632]], "Ev Idx": 652 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274540324.114, "dur": 2.925, + "args": { + "External id": 4053646,"Record function id": 0, "Concrete Inputs": ["", "[2048, 1, 5632]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[11534336, 5632, 1], []], "Input Dims": [[1, 2048, 5632], []], "Ev Idx": 653 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::permute", "pid": 1336756, "tid": 1381189, + "ts": 1655274540327.634, "dur": 4.037, + "args": { + "External id": 4053647,"Record function id": 0, "Concrete Inputs": ["", "[0, 2, 1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[5632, 5632, 1], []], "Input Dims": [[2048, 1, 5632], []], "Ev Idx": 654 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274540330.756, "dur": 0.538, + "args": { + "External id": 4053648,"Record function id": 0, "Concrete Inputs": ["", "[2048, 5632, 1]", "[5632, 1, 5632]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[5632, 5632, 1], [], [], []], "Input Dims": [[2048, 1, 5632], [], [], []], "Ev Idx": 655 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274540333.694, "dur": 0.849, + "args": { + "External id": 4053649,"Record function id": 0, "Concrete Inputs": ["", "[2048, 5632]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[5632, 1, 5632], []], "Input Dims": [[2048, 5632, 1], []], "Ev Idx": 656 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274540376.760, "dur": 8.170, + "args": { + "External id": 4053650,"Record function id": 0, "Ev Idx": 657 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274540378.626, "dur": 5.687, + "args": { + "External id": 4053651,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 658 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274540380.580, "dur": 2.930, + "args": { + "External id": 4053652,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 659 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274540381.413, "dur": 1.998, + "args": { + "External id": 4053653,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 660 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: UnsafeViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274540388.416, "dur": 6.096, + "args": { + "External id": 4053654,"Record function id": 0, "Sequence number": 40618511, "Fwd thread id": 1, "Ev Idx": 661 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274540389.268, "dur": 3.405, + "args": { + "External id": 4053655,"Sequence number": 40618511, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[23068672, 5632, 1]], "Input Dims": [[16, 4096, 5632]], "Ev Idx": 662 + } + }, + { + "ph": "f", "id": 69, "pid": 1336756, "tid": 1381189, "ts": 1655274540389.268, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1381189, + "ts": 1655274540390.956, "dur": 1.477, + "args": { + "External id": 4053656,"Record function id": 0, "Concrete Inputs": ["", "[65536, 5632]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[23068672, 5632, 1], []], "Input Dims": [[16, 4096, 5632], []], "Ev Idx": 663 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274540391.610, "dur": 0.697, + "args": { + "External id": 4053657,"Record function id": 0, "Concrete Inputs": ["", "[65536, 5632]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[23068672, 5632, 1], []], "Input Dims": [[16, 4096, 5632], []], "Ev Idx": 664 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: MmBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274540398.168, "dur": 148.555, + "args": { + "External id": 4053658,"Record function id": 0, "Sequence number": 40618510, "Fwd thread id": 1, "Ev Idx": 665 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274540399.196, "dur": 139.888, + "args": { + "External id": 4053659,"Sequence number": 40618510, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[65536, 5632]], "Ev Idx": 666 + } + }, + { + "ph": "f", "id": 70, "pid": 1336756, "tid": 1381189, "ts": 1655274540399.196, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1381189, + "ts": 1655274540403.657, "dur": 5.704, + "args": { + "External id": 4053660,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[65536, 5632]], "Ev Idx": 667 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1381189, + "ts": 1655274540404.606, "dur": 4.219, + "args": { + "External id": 4053661,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[5632, 1], [], []], "Input Dims": [[65536, 5632], [], []], "Ev Idx": 668 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274540408.129, "dur": 0.511, + "args": { + "External id": 4053662,"Record function id": 0, "Concrete Inputs": ["", "[5632, 65536]", "[1, 5632]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[5632, 1], [], [], []], "Input Dims": [[65536, 5632], [], [], []], "Ev Idx": 669 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655274540410.435, "dur": 61.696, + "args": { + "External id": 4053663,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 5632], [2048, 1]], "Input Dims": [[5632, 65536], [65536, 2048]], "Ev Idx": 670 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1381189, + "ts": 1655274540474.506, "dur": 6.869, + "args": { + "External id": 4053664,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 671 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1381189, + "ts": 1655274540475.532, "dur": 5.070, + "args": { + "External id": 4053665,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[5632, 2048], [], []], "Ev Idx": 672 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274540479.370, "dur": 1.060, + "args": { + "External id": 4053666,"Record function id": 0, "Concrete Inputs": ["", "[2048, 5632]", "[1, 2048]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[5632, 2048], [], [], []], "Ev Idx": 673 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1381189, + "ts": 1655274540482.833, "dur": 2.900, + "args": { + "External id": 4053667,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 2048]], "Input Dims": [[2048, 5632]], "Ev Idx": 674 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1381189, + "ts": 1655274540484.052, "dur": 1.181, + "args": { + "External id": 4053668,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 2048], [], []], "Input Dims": [[2048, 5632], [], []], "Ev Idx": 675 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274540484.793, "dur": 0.379, + "args": { + "External id": 4053669,"Record function id": 0, "Concrete Inputs": ["", "[5632, 2048]", "[2048, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 2048], [], [], []], "Input Dims": [[2048, 5632], [], [], []], "Ev Idx": 676 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655274540486.637, "dur": 51.584, + "args": { + "External id": 4053670,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [2048, 1]], "Input Dims": [[65536, 5632], [5632, 2048]], "Ev Idx": 677 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274540553.278, "dur": 8.651, + "args": { + "External id": 4053671,"Record function id": 0, "Sequence number": 40618509, "Fwd thread id": 1, "Ev Idx": 678 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274540554.363, "dur": 6.498, + "args": { + "External id": 4053672,"Sequence number": 40618509, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[65536, 2048]], "Ev Idx": 679 + } + }, + { + "ph": "f", "id": 71, "pid": 1336756, "tid": 1381189, "ts": 1655274540554.363, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1381189, + "ts": 1655274540558.572, "dur": 2.125, + "args": { + "External id": 4053673,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 680 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274540559.350, "dur": 1.251, + "args": { + "External id": 4053674,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 681 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: TBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274540565.320, "dur": 9.074, + "args": { + "External id": 4053675,"Record function id": 0, "Sequence number": 40618508, "Fwd thread id": 1, "Ev Idx": 682 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274540568.395, "dur": 3.906, + "args": { + "External id": 4053676,"Sequence number": 40618508, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 2048]], "Input Dims": [[2048, 5632]], "Ev Idx": 683 + } + }, + { + "ph": "f", "id": 72, "pid": 1336756, "tid": 1381189, "ts": 1655274540568.395, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1381189, + "ts": 1655274540569.170, "dur": 2.919, + "args": { + "External id": 4053677,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 2048]], "Input Dims": [[2048, 5632]], "Ev Idx": 684 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1381189, + "ts": 1655274540569.894, "dur": 1.716, + "args": { + "External id": 4053678,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 2048], [], []], "Input Dims": [[2048, 5632], [], []], "Ev Idx": 685 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274540570.972, "dur": 0.522, + "args": { + "External id": 4053679,"Record function id": 0, "Concrete Inputs": ["", "[5632, 2048]", "[2048, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 2048], [], [], []], "Input Dims": [[2048, 5632], [], [], []], "Ev Idx": 686 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274540578.363, "dur": 5.247, + "args": { + "External id": 4053680,"Record function id": 0, "Ev Idx": 687 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274540579.673, "dur": 3.450, + "args": { + "External id": 4053681,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 688 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274540580.790, "dur": 2.048, + "args": { + "External id": 4053682,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 689 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274540581.300, "dur": 1.469, + "args": { + "External id": 4053683,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 690 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: UnsafeViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274540586.690, "dur": 8.564, + "args": { + "External id": 4053684,"Record function id": 0, "Sequence number": 40618507, "Fwd thread id": 1, "Ev Idx": 691 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274540589.425, "dur": 4.024, + "args": { + "External id": 4053685,"Sequence number": 40618507, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[23068672, 5632, 1]], "Input Dims": [[16, 4096, 5632]], "Ev Idx": 692 + } + }, + { + "ph": "f", "id": 73, "pid": 1336756, "tid": 1381189, "ts": 1655274540589.425, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1381189, + "ts": 1655274540590.297, "dur": 3.011, + "args": { + "External id": 4053686,"Record function id": 0, "Concrete Inputs": ["", "[65536, 5632]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[23068672, 5632, 1], []], "Input Dims": [[16, 4096, 5632], []], "Ev Idx": 693 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274540592.585, "dur": 0.607, + "args": { + "External id": 4053687,"Record function id": 0, "Concrete Inputs": ["", "[65536, 5632]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[23068672, 5632, 1], []], "Input Dims": [[16, 4096, 5632], []], "Ev Idx": 694 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: MmBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274540598.269, "dur": 114.214, + "args": { + "External id": 4053688,"Record function id": 0, "Sequence number": 40618506, "Fwd thread id": 1, "Ev Idx": 695 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274540599.243, "dur": 105.494, + "args": { + "External id": 4053689,"Sequence number": 40618506, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[65536, 5632]], "Ev Idx": 696 + } + }, + { + "ph": "f", "id": 74, "pid": 1336756, "tid": 1381189, "ts": 1655274540599.243, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1381189, + "ts": 1655274540601.373, "dur": 5.048, + "args": { + "External id": 4053690,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[65536, 5632]], "Ev Idx": 697 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1381189, + "ts": 1655274540601.815, "dur": 4.166, + "args": { + "External id": 4053691,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[5632, 1], [], []], "Input Dims": [[65536, 5632], [], []], "Ev Idx": 698 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274540605.437, "dur": 0.442, + "args": { + "External id": 4053692,"Record function id": 0, "Concrete Inputs": ["", "[5632, 65536]", "[1, 5632]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[5632, 1], [], [], []], "Input Dims": [[65536, 5632], [], [], []], "Ev Idx": 699 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655274540609.321, "dur": 34.017, + "args": { + "External id": 4053693,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 5632], [2048, 1]], "Input Dims": [[5632, 65536], [65536, 2048]], "Ev Idx": 700 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1381189, + "ts": 1655274540644.368, "dur": 4.671, + "args": { + "External id": 4053694,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 701 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1381189, + "ts": 1655274540645.016, "dur": 3.449, + "args": { + "External id": 4053695,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[5632, 2048], [], []], "Ev Idx": 702 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274540646.149, "dur": 2.156, + "args": { + "External id": 4053696,"Record function id": 0, "Concrete Inputs": ["", "[2048, 5632]", "[1, 2048]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[5632, 2048], [], [], []], "Ev Idx": 703 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1381189, + "ts": 1655274540650.213, "dur": 8.231, + "args": { + "External id": 4053697,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 2048]], "Input Dims": [[2048, 5632]], "Ev Idx": 704 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1381189, + "ts": 1655274540650.899, "dur": 7.188, + "args": { + "External id": 4053698,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 2048], [], []], "Input Dims": [[2048, 5632], [], []], "Ev Idx": 705 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274540655.550, "dur": 2.474, + "args": { + "External id": 4053699,"Record function id": 0, "Concrete Inputs": ["", "[5632, 2048]", "[2048, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 2048], [], [], []], "Input Dims": [[2048, 5632], [], [], []], "Ev Idx": 706 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655274540659.000, "dur": 44.941, + "args": { + "External id": 4053700,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [2048, 1]], "Input Dims": [[65536, 5632], [5632, 2048]], "Ev Idx": 707 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274540717.075, "dur": 29.378, + "args": { + "External id": 4053701,"Record function id": 0, "Sequence number": 40618505, "Fwd thread id": 1, "Ev Idx": 708 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274540718.036, "dur": 3.323, + "args": { + "External id": 4053702,"Sequence number": 40618505, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[65536, 2048]], "Ev Idx": 709 + } + }, + { + "ph": "f", "id": 75, "pid": 1336756, "tid": 1381189, "ts": 1655274540718.036, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1381189, + "ts": 1655274540719.267, "dur": 1.946, + "args": { + "External id": 4053703,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 710 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274540719.956, "dur": 1.160, + "args": { + "External id": 4053704,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 711 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add", "pid": 1336756, "tid": 1381189, + "ts": 1655274540724.222, "dur": 19.693, + "args": { + "External id": 4053705,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[8388608, 2048, 1], [8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], [16, 4096, 2048], []], "Ev Idx": 712 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: TBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274540750.558, "dur": 11.155, + "args": { + "External id": 4053706,"Record function id": 0, "Sequence number": 40618504, "Fwd thread id": 1, "Ev Idx": 713 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274540751.621, "dur": 8.245, + "args": { + "External id": 4053707,"Sequence number": 40618504, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 2048]], "Input Dims": [[2048, 5632]], "Ev Idx": 714 + } + }, + { + "ph": "f", "id": 76, "pid": 1336756, "tid": 1381189, "ts": 1655274540751.621, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1381189, + "ts": 1655274540752.499, "dur": 7.149, + "args": { + "External id": 4053708,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 2048]], "Input Dims": [[2048, 5632]], "Ev Idx": 715 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1381189, + "ts": 1655274540753.283, "dur": 5.812, + "args": { + "External id": 4053709,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 2048], [], []], "Input Dims": [[2048, 5632], [], []], "Ev Idx": 716 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274540758.366, "dur": 0.602, + "args": { + "External id": 4053710,"Record function id": 0, "Concrete Inputs": ["", "[5632, 2048]", "[2048, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 2048], [], [], []], "Input Dims": [[2048, 5632], [], [], []], "Ev Idx": 717 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274540765.620, "dur": 5.006, + "args": { + "External id": 4053711,"Record function id": 0, "Ev Idx": 718 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274540767.113, "dur": 3.052, + "args": { + "External id": 4053712,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 719 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274540768.106, "dur": 1.768, + "args": { + "External id": 4053713,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 720 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274540768.627, "dur": 1.173, + "args": { + "External id": 4053714,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 721 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: LayerNormFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1655274540776.999, "dur": 453.457, + "args": { + "External id": 4053715,"Record function id": 0, "Sequence number": 40618503, "Fwd thread id": 1, "Ev Idx": 722 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1655274540778.316, "dur": 419.703, + "args": { + "External id": 4053716,"Sequence number": 40618503, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[8388608, 2048, 1], [33554432, 8192, 1]], "Input Dims": [[16, 4096, 2048], [16, 4096, 2048]], "Ev Idx": 723 + } + }, + { + "ph": "f", "id": 77, "pid": 1336756, "tid": 1381189, "ts": 1655274540778.316, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::contiguous", "pid": 1336756, "tid": 1381189, + "ts": 1655274540799.735, "dur": 34.075, + "args": { + "External id": 4053717,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[33554432, 8192, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 724 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 1336756, "tid": 1381189, + "ts": 1655274540801.186, "dur": 32.425, + "args": { + "External id": 4053718,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[33554432, 8192, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 725 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336756, "tid": 1381189, + "ts": 1655274540803.673, "dur": 7.581, + "args": { + "External id": 4053719,"Record function id": 0, "Concrete Inputs": ["", "15", "0", "", "", "0"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[33554432, 8192, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 2048], [], [], [], [], []], "Ev Idx": 726 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655274540808.100, "dur": 2.614, + "args": { + "External id": 4053720,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 2048]", "15", "0", "", "", "0"], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 727 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1381189, + "ts": 1655274540812.619, "dur": 20.411, + "args": { + "External id": 4053721,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[8388608, 2048, 1], [33554432, 8192, 1], []], "Input Dims": [[16, 4096, 2048], [16, 4096, 2048], []], "Ev Idx": 728 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1381189, + "ts": 1655274540843.852, "dur": 4.491, + "args": { + "External id": 4053722,"Record function id": 0, "Concrete Inputs": ["", "[-1, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 729 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274540847.020, "dur": 1.176, + "args": { + "External id": 4053723,"Record function id": 0, "Concrete Inputs": ["", "[-1, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 730 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1381189, + "ts": 1655274540852.149, "dur": 3.657, + "args": { + "External id": 4053724,"Record function id": 0, "Concrete Inputs": ["", "[-1, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 731 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274540852.835, "dur": 2.882, + "args": { + "External id": 4053725,"Record function id": 0, "Concrete Inputs": ["", "[-1, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 732 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655274540867.303, "dur": 1.964, + "args": { + "External id": 4053726,"Record function id": 0, "Concrete Inputs": ["[65536, 2048]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 733 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655274540879.720, "dur": 1.870, + "args": { + "External id": 4053727,"Record function id": 0, "Concrete Inputs": ["[132, 2048]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 734 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274541084.186, "dur": 3.070, + "args": { + "External id": 4053728,"Record function id": 0, "Concrete Inputs": ["", "[1, -1, 2048]"], "Input type": ["float", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[132, 2048], []], "Ev Idx": 735 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 1336756, "tid": 1381189, + "ts": 1655274541091.445, "dur": 36.273, + "args": { + "External id": 4053729,"Record function id": 0, "Concrete Inputs": ["", "[1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", ""], "Input Strides": [[270336, 2048, 1], [], [], []], "Input Dims": [[1, 132, 2048], [], [], []], "Ev Idx": 736 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274541100.824, "dur": 1.306, + "args": { + "External id": 4053730,"Record function id": 0, "Concrete Inputs": ["", "[1, 1, 2048]", "[2048, 0, 1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[1, 2048], [], [], []], "Ev Idx": 737 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1381189, + "ts": 1655274541133.278, "dur": 30.313, + "args": { + "External id": 4053731,"Record function id": 0, "Concrete Inputs": ["", "", "15", "False", "False", ""], "Input type": ["float", "", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[2048, 1], [], [], [], [], []], "Input Dims": [[1, 2048], [], [], [], [], []], "Ev Idx": 738 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336756, "tid": 1381189, + "ts": 1655274541135.217, "dur": 28.136, + "args": { + "External id": 4053732,"Record function id": 0, "Concrete Inputs": ["", "15", "", "", "", "False", ""], "Input type": ["float", "Scalar", "", "", "", "Scalar", ""], "Input Strides": [[2048, 1], [], [], [], [], [], []], "Input Dims": [[1, 2048], [], [], [], [], [], []], "Ev Idx": 739 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274541140.880, "dur": 4.390, + "args": { + "External id": 4053733,"Record function id": 0, "Concrete Inputs": ["[1, 2048]", "[2048, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 740 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1381189, + "ts": 1655274541146.784, "dur": 15.942, + "args": { + "External id": 4053734,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "float", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[1, 2048], [1, 2048], []], "Ev Idx": 741 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 1336756, "tid": 1381189, + "ts": 1655274541168.749, "dur": 4.285, + "args": { + "External id": 4053735,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1]], "Input Dims": [[1, 2048], [2048]], "Ev Idx": 742 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274541172.021, "dur": 0.896, + "args": { + "External id": 4053736,"Record function id": 0, "Concrete Inputs": ["", "[2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[1, 2048], []], "Ev Idx": 743 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1381189, + "ts": 1655274541178.977, "dur": 1.999, + "args": { + "External id": 4053737,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 744 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274541179.882, "dur": 0.987, + "args": { + "External id": 4053738,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 745 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1381189, + "ts": 1655274541185.055, "dur": 3.722, + "args": { + "External id": 4053739,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 746 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274541185.676, "dur": 3.015, + "args": { + "External id": 4053740,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 747 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336756, "tid": 1381189, + "ts": 1655274541213.027, "dur": 15.855, + "args": { + "External id": 4053741,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[8388608, 2048, 1], [8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], [16, 4096, 2048], []], "Ev Idx": 748 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274541243.673, "dur": 10.651, + "args": { + "External id": 4053742,"Record function id": 0, "Ev Idx": 749 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274541245.741, "dur": 7.887, + "args": { + "External id": 4053743,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 750 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274541247.994, "dur": 4.854, + "args": { + "External id": 4053744,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 751 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274541251.152, "dur": 1.615, + "args": { + "External id": 4053745,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 752 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: UnsafeViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274541258.226, "dur": 6.379, + "args": { + "External id": 4053746,"Record function id": 0, "Sequence number": 40618502, "Fwd thread id": 1, "Ev Idx": 753 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274541258.933, "dur": 3.461, + "args": { + "External id": 4053747,"Sequence number": 40618502, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 754 + } + }, + { + "ph": "f", "id": 78, "pid": 1336756, "tid": 1381189, "ts": 1655274541258.933, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1381189, + "ts": 1655274541260.081, "dur": 2.138, + "args": { + "External id": 4053748,"Record function id": 0, "Concrete Inputs": ["", "[65536, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 755 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274541260.931, "dur": 1.122, + "args": { + "External id": 4053749,"Record function id": 0, "Concrete Inputs": ["", "[65536, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 756 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: MmBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274541268.060, "dur": 125.840, + "args": { + "External id": 4053750,"Record function id": 0, "Sequence number": 40618501, "Fwd thread id": 1, "Ev Idx": 757 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274541268.790, "dur": 118.994, + "args": { + "External id": 4053751,"Sequence number": 40618501, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[65536, 2048]], "Ev Idx": 758 + } + }, + { + "ph": "f", "id": 79, "pid": 1336756, "tid": 1381189, "ts": 1655274541268.790, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1381189, + "ts": 1655274541271.403, "dur": 8.788, + "args": { + "External id": 4053752,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[65536, 2048]], "Ev Idx": 759 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1381189, + "ts": 1655274541274.967, "dur": 4.545, + "args": { + "External id": 4053753,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[65536, 2048], [], []], "Ev Idx": 760 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274541278.741, "dur": 0.586, + "args": { + "External id": 4053754,"Record function id": 0, "Concrete Inputs": ["", "[2048, 65536]", "[1, 2048]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[65536, 2048], [], [], []], "Ev Idx": 761 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655274541281.160, "dur": 53.991, + "args": { + "External id": 4053755,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048]], "Ev Idx": 762 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1381189, + "ts": 1655274541336.320, "dur": 4.796, + "args": { + "External id": 4053756,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 763 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1381189, + "ts": 1655274541337.164, "dur": 3.386, + "args": { + "External id": 4053757,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[2048, 2048], [], []], "Ev Idx": 764 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274541338.071, "dur": 2.310, + "args": { + "External id": 4053758,"Record function id": 0, "Concrete Inputs": ["", "[2048, 2048]", "[1, 2048]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[2048, 2048], [], [], []], "Ev Idx": 765 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1381189, + "ts": 1655274541344.656, "dur": 2.642, + "args": { + "External id": 4053759,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 2048]], "Input Dims": [[2048, 2048]], "Ev Idx": 766 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1381189, + "ts": 1655274541345.713, "dur": 1.181, + "args": { + "External id": 4053760,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 2048], [], []], "Input Dims": [[2048, 2048], [], []], "Ev Idx": 767 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274541346.375, "dur": 0.423, + "args": { + "External id": 4053761,"Record function id": 0, "Concrete Inputs": ["", "[2048, 2048]", "[2048, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 2048], [], [], []], "Input Dims": [[2048, 2048], [], [], []], "Ev Idx": 768 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655274541347.978, "dur": 38.886, + "args": { + "External id": 4053762,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048]], "Ev Idx": 769 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274541398.852, "dur": 10.007, + "args": { + "External id": 4053763,"Record function id": 0, "Sequence number": 40618500, "Fwd thread id": 1, "Ev Idx": 770 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274541399.760, "dur": 7.473, + "args": { + "External id": 4053764,"Sequence number": 40618500, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[65536, 2048]], "Ev Idx": 771 + } + }, + { + "ph": "f", "id": 80, "pid": 1336756, "tid": 1381189, "ts": 1655274541399.760, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1381189, + "ts": 1655274541402.937, "dur": 4.141, + "args": { + "External id": 4053765,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 772 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274541403.786, "dur": 3.140, + "args": { + "External id": 4053766,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 773 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: TBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274541414.065, "dur": 28.983, + "args": { + "External id": 4053767,"Record function id": 0, "Sequence number": 40618499, "Fwd thread id": 1, "Ev Idx": 774 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274541434.318, "dur": 5.573, + "args": { + "External id": 4053768,"Sequence number": 40618499, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 2048]], "Input Dims": [[2048, 2048]], "Ev Idx": 775 + } + }, + { + "ph": "f", "id": 81, "pid": 1336756, "tid": 1381189, "ts": 1655274541434.318, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1381189, + "ts": 1655274541435.335, "dur": 4.353, + "args": { + "External id": 4053769,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 2048]], "Input Dims": [[2048, 2048]], "Ev Idx": 776 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1381189, + "ts": 1655274541436.531, "dur": 2.467, + "args": { + "External id": 4053770,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 2048], [], []], "Input Dims": [[2048, 2048], [], []], "Ev Idx": 777 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274541438.002, "dur": 0.736, + "args": { + "External id": 4053771,"Record function id": 0, "Concrete Inputs": ["", "[2048, 2048]", "[2048, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 2048], [], [], []], "Input Dims": [[2048, 2048], [], [], []], "Ev Idx": 778 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274541449.057, "dur": 5.807, + "args": { + "External id": 4053772,"Record function id": 0, "Ev Idx": 779 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274541450.521, "dur": 3.833, + "args": { + "External id": 4053773,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 780 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274541451.718, "dur": 2.343, + "args": { + "External id": 4053774,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 781 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274541452.497, "dur": 1.493, + "args": { + "External id": 4053775,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 782 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274541457.757, "dur": 9.629, + "args": { + "External id": 4053776,"Record function id": 0, "Sequence number": 40618498, "Fwd thread id": 1, "Ev Idx": 783 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274541458.473, "dur": 7.226, + "args": { + "External id": 4053777,"Sequence number": 40618498, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 784 + } + }, + { + "ph": "f", "id": 82, "pid": 1336756, "tid": 1381189, "ts": 1655274541458.473, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1381189, + "ts": 1655274541461.350, "dur": 4.189, + "args": { + "External id": 4053778,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 32, 64]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 785 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274541463.794, "dur": 1.599, + "args": { + "External id": 4053779,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 32, 64]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 786 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: FlashAttnFuncBackward", "pid": 1336756, "tid": 1381189, + "ts": 1655274541471.452, "dur": 276.558, + "args": { + "External id": 4053780,"Record function id": 0, "Sequence number": 40618497, "Fwd thread id": 1, "Ev Idx": 787 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "FlashAttnFuncBackward", "pid": 1336756, "tid": 1381189, + "ts": 1655274541472.563, "dur": 258.854, + "args": { + "External id": 4053781,"Sequence number": 40618497, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 64, 1]], "Input Dims": [[16, 4096, 32, 64]], "Ev Idx": 788 + } + }, + { + "ph": "f", "id": 83, "pid": 1336756, "tid": 1381189, "ts": 1655274541472.563, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336756, "tid": 1381189, + "ts": 1655274541488.355, "dur": 6.693, + "args": { + "External id": 4053782,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[8388608, 2048, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [], [], [], [], []], "Ev Idx": 789 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274541490.539, "dur": 4.043, + "args": { + "External id": 4053783,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "[8388608, 2048, 64, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 790 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336756, "tid": 1381189, + "ts": 1655274541496.999, "dur": 5.078, + "args": { + "External id": 4053784,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[8388608, 2048, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [], [], [], [], []], "Ev Idx": 791 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274541499.796, "dur": 2.105, + "args": { + "External id": 4053785,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "[8388608, 2048, 64, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 792 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336756, "tid": 1381189, + "ts": 1655274541503.286, "dur": 4.302, + "args": { + "External id": 4053786,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[8388608, 2048, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [], [], [], [], []], "Ev Idx": 793 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274541504.463, "dur": 2.965, + "args": { + "External id": 4053787,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "[8388608, 2048, 64, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 794 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 1336756, "tid": 1381189, + "ts": 1655274541534.451, "dur": 171.706, + "args": { + "External id": 4053788,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.125", "True", "-1", "-1", "0.", "", "False", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar", "long int"], "Input Strides": [[8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [131072, 4096, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 32, 4096], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 795 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655274541612.216, "dur": 3.482, + "args": { + "External id": 4053789,"Record function id": 0, "Concrete Inputs": ["[16, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 796 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655274541617.707, "dur": 4.136, + "args": { + "External id": 4053790,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 797 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::alias", "pid": 1336756, "tid": 1381189, + "ts": 1655274541718.820, "dur": 3.690, + "args": { + "External id": 4053791,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 64, 1]], "Input Dims": [[16, 4096, 32, 64]], "Ev Idx": 798 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::alias", "pid": 1336756, "tid": 1381189, + "ts": 1655274541725.622, "dur": 0.658, + "args": { + "External id": 4053792,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 64, 1]], "Input Dims": [[16, 4096, 32, 64]], "Ev Idx": 799 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::alias", "pid": 1336756, "tid": 1381189, + "ts": 1655274541728.227, "dur": 0.611, + "args": { + "External id": 4053793,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 64, 1]], "Input Dims": [[16, 4096, 32, 64]], "Ev Idx": 800 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RotaryEmbeddingFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1655274541754.775, "dur": 217.149, + "args": { + "External id": 4053794,"Record function id": 0, "Sequence number": 40618496, "Fwd thread id": 1, "Ev Idx": 801 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1655274541756.171, "dur": 209.418, + "args": { + "External id": 4053795,"Sequence number": 40618496, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 64, 1]], "Input Dims": [[16, 4096, 32, 64]], "Ev Idx": 802 + } + }, + { + "ph": "f", "id": 84, "pid": 1336756, "tid": 1381189, "ts": 1655274541756.171, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 1336756, "tid": 1381189, + "ts": 1655274541776.335, "dur": 42.576, + "args": { + "External id": 4053796,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", ""], "Input Strides": [[8388608, 2048, 64, 1], []], "Input Dims": [[16, 4096, 32, 64], []], "Ev Idx": 803 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274541778.700, "dur": 2.541, + "args": { + "External id": 4053797,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "[8388608, 2048, 64, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 804 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1381189, + "ts": 1655274541782.737, "dur": 35.595, + "args": { + "External id": 4053798,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [8388608, 2048, 64, 1], []], "Input Dims": [[16, 4096, 32, 64], [16, 4096, 32, 64], []], "Ev Idx": 805 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336756, "tid": 1381189, + "ts": 1655274541827.462, "dur": 5.783, + "args": { + "External id": 4053799,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[8388608, 2048, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [], [], [], [], []], "Ev Idx": 806 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274541830.915, "dur": 2.049, + "args": { + "External id": 4053800,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "[8388608, 2048, 64, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 807 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RotaryEmbeddingFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1655274541978.484, "dur": 201.408, + "args": { + "External id": 4053801,"Record function id": 0, "Sequence number": 40618495, "Fwd thread id": 1, "Ev Idx": 808 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1655274541979.821, "dur": 193.597, + "args": { + "External id": 4053802,"Sequence number": 40618495, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 64, 1]], "Input Dims": [[16, 4096, 32, 64]], "Ev Idx": 809 + } + }, + { + "ph": "f", "id": 85, "pid": 1336756, "tid": 1381189, "ts": 1655274541979.821, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 1336756, "tid": 1381189, + "ts": 1655274542033.584, "dur": 36.480, + "args": { + "External id": 4053803,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", ""], "Input Strides": [[8388608, 2048, 64, 1], []], "Input Dims": [[16, 4096, 32, 64], []], "Ev Idx": 810 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274542036.148, "dur": 3.840, + "args": { + "External id": 4053804,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "[8388608, 2048, 64, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 811 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1381189, + "ts": 1655274542041.160, "dur": 28.222, + "args": { + "External id": 4053805,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [8388608, 2048, 64, 1], []], "Input Dims": [[16, 4096, 32, 64], [16, 4096, 32, 64], []], "Ev Idx": 812 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336756, "tid": 1381189, + "ts": 1655274542077.138, "dur": 8.404, + "args": { + "External id": 4053806,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[8388608, 2048, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [], [], [], [], []], "Ev Idx": 813 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274542082.935, "dur": 2.340, + "args": { + "External id": 4053807,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "[8388608, 2048, 64, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 814 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274542188.045, "dur": 14.121, + "args": { + "External id": 4053808,"Record function id": 0, "Sequence number": 40618494, "Fwd thread id": 1, "Ev Idx": 815 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274542189.681, "dur": 9.650, + "args": { + "External id": 4053809,"Sequence number": 40618494, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 64, 1]], "Input Dims": [[16, 4096, 32, 64]], "Ev Idx": 816 + } + }, + { + "ph": "f", "id": 86, "pid": 1336756, "tid": 1381189, "ts": 1655274542189.681, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1381189, + "ts": 1655274542191.601, "dur": 7.423, + "args": { + "External id": 4053810,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 64, 1], []], "Input Dims": [[16, 4096, 32, 64], []], "Ev Idx": 817 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274542192.838, "dur": 5.990, + "args": { + "External id": 4053811,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 64, 1], []], "Input Dims": [[16, 4096, 32, 64], []], "Ev Idx": 818 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274542205.840, "dur": 9.425, + "args": { + "External id": 4053812,"Record function id": 0, "Sequence number": 40618493, "Fwd thread id": 1, "Ev Idx": 819 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274542208.967, "dur": 4.258, + "args": { + "External id": 4053813,"Sequence number": 40618493, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 64, 1]], "Input Dims": [[16, 4096, 32, 64]], "Ev Idx": 820 + } + }, + { + "ph": "f", "id": 87, "pid": 1336756, "tid": 1381189, "ts": 1655274542208.967, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1381189, + "ts": 1655274542209.943, "dur": 3.141, + "args": { + "External id": 4053814,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 64, 1], []], "Input Dims": [[16, 4096, 32, 64], []], "Ev Idx": 821 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274542212.249, "dur": 0.728, + "args": { + "External id": 4053815,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 64, 1], []], "Input Dims": [[16, 4096, 32, 64], []], "Ev Idx": 822 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274542220.947, "dur": 5.078, + "args": { + "External id": 4053816,"Record function id": 0, "Sequence number": 40618492, "Fwd thread id": 1, "Ev Idx": 823 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274542221.615, "dur": 2.499, + "args": { + "External id": 4053817,"Sequence number": 40618492, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 64, 1]], "Input Dims": [[16, 4096, 32, 64]], "Ev Idx": 824 + } + }, + { + "ph": "f", "id": 88, "pid": 1336756, "tid": 1381189, "ts": 1655274542221.615, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1381189, + "ts": 1655274542222.731, "dur": 1.246, + "args": { + "External id": 4053818,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 64, 1], []], "Input Dims": [[16, 4096, 32, 64], []], "Ev Idx": 825 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274542223.180, "dur": 0.661, + "args": { + "External id": 4053819,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 64, 1], []], "Input Dims": [[16, 4096, 32, 64], []], "Ev Idx": 826 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: UnsafeViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274542229.224, "dur": 9.352, + "args": { + "External id": 4053820,"Record function id": 0, "Sequence number": 40618491, "Fwd thread id": 1, "Ev Idx": 827 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274542230.084, "dur": 6.625, + "args": { + "External id": 4053821,"Sequence number": 40618491, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 828 + } + }, + { + "ph": "f", "id": 89, "pid": 1336756, "tid": 1381189, "ts": 1655274542230.084, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1381189, + "ts": 1655274542230.836, "dur": 5.720, + "args": { + "External id": 4053822,"Record function id": 0, "Concrete Inputs": ["", "[65536, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 829 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274542235.605, "dur": 0.858, + "args": { + "External id": 4053823,"Record function id": 0, "Concrete Inputs": ["", "[65536, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 830 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: MmBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274542242.081, "dur": 140.574, + "args": { + "External id": 4053824,"Record function id": 0, "Sequence number": 40618490, "Fwd thread id": 1, "Ev Idx": 831 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274542242.796, "dur": 132.108, + "args": { + "External id": 4053825,"Sequence number": 40618490, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[65536, 2048]], "Ev Idx": 832 + } + }, + { + "ph": "f", "id": 90, "pid": 1336756, "tid": 1381189, "ts": 1655274542242.796, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1381189, + "ts": 1655274542246.035, "dur": 6.231, + "args": { + "External id": 4053826,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[65536, 2048]], "Ev Idx": 833 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1381189, + "ts": 1655274542248.131, "dur": 3.562, + "args": { + "External id": 4053827,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[65536, 2048], [], []], "Ev Idx": 834 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274542249.932, "dur": 1.477, + "args": { + "External id": 4053828,"Record function id": 0, "Concrete Inputs": ["", "[2048, 65536]", "[1, 2048]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[65536, 2048], [], [], []], "Ev Idx": 835 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655274542253.707, "dur": 64.271, + "args": { + "External id": 4053829,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048]], "Ev Idx": 836 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1381189, + "ts": 1655274542319.300, "dur": 5.566, + "args": { + "External id": 4053830,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 837 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1381189, + "ts": 1655274542321.889, "dur": 2.373, + "args": { + "External id": 4053831,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[2048, 2048], [], []], "Ev Idx": 838 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274542323.145, "dur": 0.967, + "args": { + "External id": 4053832,"Record function id": 0, "Concrete Inputs": ["", "[2048, 2048]", "[1, 2048]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[2048, 2048], [], [], []], "Ev Idx": 839 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1381189, + "ts": 1655274542326.485, "dur": 4.559, + "args": { + "External id": 4053833,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 2048]], "Input Dims": [[2048, 2048]], "Ev Idx": 840 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1381189, + "ts": 1655274542327.238, "dur": 3.325, + "args": { + "External id": 4053834,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 2048], [], []], "Input Dims": [[2048, 2048], [], []], "Ev Idx": 841 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274542330.126, "dur": 0.355, + "args": { + "External id": 4053835,"Record function id": 0, "Concrete Inputs": ["", "[2048, 2048]", "[2048, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 2048], [], [], []], "Input Dims": [[2048, 2048], [], [], []], "Ev Idx": 842 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655274542331.843, "dur": 42.117, + "args": { + "External id": 4053836,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048]], "Ev Idx": 843 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274542387.232, "dur": 8.321, + "args": { + "External id": 4053837,"Record function id": 0, "Sequence number": 40618489, "Fwd thread id": 1, "Ev Idx": 844 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274542388.345, "dur": 5.566, + "args": { + "External id": 4053838,"Sequence number": 40618489, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[65536, 2048]], "Ev Idx": 845 + } + }, + { + "ph": "f", "id": 91, "pid": 1336756, "tid": 1381189, "ts": 1655274542388.345, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1381189, + "ts": 1655274542391.793, "dur": 1.981, + "args": { + "External id": 4053839,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 846 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274542392.631, "dur": 1.050, + "args": { + "External id": 4053840,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 847 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: TBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274542399.081, "dur": 6.386, + "args": { + "External id": 4053841,"Record function id": 0, "Sequence number": 40618488, "Fwd thread id": 1, "Ev Idx": 848 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274542400.187, "dur": 3.651, + "args": { + "External id": 4053842,"Sequence number": 40618488, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 2048]], "Input Dims": [[2048, 2048]], "Ev Idx": 849 + } + }, + { + "ph": "f", "id": 92, "pid": 1336756, "tid": 1381189, "ts": 1655274542400.187, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1381189, + "ts": 1655274542401.086, "dur": 2.540, + "args": { + "External id": 4053843,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 2048]], "Input Dims": [[2048, 2048]], "Ev Idx": 850 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1381189, + "ts": 1655274542401.766, "dur": 1.376, + "args": { + "External id": 4053844,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 2048], [], []], "Input Dims": [[2048, 2048], [], []], "Ev Idx": 851 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274542402.516, "dur": 0.523, + "args": { + "External id": 4053845,"Record function id": 0, "Concrete Inputs": ["", "[2048, 2048]", "[2048, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 2048], [], [], []], "Input Dims": [[2048, 2048], [], [], []], "Ev Idx": 852 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274542413.637, "dur": 30.760, + "args": { + "External id": 4053846,"Record function id": 0, "Ev Idx": 853 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274542432.738, "dur": 10.409, + "args": { + "External id": 4053847,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 854 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274542435.891, "dur": 6.774, + "args": { + "External id": 4053848,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 855 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274542439.108, "dur": 3.303, + "args": { + "External id": 4053849,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 856 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: UnsafeViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274542449.451, "dur": 6.227, + "args": { + "External id": 4053850,"Record function id": 0, "Sequence number": 40618487, "Fwd thread id": 1, "Ev Idx": 857 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274542450.690, "dur": 3.470, + "args": { + "External id": 4053851,"Sequence number": 40618487, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 858 + } + }, + { + "ph": "f", "id": 93, "pid": 1336756, "tid": 1381189, "ts": 1655274542450.690, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1381189, + "ts": 1655274542451.789, "dur": 2.202, + "args": { + "External id": 4053852,"Record function id": 0, "Concrete Inputs": ["", "[65536, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 859 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274542452.585, "dur": 1.311, + "args": { + "External id": 4053853,"Record function id": 0, "Concrete Inputs": ["", "[65536, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 860 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: MmBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274542458.917, "dur": 95.848, + "args": { + "External id": 4053854,"Record function id": 0, "Sequence number": 40618486, "Fwd thread id": 1, "Ev Idx": 861 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274542459.884, "dur": 89.702, + "args": { + "External id": 4053855,"Sequence number": 40618486, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[65536, 2048]], "Ev Idx": 862 + } + }, + { + "ph": "f", "id": 94, "pid": 1336756, "tid": 1381189, "ts": 1655274542459.884, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1381189, + "ts": 1655274542461.844, "dur": 5.376, + "args": { + "External id": 4053856,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[65536, 2048]], "Ev Idx": 863 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1381189, + "ts": 1655274542465.024, "dur": 1.774, + "args": { + "External id": 4053857,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[65536, 2048], [], []], "Ev Idx": 864 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274542465.889, "dur": 0.804, + "args": { + "External id": 4053858,"Record function id": 0, "Concrete Inputs": ["", "[2048, 65536]", "[1, 2048]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[65536, 2048], [], [], []], "Ev Idx": 865 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655274542468.016, "dur": 30.948, + "args": { + "External id": 4053859,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048]], "Ev Idx": 866 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1381189, + "ts": 1655274542499.903, "dur": 6.056, + "args": { + "External id": 4053860,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 867 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1381189, + "ts": 1655274542500.770, "dur": 4.742, + "args": { + "External id": 4053861,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[2048, 2048], [], []], "Ev Idx": 868 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274542504.333, "dur": 1.029, + "args": { + "External id": 4053862,"Record function id": 0, "Concrete Inputs": ["", "[2048, 2048]", "[1, 2048]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[2048, 2048], [], [], []], "Ev Idx": 869 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1381189, + "ts": 1655274542508.968, "dur": 5.208, + "args": { + "External id": 4053863,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 2048]], "Input Dims": [[2048, 2048]], "Ev Idx": 870 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1381189, + "ts": 1655274542510.218, "dur": 3.594, + "args": { + "External id": 4053864,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 2048], [], []], "Input Dims": [[2048, 2048], [], []], "Ev Idx": 871 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274542511.062, "dur": 2.650, + "args": { + "External id": 4053865,"Record function id": 0, "Concrete Inputs": ["", "[2048, 2048]", "[2048, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 2048], [], [], []], "Input Dims": [[2048, 2048], [], [], []], "Ev Idx": 872 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655274542514.853, "dur": 34.039, + "args": { + "External id": 4053866,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048]], "Ev Idx": 873 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274542559.608, "dur": 34.285, + "args": { + "External id": 4053867,"Record function id": 0, "Sequence number": 40618485, "Fwd thread id": 1, "Ev Idx": 874 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274542560.491, "dur": 5.041, + "args": { + "External id": 4053868,"Sequence number": 40618485, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[65536, 2048]], "Ev Idx": 875 + } + }, + { + "ph": "f", "id": 95, "pid": 1336756, "tid": 1381189, "ts": 1655274542560.491, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1381189, + "ts": 1655274542561.752, "dur": 3.638, + "args": { + "External id": 4053869,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 876 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274542564.364, "dur": 0.930, + "args": { + "External id": 4053870,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 877 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add", "pid": 1336756, "tid": 1381189, + "ts": 1655274542568.908, "dur": 20.974, + "args": { + "External id": 4053871,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[8388608, 2048, 1], [8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], [16, 4096, 2048], []], "Ev Idx": 878 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: TBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274542597.730, "dur": 6.773, + "args": { + "External id": 4053872,"Record function id": 0, "Sequence number": 40618484, "Fwd thread id": 1, "Ev Idx": 879 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274542598.707, "dur": 3.659, + "args": { + "External id": 4053873,"Sequence number": 40618484, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 2048]], "Input Dims": [[2048, 2048]], "Ev Idx": 880 + } + }, + { + "ph": "f", "id": 96, "pid": 1336756, "tid": 1381189, "ts": 1655274542598.707, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1381189, + "ts": 1655274542599.597, "dur": 2.547, + "args": { + "External id": 4053874,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 2048]], "Input Dims": [[2048, 2048]], "Ev Idx": 881 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1381189, + "ts": 1655274542600.267, "dur": 1.420, + "args": { + "External id": 4053875,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 2048], [], []], "Input Dims": [[2048, 2048], [], []], "Ev Idx": 882 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274542601.128, "dur": 0.437, + "args": { + "External id": 4053876,"Record function id": 0, "Concrete Inputs": ["", "[2048, 2048]", "[2048, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 2048], [], [], []], "Input Dims": [[2048, 2048], [], [], []], "Ev Idx": 883 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274542608.437, "dur": 7.165, + "args": { + "External id": 4053877,"Record function id": 0, "Ev Idx": 884 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274542609.652, "dur": 5.480, + "args": { + "External id": 4053878,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 885 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274542610.647, "dur": 4.200, + "args": { + "External id": 4053879,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 886 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274542613.813, "dur": 0.920, + "args": { + "External id": 4053880,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 887 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: UnsafeViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274542619.100, "dur": 7.769, + "args": { + "External id": 4053881,"Record function id": 0, "Sequence number": 40618483, "Fwd thread id": 1, "Ev Idx": 888 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274542619.912, "dur": 4.918, + "args": { + "External id": 4053882,"Sequence number": 40618483, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 889 + } + }, + { + "ph": "f", "id": 97, "pid": 1336756, "tid": 1381189, "ts": 1655274542619.912, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1381189, + "ts": 1655274542621.020, "dur": 3.664, + "args": { + "External id": 4053883,"Record function id": 0, "Concrete Inputs": ["", "[65536, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 890 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274542623.771, "dur": 0.729, + "args": { + "External id": 4053884,"Record function id": 0, "Concrete Inputs": ["", "[65536, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 891 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: MmBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274542632.294, "dur": 92.577, + "args": { + "External id": 4053885,"Record function id": 0, "Sequence number": 40618482, "Fwd thread id": 1, "Ev Idx": 892 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274542633.122, "dur": 84.663, + "args": { + "External id": 4053886,"Sequence number": 40618482, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[65536, 2048]], "Ev Idx": 893 + } + }, + { + "ph": "f", "id": 98, "pid": 1336756, "tid": 1381189, "ts": 1655274542633.122, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1381189, + "ts": 1655274542635.129, "dur": 4.546, + "args": { + "External id": 4053887,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[65536, 2048]], "Ev Idx": 894 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1381189, + "ts": 1655274542635.915, "dur": 3.354, + "args": { + "External id": 4053888,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[65536, 2048], [], []], "Ev Idx": 895 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274542638.715, "dur": 0.442, + "args": { + "External id": 4053889,"Record function id": 0, "Concrete Inputs": ["", "[2048, 65536]", "[1, 2048]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[65536, 2048], [], [], []], "Ev Idx": 896 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655274542640.384, "dur": 27.123, + "args": { + "External id": 4053890,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048]], "Ev Idx": 897 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1381189, + "ts": 1655274542668.344, "dur": 3.180, + "args": { + "External id": 4053891,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 898 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1381189, + "ts": 1655274542668.882, "dur": 2.165, + "args": { + "External id": 4053892,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[2048, 2048], [], []], "Ev Idx": 899 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274542669.839, "dur": 1.091, + "args": { + "External id": 4053893,"Record function id": 0, "Concrete Inputs": ["", "[2048, 2048]", "[1, 2048]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[2048, 2048], [], [], []], "Ev Idx": 900 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1381189, + "ts": 1655274542672.763, "dur": 10.008, + "args": { + "External id": 4053894,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 2048]], "Input Dims": [[2048, 2048]], "Ev Idx": 901 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1381189, + "ts": 1655274542678.958, "dur": 3.391, + "args": { + "External id": 4053895,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 2048], [], []], "Input Dims": [[2048, 2048], [], []], "Ev Idx": 902 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274542681.893, "dur": 0.344, + "args": { + "External id": 4053896,"Record function id": 0, "Concrete Inputs": ["", "[2048, 2048]", "[2048, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 2048], [], [], []], "Input Dims": [[2048, 2048], [], [], []], "Ev Idx": 903 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655274542683.449, "dur": 33.542, + "args": { + "External id": 4053897,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048]], "Ev Idx": 904 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274542729.550, "dur": 22.772, + "args": { + "External id": 4053898,"Record function id": 0, "Sequence number": 40618481, "Fwd thread id": 1, "Ev Idx": 905 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274542730.559, "dur": 3.171, + "args": { + "External id": 4053899,"Sequence number": 40618481, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[65536, 2048]], "Ev Idx": 906 + } + }, + { + "ph": "f", "id": 99, "pid": 1336756, "tid": 1381189, "ts": 1655274542730.559, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1381189, + "ts": 1655274542731.573, "dur": 2.005, + "args": { + "External id": 4053900,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 907 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274542732.359, "dur": 1.087, + "args": { + "External id": 4053901,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 908 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336756, "tid": 1381189, + "ts": 1655274542735.838, "dur": 14.364, + "args": { + "External id": 4053902,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[8388608, 2048, 1], [8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], [16, 4096, 2048], []], "Ev Idx": 909 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: TBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274542755.890, "dur": 10.845, + "args": { + "External id": 4053903,"Record function id": 0, "Sequence number": 40618480, "Fwd thread id": 1, "Ev Idx": 910 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274542759.119, "dur": 5.869, + "args": { + "External id": 4053904,"Sequence number": 40618480, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 2048]], "Input Dims": [[2048, 2048]], "Ev Idx": 911 + } + }, + { + "ph": "f", "id": 100, "pid": 1336756, "tid": 1381189, "ts": 1655274542759.119, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1381189, + "ts": 1655274542759.994, "dur": 4.788, + "args": { + "External id": 4053905,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 2048]], "Input Dims": [[2048, 2048]], "Ev Idx": 912 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1381189, + "ts": 1655274542760.859, "dur": 3.389, + "args": { + "External id": 4053906,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 2048], [], []], "Input Dims": [[2048, 2048], [], []], "Ev Idx": 913 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274542763.555, "dur": 0.596, + "args": { + "External id": 4053907,"Record function id": 0, "Concrete Inputs": ["", "[2048, 2048]", "[2048, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 2048], [], [], []], "Input Dims": [[2048, 2048], [], [], []], "Ev Idx": 914 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274542770.396, "dur": 4.866, + "args": { + "External id": 4053908,"Record function id": 0, "Ev Idx": 915 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274542771.641, "dur": 3.158, + "args": { + "External id": 4053909,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 916 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274542772.906, "dur": 1.601, + "args": { + "External id": 4053910,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 917 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274542773.408, "dur": 0.980, + "args": { + "External id": 4053911,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 918 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: LayerNormFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1655274542779.555, "dur": 386.131, + "args": { + "External id": 4053912,"Record function id": 0, "Sequence number": 40618479, "Fwd thread id": 1, "Ev Idx": 919 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1655274542780.879, "dur": 349.967, + "args": { + "External id": 4053913,"Sequence number": 40618479, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 920 + } + }, + { + "ph": "f", "id": 101, "pid": 1336756, "tid": 1381189, "ts": 1655274542780.879, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1381189, + "ts": 1655274542811.564, "dur": 3.697, + "args": { + "External id": 4053914,"Record function id": 0, "Concrete Inputs": ["", "[-1, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 921 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274542814.183, "dur": 0.934, + "args": { + "External id": 4053915,"Record function id": 0, "Concrete Inputs": ["", "[-1, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 922 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655274542829.316, "dur": 5.252, + "args": { + "External id": 4053916,"Record function id": 0, "Concrete Inputs": ["[65536, 2048]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 923 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655274542843.567, "dur": 1.691, + "args": { + "External id": 4053917,"Record function id": 0, "Concrete Inputs": ["[132, 2048]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 924 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274542981.820, "dur": 1.593, + "args": { + "External id": 4053918,"Record function id": 0, "Concrete Inputs": ["", "[1, -1, 2048]"], "Input type": ["float", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[132, 2048], []], "Ev Idx": 925 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 1336756, "tid": 1381189, + "ts": 1655274543026.217, "dur": 38.304, + "args": { + "External id": 4053919,"Record function id": 0, "Concrete Inputs": ["", "[1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", ""], "Input Strides": [[270336, 2048, 1], [], [], []], "Input Dims": [[1, 132, 2048], [], [], []], "Ev Idx": 926 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274543038.086, "dur": 1.021, + "args": { + "External id": 4053920,"Record function id": 0, "Concrete Inputs": ["", "[1, 1, 2048]", "[2048, 0, 1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[1, 2048], [], [], []], "Ev Idx": 927 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1381189, + "ts": 1655274543074.079, "dur": 33.964, + "args": { + "External id": 4053921,"Record function id": 0, "Concrete Inputs": ["", "", "15", "False", "False", ""], "Input type": ["float", "", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[2048, 1], [], [], [], [], []], "Input Dims": [[1, 2048], [], [], [], [], []], "Ev Idx": 928 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336756, "tid": 1381189, + "ts": 1655274543076.083, "dur": 31.767, + "args": { + "External id": 4053922,"Record function id": 0, "Concrete Inputs": ["", "15", "", "", "", "False", ""], "Input type": ["float", "Scalar", "", "", "", "Scalar", ""], "Input Strides": [[2048, 1], [], [], [], [], [], []], "Input Dims": [[1, 2048], [], [], [], [], [], []], "Ev Idx": 929 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274543084.140, "dur": 5.099, + "args": { + "External id": 4053923,"Record function id": 0, "Concrete Inputs": ["[1, 2048]", "[2048, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 930 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1381189, + "ts": 1655274543090.822, "dur": 16.428, + "args": { + "External id": 4053924,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "float", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[1, 2048], [1, 2048], []], "Ev Idx": 931 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 1336756, "tid": 1381189, + "ts": 1655274543112.615, "dur": 3.006, + "args": { + "External id": 4053925,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1]], "Input Dims": [[1, 2048], [2048]], "Ev Idx": 932 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274543114.146, "dur": 1.382, + "args": { + "External id": 4053926,"Record function id": 0, "Concrete Inputs": ["", "[2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[1, 2048], []], "Ev Idx": 933 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1381189, + "ts": 1655274543121.445, "dur": 2.224, + "args": { + "External id": 4053927,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 934 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274543122.490, "dur": 1.033, + "args": { + "External id": 4053928,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 935 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336756, "tid": 1381189, + "ts": 1655274543143.328, "dur": 18.093, + "args": { + "External id": 4053929,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[8388608, 2048, 1], [8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], [16, 4096, 2048], []], "Ev Idx": 936 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274543178.040, "dur": 10.510, + "args": { + "External id": 4053930,"Record function id": 0, "Ev Idx": 937 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274543181.926, "dur": 5.853, + "args": { + "External id": 4053931,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 938 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274543184.083, "dur": 2.573, + "args": { + "External id": 4053932,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 939 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274543184.945, "dur": 1.575, + "args": { + "External id": 4053933,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 940 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: AddBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274543192.359, "dur": 5.199, + "args": { + "External id": 4053934,"Record function id": 0, "Sequence number": 40618478, "Fwd thread id": 1, "Ev Idx": 941 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "AddBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274543193.640, "dur": 1.046, + "args": { + "External id": 4053935,"Sequence number": 40618478, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[33554432, 8192, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 942 + } + }, + { + "ph": "f", "id": 102, "pid": 1336756, "tid": 1381189, "ts": 1655274543193.640, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: SwiGLULinearFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1655274543201.482, "dur": 459.298, + "args": { + "External id": 4053936,"Record function id": 0, "Sequence number": 40618477, "Fwd thread id": 1, "Ev Idx": 943 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SwiGLULinearFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1655274543202.848, "dur": 446.427, + "args": { + "External id": 4053937,"Sequence number": 40618477, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[33554432, 8192, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 944 + } + }, + { + "ph": "f", "id": 103, "pid": 1336756, "tid": 1381189, "ts": 1655274543202.848, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1381189, + "ts": 1655274543234.544, "dur": 7.894, + "args": { + "External id": 4053938,"Record function id": 0, "Concrete Inputs": ["", "[-1, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[33554432, 8192, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 945 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_reshape_alias", "pid": 1336756, "tid": 1381189, + "ts": 1655274543239.051, "dur": 3.166, + "args": { + "External id": 4053939,"Record function id": 0, "Concrete Inputs": ["", "[65536, 2048]", "[8192, 1]"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList"], "Input Strides": [[33554432, 8192, 1], [], []], "Input Dims": [[16, 4096, 2048], [], []], "Ev Idx": 946 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1381189, + "ts": 1655274543245.739, "dur": 6.201, + "args": { + "External id": 4053940,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 947 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1381189, + "ts": 1655274543247.203, "dur": 4.104, + "args": { + "External id": 4053941,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[5632, 1], [], []], "Input Dims": [[2048, 5632], [], []], "Ev Idx": 948 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274543250.507, "dur": 0.642, + "args": { + "External id": 4053942,"Record function id": 0, "Concrete Inputs": ["", "[5632, 2048]", "[1, 5632]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[5632, 1], [], [], []], "Input Dims": [[2048, 5632], [], [], []], "Ev Idx": 949 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336756, "tid": 1381189, + "ts": 1655274543255.511, "dur": 104.589, + "args": { + "External id": 4053943,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[8192, 1], [1, 5632], []], "Input Dims": [[65536, 2048], [5632, 2048], []], "Ev Idx": 950 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1381189, + "ts": 1655274543256.554, "dur": 6.795, + "args": { + "External id": 4053944,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 5632]], "Input Dims": [[5632, 2048]], "Ev Idx": 951 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1381189, + "ts": 1655274543259.258, "dur": 3.625, + "args": { + "External id": 4053945,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 5632], [], []], "Input Dims": [[5632, 2048], [], []], "Ev Idx": 952 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274543260.355, "dur": 2.432, + "args": { + "External id": 4053946,"Record function id": 0, "Concrete Inputs": ["", "[2048, 5632]", "[5632, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 5632], [], [], []], "Input Dims": [[5632, 2048], [], [], []], "Ev Idx": 953 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336756, "tid": 1381189, + "ts": 1655274543264.629, "dur": 94.890, + "args": { + "External id": 4053947,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[8192, 1], [5632, 1]], "Input Dims": [[65536, 2048], [2048, 5632]], "Ev Idx": 954 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655274543266.456, "dur": 92.061, + "args": { + "External id": 4053948,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[8192, 1], [5632, 1]], "Input Dims": [[65536, 2048], [2048, 5632]], "Ev Idx": 955 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 1336756, "tid": 1381189, + "ts": 1655274543363.543, "dur": 2.428, + "args": { + "External id": 4053949,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [23068672, 5632, 1]], "Input Dims": [[65536, 5632], [16, 4096, 5632]], "Ev Idx": 956 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274543364.609, "dur": 1.194, + "args": { + "External id": 4053950,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 5632]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[5632, 1], []], "Input Dims": [[65536, 5632], []], "Ev Idx": 957 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655274543398.077, "dur": 3.961, + "args": { + "External id": 4053951,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 5632]", "15", "", "", "", "0"], "Input type": ["ScalarList", "Scalar", "", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 958 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655274543405.426, "dur": 1.624, + "args": { + "External id": 4053952,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 5632]", "15", "", "", "", "0"], "Input type": ["ScalarList", "Scalar", "", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 959 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655274543407.927, "dur": 1.613, + "args": { + "External id": 4053953,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 5632]", "15", "", "", "", "0"], "Input type": ["ScalarList", "Scalar", "", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 960 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1381189, + "ts": 1655274543460.592, "dur": 2.566, + "args": { + "External id": 4053954,"Record function id": 0, "Concrete Inputs": ["", "[-1, 5632]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[23068672, 5632, 1], []], "Input Dims": [[16, 4096, 5632], []], "Ev Idx": 961 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274543461.164, "dur": 1.716, + "args": { + "External id": 4053955,"Record function id": 0, "Concrete Inputs": ["", "[-1, 5632]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[23068672, 5632, 1], []], "Input Dims": [[16, 4096, 5632], []], "Ev Idx": 962 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::einsum", "pid": 1336756, "tid": 1381189, + "ts": 1655274543485.890, "dur": 145.836, + "args": { + "External id": 4053956,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["", "TensorList", ""], "Input Strides": [[], [[8192, 1], [5632, 1]], []], "Input Dims": [[], [[65536, 2048], [65536, 5632]], []], "Ev Idx": 963 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1381189, + "ts": 1655274543491.074, "dur": 7.484, + "args": { + "External id": 4053957,"Record function id": 0, "Concrete Inputs": ["", "2"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[8192, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 964 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274543496.688, "dur": 1.017, + "args": { + "External id": 4053958,"Record function id": 0, "Concrete Inputs": ["", "[65536, 2048, 1]", "[8192, 1, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[8192, 1], [], [], []], "Input Dims": [[65536, 2048], [], [], []], "Ev Idx": 965 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::permute", "pid": 1336756, "tid": 1381189, + "ts": 1655274543499.783, "dur": 8.930, + "args": { + "External id": 4053959,"Record function id": 0, "Concrete Inputs": ["", "[1, 2, 0]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8192, 1, 1], []], "Input Dims": [[65536, 2048, 1], []], "Ev Idx": 966 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274543505.970, "dur": 2.109, + "args": { + "External id": 4053960,"Record function id": 0, "Concrete Inputs": ["", "[2048, 1, 65536]", "[1, 1, 8192]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[8192, 1, 1], [], [], []], "Input Dims": [[65536, 2048, 1], [], [], []], "Ev Idx": 967 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1381189, + "ts": 1655274543510.006, "dur": 1.907, + "args": { + "External id": 4053961,"Record function id": 0, "Concrete Inputs": ["", "2"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[5632, 1], []], "Input Dims": [[65536, 5632], []], "Ev Idx": 968 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274543511.232, "dur": 0.365, + "args": { + "External id": 4053962,"Record function id": 0, "Concrete Inputs": ["", "[65536, 5632, 1]", "[5632, 1, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[5632, 1], [], [], []], "Input Dims": [[65536, 5632], [], [], []], "Ev Idx": 969 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::permute", "pid": 1336756, "tid": 1381189, + "ts": 1655274543514.258, "dur": 1.758, + "args": { + "External id": 4053963,"Record function id": 0, "Concrete Inputs": ["", "[2, 1, 0]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[5632, 1, 1], []], "Input Dims": [[65536, 5632, 1], []], "Ev Idx": 970 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274543515.013, "dur": 0.653, + "args": { + "External id": 4053964,"Record function id": 0, "Concrete Inputs": ["", "[1, 5632, 65536]", "[1, 1, 5632]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[5632, 1, 1], [], [], []], "Input Dims": [[65536, 5632, 1], [], [], []], "Ev Idx": 971 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::permute", "pid": 1336756, "tid": 1381189, + "ts": 1655274543521.734, "dur": 1.798, + "args": { + "External id": 4053965,"Record function id": 0, "Concrete Inputs": ["", "[0, 2, 1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1, 1, 8192], []], "Input Dims": [[2048, 1, 65536], []], "Ev Idx": 972 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274543522.729, "dur": 0.520, + "args": { + "External id": 4053966,"Record function id": 0, "Concrete Inputs": ["", "[2048, 65536, 1]", "[1, 8192, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1, 8192], [], [], []], "Input Dims": [[2048, 1, 65536], [], [], []], "Ev Idx": 973 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1381189, + "ts": 1655274543524.316, "dur": 6.972, + "args": { + "External id": 4053967,"Record function id": 0, "Concrete Inputs": ["", "[1, 2048, 65536]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1, 8192, 1], []], "Input Dims": [[2048, 65536, 1], []], "Ev Idx": 974 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_reshape_alias", "pid": 1336756, "tid": 1381189, + "ts": 1655274543529.296, "dur": 1.811, + "args": { + "External id": 4053968,"Record function id": 0, "Concrete Inputs": ["", "[1, 2048, 65536]", "[2048, 1, 8192]"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList"], "Input Strides": [[1, 8192, 1], [], []], "Input Dims": [[2048, 65536, 1], [], []], "Ev Idx": 975 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::permute", "pid": 1336756, "tid": 1381189, + "ts": 1655274543532.037, "dur": 3.702, + "args": { + "External id": 4053969,"Record function id": 0, "Concrete Inputs": ["", "[2, 1, 0]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1, 1, 5632], []], "Input Dims": [[1, 5632, 65536], []], "Ev Idx": 976 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274543535.013, "dur": 0.466, + "args": { + "External id": 4053970,"Record function id": 0, "Concrete Inputs": ["", "[65536, 5632, 1]", "[5632, 1, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1, 5632], [], [], []], "Input Dims": [[1, 5632, 65536], [], [], []], "Ev Idx": 977 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1381189, + "ts": 1655274543538.125, "dur": 3.167, + "args": { + "External id": 4053971,"Record function id": 0, "Concrete Inputs": ["", "[1, 65536, 5632]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[5632, 1, 1], []], "Input Dims": [[65536, 5632, 1], []], "Ev Idx": 978 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274543538.931, "dur": 2.276, + "args": { + "External id": 4053972,"Record function id": 0, "Concrete Inputs": ["", "[1, 65536, 5632]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[5632, 1, 1], []], "Input Dims": [[65536, 5632, 1], []], "Ev Idx": 979 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 1336756, "tid": 1381189, + "ts": 1655274543542.605, "dur": 73.412, + "args": { + "External id": 4053973,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1, 8192], [369098752, 5632, 1]], "Input Dims": [[1, 2048, 65536], [1, 65536, 5632]], "Ev Idx": 980 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274543619.563, "dur": 3.007, + "args": { + "External id": 4053974,"Record function id": 0, "Concrete Inputs": ["", "[2048, 1, 5632]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[11534336, 5632, 1], []], "Input Dims": [[1, 2048, 5632], []], "Ev Idx": 981 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::permute", "pid": 1336756, "tid": 1381189, + "ts": 1655274543623.328, "dur": 4.283, + "args": { + "External id": 4053975,"Record function id": 0, "Concrete Inputs": ["", "[0, 2, 1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[5632, 5632, 1], []], "Input Dims": [[2048, 1, 5632], []], "Ev Idx": 982 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274543626.747, "dur": 0.449, + "args": { + "External id": 4053976,"Record function id": 0, "Concrete Inputs": ["", "[2048, 5632, 1]", "[5632, 1, 5632]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[5632, 5632, 1], [], [], []], "Input Dims": [[2048, 1, 5632], [], [], []], "Ev Idx": 983 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274543629.783, "dur": 0.817, + "args": { + "External id": 4053977,"Record function id": 0, "Concrete Inputs": ["", "[2048, 5632]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[5632, 1, 5632], []], "Input Dims": [[2048, 5632, 1], []], "Ev Idx": 984 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274543672.127, "dur": 8.524, + "args": { + "External id": 4053978,"Record function id": 0, "Ev Idx": 985 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274543674.180, "dur": 5.855, + "args": { + "External id": 4053979,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 986 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274543676.137, "dur": 2.907, + "args": { + "External id": 4053980,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 987 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274543676.987, "dur": 1.948, + "args": { + "External id": 4053981,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 988 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: UnsafeViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274543684.347, "dur": 8.492, + "args": { + "External id": 4053982,"Record function id": 0, "Sequence number": 40618476, "Fwd thread id": 1, "Ev Idx": 989 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274543685.078, "dur": 5.719, + "args": { + "External id": 4053983,"Sequence number": 40618476, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[23068672, 5632, 1]], "Input Dims": [[16, 4096, 5632]], "Ev Idx": 990 + } + }, + { + "ph": "f", "id": 104, "pid": 1336756, "tid": 1381189, "ts": 1655274543685.078, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1381189, + "ts": 1655274543688.910, "dur": 1.688, + "args": { + "External id": 4053984,"Record function id": 0, "Concrete Inputs": ["", "[65536, 5632]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[23068672, 5632, 1], []], "Input Dims": [[16, 4096, 5632], []], "Ev Idx": 991 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274543689.702, "dur": 0.754, + "args": { + "External id": 4053985,"Record function id": 0, "Concrete Inputs": ["", "[65536, 5632]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[23068672, 5632, 1], []], "Input Dims": [[16, 4096, 5632], []], "Ev Idx": 992 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: MmBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274543696.349, "dur": 177.649, + "args": { + "External id": 4053986,"Record function id": 0, "Sequence number": 40618475, "Fwd thread id": 1, "Ev Idx": 993 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274543697.114, "dur": 170.480, + "args": { + "External id": 4053987,"Sequence number": 40618475, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[65536, 5632]], "Ev Idx": 994 + } + }, + { + "ph": "f", "id": 105, "pid": 1336756, "tid": 1381189, "ts": 1655274543697.114, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1381189, + "ts": 1655274543700.495, "dur": 5.776, + "args": { + "External id": 4053988,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[65536, 5632]], "Ev Idx": 995 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1381189, + "ts": 1655274543701.891, "dur": 3.940, + "args": { + "External id": 4053989,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[5632, 1], [], []], "Input Dims": [[65536, 5632], [], []], "Ev Idx": 996 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274543704.942, "dur": 0.747, + "args": { + "External id": 4053990,"Record function id": 0, "Concrete Inputs": ["", "[5632, 65536]", "[1, 5632]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[5632, 1], [], [], []], "Input Dims": [[65536, 5632], [], [], []], "Ev Idx": 997 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655274543707.319, "dur": 55.157, + "args": { + "External id": 4053991,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 5632], [2048, 1]], "Input Dims": [[5632, 65536], [65536, 2048]], "Ev Idx": 998 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1381189, + "ts": 1655274543763.649, "dur": 6.066, + "args": { + "External id": 4053992,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 999 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1381189, + "ts": 1655274543764.400, "dur": 4.529, + "args": { + "External id": 4053993,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[5632, 2048], [], []], "Ev Idx": 1000 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274543767.690, "dur": 1.092, + "args": { + "External id": 4053994,"Record function id": 0, "Concrete Inputs": ["", "[2048, 5632]", "[1, 2048]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[5632, 2048], [], [], []], "Ev Idx": 1001 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1381189, + "ts": 1655274543771.183, "dur": 4.365, + "args": { + "External id": 4053995,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 2048]], "Input Dims": [[2048, 5632]], "Ev Idx": 1002 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1381189, + "ts": 1655274543772.069, "dur": 3.034, + "args": { + "External id": 4053996,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 2048], [], []], "Input Dims": [[2048, 5632], [], []], "Ev Idx": 1003 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274543774.615, "dur": 0.405, + "args": { + "External id": 4053997,"Record function id": 0, "Concrete Inputs": ["", "[5632, 2048]", "[2048, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 2048], [], [], []], "Input Dims": [[2048, 5632], [], [], []], "Ev Idx": 1004 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655274543775.963, "dur": 90.971, + "args": { + "External id": 4053998,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [2048, 1]], "Input Dims": [[65536, 5632], [5632, 2048]], "Ev Idx": 1005 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274543878.721, "dur": 8.138, + "args": { + "External id": 4053999,"Record function id": 0, "Sequence number": 40618474, "Fwd thread id": 1, "Ev Idx": 1006 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274543879.770, "dur": 5.533, + "args": { + "External id": 4054000,"Sequence number": 40618474, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[65536, 2048]], "Ev Idx": 1007 + } + }, + { + "ph": "f", "id": 106, "pid": 1336756, "tid": 1381189, "ts": 1655274543879.770, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1381189, + "ts": 1655274543880.896, "dur": 4.257, + "args": { + "External id": 4054001,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 1008 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274543883.929, "dur": 1.094, + "args": { + "External id": 4054002,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 1009 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: TBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274543890.035, "dur": 8.798, + "args": { + "External id": 4054003,"Record function id": 0, "Sequence number": 40618473, "Fwd thread id": 1, "Ev Idx": 1010 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274543890.998, "dur": 5.933, + "args": { + "External id": 4054004,"Sequence number": 40618473, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 2048]], "Input Dims": [[2048, 5632]], "Ev Idx": 1011 + } + }, + { + "ph": "f", "id": 107, "pid": 1336756, "tid": 1381189, "ts": 1655274543890.998, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1381189, + "ts": 1655274543891.856, "dur": 4.867, + "args": { + "External id": 4054005,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 2048]], "Input Dims": [[2048, 5632]], "Ev Idx": 1012 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1381189, + "ts": 1655274543892.627, "dur": 3.615, + "args": { + "External id": 4054006,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 2048], [], []], "Input Dims": [[2048, 5632], [], []], "Ev Idx": 1013 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274543895.605, "dur": 0.484, + "args": { + "External id": 4054007,"Record function id": 0, "Concrete Inputs": ["", "[5632, 2048]", "[2048, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 2048], [], [], []], "Input Dims": [[2048, 5632], [], [], []], "Ev Idx": 1014 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274543902.481, "dur": 4.808, + "args": { + "External id": 4054008,"Record function id": 0, "Ev Idx": 1015 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274543903.534, "dur": 3.251, + "args": { + "External id": 4054009,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 1016 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274543904.495, "dur": 2.082, + "args": { + "External id": 4054010,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 1017 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274543904.997, "dur": 1.504, + "args": { + "External id": 4054011,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 1018 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: UnsafeViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274543912.447, "dur": 7.634, + "args": { + "External id": 4054012,"Record function id": 0, "Sequence number": 40618472, "Fwd thread id": 1, "Ev Idx": 1019 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274543913.201, "dur": 4.934, + "args": { + "External id": 4054013,"Sequence number": 40618472, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[23068672, 5632, 1]], "Input Dims": [[16, 4096, 5632]], "Ev Idx": 1020 + } + }, + { + "ph": "f", "id": 108, "pid": 1336756, "tid": 1381189, "ts": 1655274543913.201, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1381189, + "ts": 1655274543914.198, "dur": 3.800, + "args": { + "External id": 4054014,"Record function id": 0, "Concrete Inputs": ["", "[65536, 5632]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[23068672, 5632, 1], []], "Input Dims": [[16, 4096, 5632], []], "Ev Idx": 1021 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274543917.150, "dur": 0.720, + "args": { + "External id": 4054015,"Record function id": 0, "Concrete Inputs": ["", "[65536, 5632]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[23068672, 5632, 1], []], "Input Dims": [[16, 4096, 5632], []], "Ev Idx": 1022 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: MmBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274543923.039, "dur": 219.229, + "args": { + "External id": 4054016,"Record function id": 0, "Sequence number": 40618471, "Fwd thread id": 1, "Ev Idx": 1023 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274543945.168, "dur": 188.783, + "args": { + "External id": 4054017,"Sequence number": 40618471, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[65536, 5632]], "Ev Idx": 1024 + } + }, + { + "ph": "f", "id": 109, "pid": 1336756, "tid": 1381189, "ts": 1655274543945.168, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1381189, + "ts": 1655274543949.046, "dur": 2.218, + "args": { + "External id": 4054018,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[65536, 5632]], "Ev Idx": 1025 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1381189, + "ts": 1655274543949.511, "dur": 1.301, + "args": { + "External id": 4054019,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[5632, 1], [], []], "Input Dims": [[65536, 5632], [], []], "Ev Idx": 1026 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274543950.271, "dur": 0.427, + "args": { + "External id": 4054020,"Record function id": 0, "Concrete Inputs": ["", "[5632, 65536]", "[1, 5632]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[5632, 1], [], [], []], "Input Dims": [[65536, 5632], [], [], []], "Ev Idx": 1027 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655274543951.926, "dur": 72.618, + "args": { + "External id": 4054021,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 5632], [2048, 1]], "Input Dims": [[5632, 65536], [65536, 2048]], "Ev Idx": 1028 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1381189, + "ts": 1655274544026.962, "dur": 7.790, + "args": { + "External id": 4054022,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 1029 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1381189, + "ts": 1655274544027.682, "dur": 6.122, + "args": { + "External id": 4054023,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[5632, 2048], [], []], "Ev Idx": 1030 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274544031.120, "dur": 2.528, + "args": { + "External id": 4054024,"Record function id": 0, "Concrete Inputs": ["", "[2048, 5632]", "[1, 2048]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[5632, 2048], [], [], []], "Ev Idx": 1031 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1381189, + "ts": 1655274544035.787, "dur": 6.140, + "args": { + "External id": 4054025,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 2048]], "Input Dims": [[2048, 5632]], "Ev Idx": 1032 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1381189, + "ts": 1655274544036.706, "dur": 4.771, + "args": { + "External id": 4054026,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 2048], [], []], "Input Dims": [[2048, 5632], [], []], "Ev Idx": 1033 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274544039.430, "dur": 1.980, + "args": { + "External id": 4054027,"Record function id": 0, "Concrete Inputs": ["", "[5632, 2048]", "[2048, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 2048], [], [], []], "Input Dims": [[2048, 5632], [], [], []], "Ev Idx": 1034 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655274544042.462, "dur": 90.688, + "args": { + "External id": 4054028,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [2048, 1]], "Input Dims": [[65536, 5632], [5632, 2048]], "Ev Idx": 1035 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274544148.648, "dur": 32.563, + "args": { + "External id": 4054029,"Record function id": 0, "Sequence number": 40618470, "Fwd thread id": 1, "Ev Idx": 1036 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274544149.702, "dur": 5.127, + "args": { + "External id": 4054030,"Sequence number": 40618470, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[65536, 2048]], "Ev Idx": 1037 + } + }, + { + "ph": "f", "id": 110, "pid": 1336756, "tid": 1381189, "ts": 1655274544149.702, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1381189, + "ts": 1655274544152.890, "dur": 1.789, + "args": { + "External id": 4054031,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 1038 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274544153.389, "dur": 1.174, + "args": { + "External id": 4054032,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 1039 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add", "pid": 1336756, "tid": 1381189, + "ts": 1655274544157.580, "dur": 20.336, + "args": { + "External id": 4054033,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[8388608, 2048, 1], [8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], [16, 4096, 2048], []], "Ev Idx": 1040 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: TBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274544185.083, "dur": 7.470, + "args": { + "External id": 4054034,"Record function id": 0, "Sequence number": 40618469, "Fwd thread id": 1, "Ev Idx": 1041 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274544185.919, "dur": 4.963, + "args": { + "External id": 4054035,"Sequence number": 40618469, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 2048]], "Input Dims": [[2048, 5632]], "Ev Idx": 1042 + } + }, + { + "ph": "f", "id": 111, "pid": 1336756, "tid": 1381189, "ts": 1655274544185.919, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1381189, + "ts": 1655274544186.495, "dur": 4.204, + "args": { + "External id": 4054036,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 2048]], "Input Dims": [[2048, 5632]], "Ev Idx": 1043 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1381189, + "ts": 1655274544187.034, "dur": 3.180, + "args": { + "External id": 4054037,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 2048], [], []], "Input Dims": [[2048, 5632], [], []], "Ev Idx": 1044 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274544189.710, "dur": 0.385, + "args": { + "External id": 4054038,"Record function id": 0, "Concrete Inputs": ["", "[5632, 2048]", "[2048, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 2048], [], [], []], "Input Dims": [[2048, 5632], [], [], []], "Ev Idx": 1045 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274544196.612, "dur": 7.609, + "args": { + "External id": 4054039,"Record function id": 0, "Ev Idx": 1046 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274544197.767, "dur": 5.939, + "args": { + "External id": 4054040,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 1047 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274544199.074, "dur": 4.226, + "args": { + "External id": 4054041,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 1048 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274544201.970, "dur": 1.201, + "args": { + "External id": 4054042,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 1049 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: LayerNormFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1655274544207.953, "dur": 436.933, + "args": { + "External id": 4054043,"Record function id": 0, "Sequence number": 40618468, "Fwd thread id": 1, "Ev Idx": 1050 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1655274544209.145, "dur": 404.762, + "args": { + "External id": 4054044,"Sequence number": 40618468, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[8388608, 2048, 1], [33554432, 8192, 1]], "Input Dims": [[16, 4096, 2048], [16, 4096, 2048]], "Ev Idx": 1051 + } + }, + { + "ph": "f", "id": 112, "pid": 1336756, "tid": 1381189, "ts": 1655274544209.145, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::contiguous", "pid": 1336756, "tid": 1381189, + "ts": 1655274544233.339, "dur": 34.732, + "args": { + "External id": 4054045,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[33554432, 8192, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 1052 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 1336756, "tid": 1381189, + "ts": 1655274544234.587, "dur": 33.284, + "args": { + "External id": 4054046,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[33554432, 8192, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 1053 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336756, "tid": 1381189, + "ts": 1655274544237.090, "dur": 5.450, + "args": { + "External id": 4054047,"Record function id": 0, "Concrete Inputs": ["", "15", "0", "", "", "0"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[33554432, 8192, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 2048], [], [], [], [], []], "Ev Idx": 1054 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655274544239.416, "dur": 2.527, + "args": { + "External id": 4054048,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 2048]", "15", "0", "", "", "0"], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1055 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1381189, + "ts": 1655274544243.835, "dur": 23.661, + "args": { + "External id": 4054049,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[8388608, 2048, 1], [33554432, 8192, 1], []], "Input Dims": [[16, 4096, 2048], [16, 4096, 2048], []], "Ev Idx": 1056 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1381189, + "ts": 1655274544280.668, "dur": 1.994, + "args": { + "External id": 4054050,"Record function id": 0, "Concrete Inputs": ["", "[-1, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 1057 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274544281.355, "dur": 1.172, + "args": { + "External id": 4054051,"Record function id": 0, "Concrete Inputs": ["", "[-1, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 1058 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1381189, + "ts": 1655274544286.390, "dur": 5.706, + "args": { + "External id": 4054052,"Record function id": 0, "Concrete Inputs": ["", "[-1, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 1059 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274544289.486, "dur": 2.529, + "args": { + "External id": 4054053,"Record function id": 0, "Concrete Inputs": ["", "[-1, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 1060 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655274544303.501, "dur": 2.350, + "args": { + "External id": 4054054,"Record function id": 0, "Concrete Inputs": ["[65536, 2048]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1061 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655274544316.633, "dur": 1.939, + "args": { + "External id": 4054055,"Record function id": 0, "Concrete Inputs": ["[132, 2048]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1062 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274544500.747, "dur": 3.738, + "args": { + "External id": 4054056,"Record function id": 0, "Concrete Inputs": ["", "[1, -1, 2048]"], "Input type": ["float", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[132, 2048], []], "Ev Idx": 1063 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 1336756, "tid": 1381189, + "ts": 1655274544511.154, "dur": 32.799, + "args": { + "External id": 4054057,"Record function id": 0, "Concrete Inputs": ["", "[1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", ""], "Input Strides": [[270336, 2048, 1], [], [], []], "Input Dims": [[1, 132, 2048], [], [], []], "Ev Idx": 1064 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274544521.185, "dur": 1.193, + "args": { + "External id": 4054058,"Record function id": 0, "Concrete Inputs": ["", "[1, 1, 2048]", "[2048, 0, 1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[1, 2048], [], [], []], "Ev Idx": 1065 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1381189, + "ts": 1655274544549.353, "dur": 31.621, + "args": { + "External id": 4054059,"Record function id": 0, "Concrete Inputs": ["", "", "15", "False", "False", ""], "Input type": ["float", "", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[2048, 1], [], [], [], [], []], "Input Dims": [[1, 2048], [], [], [], [], []], "Ev Idx": 1066 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336756, "tid": 1381189, + "ts": 1655274544553.422, "dur": 27.356, + "args": { + "External id": 4054060,"Record function id": 0, "Concrete Inputs": ["", "15", "", "", "", "False", ""], "Input type": ["float", "Scalar", "", "", "", "Scalar", ""], "Input Strides": [[2048, 1], [], [], [], [], [], []], "Input Dims": [[1, 2048], [], [], [], [], [], []], "Ev Idx": 1067 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274544559.200, "dur": 4.310, + "args": { + "External id": 4054061,"Record function id": 0, "Concrete Inputs": ["[1, 2048]", "[2048, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1068 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1381189, + "ts": 1655274544565.027, "dur": 15.260, + "args": { + "External id": 4054062,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "float", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[1, 2048], [1, 2048], []], "Ev Idx": 1069 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 1336756, "tid": 1381189, + "ts": 1655274544585.346, "dur": 2.340, + "args": { + "External id": 4054063,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1]], "Input Dims": [[1, 2048], [2048]], "Ev Idx": 1070 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274544586.471, "dur": 1.066, + "args": { + "External id": 4054064,"Record function id": 0, "Concrete Inputs": ["", "[2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[1, 2048], []], "Ev Idx": 1071 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1381189, + "ts": 1655274544593.539, "dur": 3.973, + "args": { + "External id": 4054065,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 1072 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274544596.099, "dur": 1.301, + "args": { + "External id": 4054066,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 1073 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1381189, + "ts": 1655274544599.308, "dur": 5.597, + "args": { + "External id": 4054067,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 1074 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274544602.094, "dur": 2.715, + "args": { + "External id": 4054068,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 1075 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336756, "tid": 1381189, + "ts": 1655274544628.397, "dur": 15.026, + "args": { + "External id": 4054069,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[8388608, 2048, 1], [8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], [16, 4096, 2048], []], "Ev Idx": 1076 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274544656.593, "dur": 7.589, + "args": { + "External id": 4054070,"Record function id": 0, "Ev Idx": 1077 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274544658.582, "dur": 4.940, + "args": { + "External id": 4054071,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 1078 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274544660.295, "dur": 2.404, + "args": { + "External id": 4054072,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 1079 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274544661.195, "dur": 1.433, + "args": { + "External id": 4054073,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 1080 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: UnsafeViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274544667.797, "dur": 8.191, + "args": { + "External id": 4054074,"Record function id": 0, "Sequence number": 40618467, "Fwd thread id": 1, "Ev Idx": 1081 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274544668.717, "dur": 5.124, + "args": { + "External id": 4054075,"Sequence number": 40618467, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 1082 + } + }, + { + "ph": "f", "id": 113, "pid": 1336756, "tid": 1381189, "ts": 1655274544668.717, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1381189, + "ts": 1655274544671.960, "dur": 1.700, + "args": { + "External id": 4054076,"Record function id": 0, "Concrete Inputs": ["", "[65536, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 1083 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274544672.488, "dur": 1.050, + "args": { + "External id": 4054077,"Record function id": 0, "Concrete Inputs": ["", "[65536, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 1084 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: MmBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274544679.911, "dur": 122.788, + "args": { + "External id": 4054078,"Record function id": 0, "Sequence number": 40618466, "Fwd thread id": 1, "Ev Idx": 1085 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274544680.631, "dur": 116.093, + "args": { + "External id": 4054079,"Sequence number": 40618466, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[65536, 2048]], "Ev Idx": 1086 + } + }, + { + "ph": "f", "id": 114, "pid": 1336756, "tid": 1381189, "ts": 1655274544680.631, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1381189, + "ts": 1655274544683.350, "dur": 6.285, + "args": { + "External id": 4054080,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[65536, 2048]], "Ev Idx": 1087 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1381189, + "ts": 1655274544684.719, "dur": 4.387, + "args": { + "External id": 4054081,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[65536, 2048], [], []], "Ev Idx": 1088 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274544688.124, "dur": 0.831, + "args": { + "External id": 4054082,"Record function id": 0, "Concrete Inputs": ["", "[2048, 65536]", "[1, 2048]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[65536, 2048], [], [], []], "Ev Idx": 1089 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655274544691.110, "dur": 52.073, + "args": { + "External id": 4054083,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048]], "Ev Idx": 1090 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1381189, + "ts": 1655274544744.538, "dur": 6.501, + "args": { + "External id": 4054084,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 1091 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1381189, + "ts": 1655274544745.225, "dur": 5.287, + "args": { + "External id": 4054085,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[2048, 2048], [], []], "Ev Idx": 1092 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274544748.507, "dur": 1.845, + "args": { + "External id": 4054086,"Record function id": 0, "Concrete Inputs": ["", "[2048, 2048]", "[1, 2048]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[2048, 2048], [], [], []], "Ev Idx": 1093 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1381189, + "ts": 1655274544752.415, "dur": 4.726, + "args": { + "External id": 4054087,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 2048]], "Input Dims": [[2048, 2048]], "Ev Idx": 1094 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1381189, + "ts": 1655274544753.255, "dur": 3.489, + "args": { + "External id": 4054088,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 2048], [], []], "Input Dims": [[2048, 2048], [], []], "Ev Idx": 1095 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274544756.131, "dur": 0.537, + "args": { + "External id": 4054089,"Record function id": 0, "Concrete Inputs": ["", "[2048, 2048]", "[2048, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 2048], [], [], []], "Input Dims": [[2048, 2048], [], [], []], "Ev Idx": 1096 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655274544757.654, "dur": 38.313, + "args": { + "External id": 4054090,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048]], "Ev Idx": 1097 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274544807.494, "dur": 10.537, + "args": { + "External id": 4054091,"Record function id": 0, "Sequence number": 40618465, "Fwd thread id": 1, "Ev Idx": 1098 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274544808.687, "dur": 7.507, + "args": { + "External id": 4054092,"Sequence number": 40618465, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[65536, 2048]], "Ev Idx": 1099 + } + }, + { + "ph": "f", "id": 115, "pid": 1336756, "tid": 1381189, "ts": 1655274544808.687, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1381189, + "ts": 1655274544809.869, "dur": 6.154, + "args": { + "External id": 4054093,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 1100 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274544812.781, "dur": 3.131, + "args": { + "External id": 4054094,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 1101 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: TBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274544823.374, "dur": 8.423, + "args": { + "External id": 4054095,"Record function id": 0, "Sequence number": 40618464, "Fwd thread id": 1, "Ev Idx": 1102 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274544824.039, "dur": 5.986, + "args": { + "External id": 4054096,"Sequence number": 40618464, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 2048]], "Input Dims": [[2048, 2048]], "Ev Idx": 1103 + } + }, + { + "ph": "f", "id": 116, "pid": 1336756, "tid": 1381189, "ts": 1655274544824.039, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1381189, + "ts": 1655274544824.874, "dur": 4.981, + "args": { + "External id": 4054097,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 2048]], "Input Dims": [[2048, 2048]], "Ev Idx": 1104 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1381189, + "ts": 1655274544825.649, "dur": 3.728, + "args": { + "External id": 4054098,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 2048], [], []], "Input Dims": [[2048, 2048], [], []], "Ev Idx": 1105 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274544828.739, "dur": 0.494, + "args": { + "External id": 4054099,"Record function id": 0, "Concrete Inputs": ["", "[2048, 2048]", "[2048, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 2048], [], [], []], "Input Dims": [[2048, 2048], [], [], []], "Ev Idx": 1106 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274544835.461, "dur": 4.497, + "args": { + "External id": 4054100,"Record function id": 0, "Ev Idx": 1107 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274544836.604, "dur": 2.901, + "args": { + "External id": 4054101,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 1108 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274544837.455, "dur": 1.814, + "args": { + "External id": 4054102,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 1109 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274544838.022, "dur": 1.136, + "args": { + "External id": 4054103,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 1110 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274544845.147, "dur": 4.891, + "args": { + "External id": 4054104,"Record function id": 0, "Sequence number": 40618463, "Fwd thread id": 1, "Ev Idx": 1111 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274544845.869, "dur": 2.797, + "args": { + "External id": 4054105,"Sequence number": 40618463, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 1112 + } + }, + { + "ph": "f", "id": 117, "pid": 1336756, "tid": 1381189, "ts": 1655274544845.869, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1381189, + "ts": 1655274544846.872, "dur": 1.650, + "args": { + "External id": 4054106,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 32, 64]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 1113 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274544847.219, "dur": 1.173, + "args": { + "External id": 4054107,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 32, 64]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 1114 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: FlashAttnFuncBackward", "pid": 1336756, "tid": 1381189, + "ts": 1655274544856.269, "dur": 330.268, + "args": { + "External id": 4054108,"Record function id": 0, "Sequence number": 40618462, "Fwd thread id": 1, "Ev Idx": 1115 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "FlashAttnFuncBackward", "pid": 1336756, "tid": 1381189, + "ts": 1655274544857.338, "dur": 311.397, + "args": { + "External id": 4054109,"Sequence number": 40618462, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 64, 1]], "Input Dims": [[16, 4096, 32, 64]], "Ev Idx": 1116 + } + }, + { + "ph": "f", "id": 118, "pid": 1336756, "tid": 1381189, "ts": 1655274544857.338, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336756, "tid": 1381189, + "ts": 1655274544871.576, "dur": 5.658, + "args": { + "External id": 4054110,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[8388608, 2048, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [], [], [], [], []], "Ev Idx": 1117 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274544873.549, "dur": 3.170, + "args": { + "External id": 4054111,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "[8388608, 2048, 64, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1118 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336756, "tid": 1381189, + "ts": 1655274544879.109, "dur": 5.867, + "args": { + "External id": 4054112,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[8388608, 2048, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [], [], [], [], []], "Ev Idx": 1119 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274544881.853, "dur": 2.909, + "args": { + "External id": 4054113,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "[8388608, 2048, 64, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1120 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336756, "tid": 1381189, + "ts": 1655274544893.300, "dur": 4.511, + "args": { + "External id": 4054114,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[8388608, 2048, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [], [], [], [], []], "Ev Idx": 1121 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274544896.046, "dur": 1.554, + "args": { + "External id": 4054115,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "[8388608, 2048, 64, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1122 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 1336756, "tid": 1381189, + "ts": 1655274544925.802, "dur": 217.299, + "args": { + "External id": 4054116,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.125", "True", "-1", "-1", "0.", "", "False", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar", "long int"], "Input Strides": [[8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [131072, 4096, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 32, 4096], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 1123 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655274545043.586, "dur": 5.588, + "args": { + "External id": 4054117,"Record function id": 0, "Concrete Inputs": ["[16, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1124 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655274545050.881, "dur": 4.667, + "args": { + "External id": 4054118,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1125 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::alias", "pid": 1336756, "tid": 1381189, + "ts": 1655274545155.942, "dur": 3.974, + "args": { + "External id": 4054119,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 64, 1]], "Input Dims": [[16, 4096, 32, 64]], "Ev Idx": 1126 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::alias", "pid": 1336756, "tid": 1381189, + "ts": 1655274545162.962, "dur": 0.676, + "args": { + "External id": 4054120,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 64, 1]], "Input Dims": [[16, 4096, 32, 64]], "Ev Idx": 1127 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::alias", "pid": 1336756, "tid": 1381189, + "ts": 1655274545165.545, "dur": 0.837, + "args": { + "External id": 4054121,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 64, 1]], "Input Dims": [[16, 4096, 32, 64]], "Ev Idx": 1128 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RotaryEmbeddingFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1655274545196.501, "dur": 244.874, + "args": { + "External id": 4054122,"Record function id": 0, "Sequence number": 40618461, "Fwd thread id": 1, "Ev Idx": 1129 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1655274545198.125, "dur": 234.156, + "args": { + "External id": 4054123,"Sequence number": 40618461, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 64, 1]], "Input Dims": [[16, 4096, 32, 64]], "Ev Idx": 1130 + } + }, + { + "ph": "f", "id": 119, "pid": 1336756, "tid": 1381189, "ts": 1655274545198.125, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 1336756, "tid": 1381189, + "ts": 1655274545217.696, "dur": 43.346, + "args": { + "External id": 4054124,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", ""], "Input Strides": [[8388608, 2048, 64, 1], []], "Input Dims": [[16, 4096, 32, 64], []], "Ev Idx": 1131 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274545220.386, "dur": 2.982, + "args": { + "External id": 4054125,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "[8388608, 2048, 64, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1132 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1381189, + "ts": 1655274545224.715, "dur": 35.662, + "args": { + "External id": 4054126,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [8388608, 2048, 64, 1], []], "Input Dims": [[16, 4096, 32, 64], [16, 4096, 32, 64], []], "Ev Idx": 1133 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336756, "tid": 1381189, + "ts": 1655274545270.627, "dur": 6.755, + "args": { + "External id": 4054127,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[8388608, 2048, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [], [], [], [], []], "Ev Idx": 1134 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274545274.599, "dur": 2.463, + "args": { + "External id": 4054128,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "[8388608, 2048, 64, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1135 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RotaryEmbeddingFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1655274545450.154, "dur": 166.969, + "args": { + "External id": 4054129,"Record function id": 0, "Sequence number": 40618460, "Fwd thread id": 1, "Ev Idx": 1136 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1655274545451.800, "dur": 159.646, + "args": { + "External id": 4054130,"Sequence number": 40618460, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 64, 1]], "Input Dims": [[16, 4096, 32, 64]], "Ev Idx": 1137 + } + }, + { + "ph": "f", "id": 120, "pid": 1336756, "tid": 1381189, "ts": 1655274545451.800, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 1336756, "tid": 1381189, + "ts": 1655274545465.372, "dur": 44.209, + "args": { + "External id": 4054131,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", ""], "Input Strides": [[8388608, 2048, 64, 1], []], "Input Dims": [[16, 4096, 32, 64], []], "Ev Idx": 1138 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274545467.587, "dur": 3.336, + "args": { + "External id": 4054132,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "[8388608, 2048, 64, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1139 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1381189, + "ts": 1655274545476.318, "dur": 32.738, + "args": { + "External id": 4054133,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [8388608, 2048, 64, 1], []], "Input Dims": [[16, 4096, 32, 64], [16, 4096, 32, 64], []], "Ev Idx": 1140 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336756, "tid": 1381189, + "ts": 1655274545517.050, "dur": 5.724, + "args": { + "External id": 4054134,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[8388608, 2048, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [], [], [], [], []], "Ev Idx": 1141 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274545520.293, "dur": 2.176, + "args": { + "External id": 4054135,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "[8388608, 2048, 64, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1142 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274545623.405, "dur": 15.402, + "args": { + "External id": 4054136,"Record function id": 0, "Sequence number": 40618459, "Fwd thread id": 1, "Ev Idx": 1143 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274545624.806, "dur": 11.813, + "args": { + "External id": 4054137,"Sequence number": 40618459, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 64, 1]], "Input Dims": [[16, 4096, 32, 64]], "Ev Idx": 1144 + } + }, + { + "ph": "f", "id": 121, "pid": 1336756, "tid": 1381189, "ts": 1655274545624.806, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1381189, + "ts": 1655274545626.998, "dur": 9.362, + "args": { + "External id": 4054138,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 64, 1], []], "Input Dims": [[16, 4096, 32, 64], []], "Ev Idx": 1145 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274545630.213, "dur": 5.904, + "args": { + "External id": 4054139,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 64, 1], []], "Input Dims": [[16, 4096, 32, 64], []], "Ev Idx": 1146 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274545642.407, "dur": 7.480, + "args": { + "External id": 4054140,"Record function id": 0, "Sequence number": 40618458, "Fwd thread id": 1, "Ev Idx": 1147 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274545643.333, "dur": 4.556, + "args": { + "External id": 4054141,"Sequence number": 40618458, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 64, 1]], "Input Dims": [[16, 4096, 32, 64]], "Ev Idx": 1148 + } + }, + { + "ph": "f", "id": 122, "pid": 1336756, "tid": 1381189, "ts": 1655274545643.333, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1381189, + "ts": 1655274545644.215, "dur": 3.518, + "args": { + "External id": 4054142,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 64, 1], []], "Input Dims": [[16, 4096, 32, 64], []], "Ev Idx": 1149 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274545646.753, "dur": 0.852, + "args": { + "External id": 4054143,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 64, 1], []], "Input Dims": [[16, 4096, 32, 64], []], "Ev Idx": 1150 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274545653.116, "dur": 4.570, + "args": { + "External id": 4054144,"Record function id": 0, "Sequence number": 40618457, "Fwd thread id": 1, "Ev Idx": 1151 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274545653.878, "dur": 2.326, + "args": { + "External id": 4054145,"Sequence number": 40618457, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 64, 1]], "Input Dims": [[16, 4096, 32, 64]], "Ev Idx": 1152 + } + }, + { + "ph": "f", "id": 123, "pid": 1336756, "tid": 1381189, "ts": 1655274545653.878, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1381189, + "ts": 1655274545654.690, "dur": 1.361, + "args": { + "External id": 4054146,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 64, 1], []], "Input Dims": [[16, 4096, 32, 64], []], "Ev Idx": 1153 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274545655.166, "dur": 0.796, + "args": { + "External id": 4054147,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 64, 1], []], "Input Dims": [[16, 4096, 32, 64], []], "Ev Idx": 1154 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: UnsafeViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274545661.166, "dur": 9.131, + "args": { + "External id": 4054148,"Record function id": 0, "Sequence number": 40618456, "Fwd thread id": 1, "Ev Idx": 1155 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274545661.823, "dur": 6.423, + "args": { + "External id": 4054149,"Sequence number": 40618456, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 1156 + } + }, + { + "ph": "f", "id": 124, "pid": 1336756, "tid": 1381189, "ts": 1655274545661.823, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1381189, + "ts": 1655274545662.692, "dur": 5.403, + "args": { + "External id": 4054150,"Record function id": 0, "Concrete Inputs": ["", "[65536, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 1157 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274545667.198, "dur": 0.810, + "args": { + "External id": 4054151,"Record function id": 0, "Concrete Inputs": ["", "[65536, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 1158 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: MmBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274545673.526, "dur": 144.426, + "args": { + "External id": 4054152,"Record function id": 0, "Sequence number": 40618455, "Fwd thread id": 1, "Ev Idx": 1159 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274545674.405, "dur": 137.308, + "args": { + "External id": 4054153,"Sequence number": 40618455, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[65536, 2048]], "Ev Idx": 1160 + } + }, + { + "ph": "f", "id": 125, "pid": 1336756, "tid": 1381189, "ts": 1655274545674.405, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1381189, + "ts": 1655274545677.813, "dur": 6.599, + "args": { + "External id": 4054154,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[65536, 2048]], "Ev Idx": 1161 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1381189, + "ts": 1655274545679.657, "dur": 4.137, + "args": { + "External id": 4054155,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[65536, 2048], [], []], "Ev Idx": 1162 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274545681.809, "dur": 1.771, + "args": { + "External id": 4054156,"Record function id": 0, "Concrete Inputs": ["", "[2048, 65536]", "[1, 2048]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[65536, 2048], [], [], []], "Ev Idx": 1163 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655274545688.508, "dur": 65.588, + "args": { + "External id": 4054157,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048]], "Ev Idx": 1164 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1381189, + "ts": 1655274545755.318, "dur": 3.679, + "args": { + "External id": 4054158,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 1165 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1381189, + "ts": 1655274545755.996, "dur": 2.385, + "args": { + "External id": 4054159,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[2048, 2048], [], []], "Ev Idx": 1166 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274545757.042, "dur": 1.206, + "args": { + "External id": 4054160,"Record function id": 0, "Concrete Inputs": ["", "[2048, 2048]", "[1, 2048]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[2048, 2048], [], [], []], "Ev Idx": 1167 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1381189, + "ts": 1655274545760.683, "dur": 4.780, + "args": { + "External id": 4054161,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 2048]], "Input Dims": [[2048, 2048]], "Ev Idx": 1168 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1381189, + "ts": 1655274545761.896, "dur": 3.109, + "args": { + "External id": 4054162,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 2048], [], []], "Input Dims": [[2048, 2048], [], []], "Ev Idx": 1169 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274545764.573, "dur": 0.368, + "args": { + "External id": 4054163,"Record function id": 0, "Concrete Inputs": ["", "[2048, 2048]", "[2048, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 2048], [], [], []], "Input Dims": [[2048, 2048], [], [], []], "Ev Idx": 1170 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655274545768.126, "dur": 42.530, + "args": { + "External id": 4054164,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048]], "Ev Idx": 1171 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274545824.628, "dur": 5.792, + "args": { + "External id": 4054165,"Record function id": 0, "Sequence number": 40618454, "Fwd thread id": 1, "Ev Idx": 1172 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274545825.760, "dur": 3.209, + "args": { + "External id": 4054166,"Sequence number": 40618454, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[65536, 2048]], "Ev Idx": 1173 + } + }, + { + "ph": "f", "id": 126, "pid": 1336756, "tid": 1381189, "ts": 1655274545825.760, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1381189, + "ts": 1655274545826.942, "dur": 1.879, + "args": { + "External id": 4054167,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 1174 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274545827.687, "dur": 1.042, + "args": { + "External id": 4054168,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 1175 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: TBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274545833.692, "dur": 7.520, + "args": { + "External id": 4054169,"Record function id": 0, "Sequence number": 40618453, "Fwd thread id": 1, "Ev Idx": 1176 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274545834.447, "dur": 5.285, + "args": { + "External id": 4054170,"Sequence number": 40618453, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 2048]], "Input Dims": [[2048, 2048]], "Ev Idx": 1177 + } + }, + { + "ph": "f", "id": 127, "pid": 1336756, "tid": 1381189, "ts": 1655274545834.447, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1381189, + "ts": 1655274545835.189, "dur": 4.335, + "args": { + "External id": 4054171,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 2048]], "Input Dims": [[2048, 2048]], "Ev Idx": 1178 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1381189, + "ts": 1655274545835.700, "dur": 3.379, + "args": { + "External id": 4054172,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 2048], [], []], "Input Dims": [[2048, 2048], [], []], "Ev Idx": 1179 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274545838.540, "dur": 0.436, + "args": { + "External id": 4054173,"Record function id": 0, "Concrete Inputs": ["", "[2048, 2048]", "[2048, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 2048], [], [], []], "Input Dims": [[2048, 2048], [], [], []], "Ev Idx": 1180 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274545848.521, "dur": 8.171, + "args": { + "External id": 4054174,"Record function id": 0, "Ev Idx": 1181 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274545849.773, "dur": 6.159, + "args": { + "External id": 4054175,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 1182 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274545852.128, "dur": 3.413, + "args": { + "External id": 4054176,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 1183 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274545853.089, "dur": 2.363, + "args": { + "External id": 4054177,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 1184 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: UnsafeViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274545859.636, "dur": 4.290, + "args": { + "External id": 4054178,"Record function id": 0, "Sequence number": 40618452, "Fwd thread id": 1, "Ev Idx": 1185 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274545860.521, "dur": 2.097, + "args": { + "External id": 4054179,"Sequence number": 40618452, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 1186 + } + }, + { + "ph": "f", "id": 128, "pid": 1336756, "tid": 1381189, "ts": 1655274545860.521, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1381189, + "ts": 1655274545861.298, "dur": 1.191, + "args": { + "External id": 4054180,"Record function id": 0, "Concrete Inputs": ["", "[65536, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 1187 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274545861.755, "dur": 0.643, + "args": { + "External id": 4054181,"Record function id": 0, "Concrete Inputs": ["", "[65536, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 1188 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: MmBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274545867.066, "dur": 86.530, + "args": { + "External id": 4054182,"Record function id": 0, "Sequence number": 40618451, "Fwd thread id": 1, "Ev Idx": 1189 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274545867.794, "dur": 79.836, + "args": { + "External id": 4054183,"Sequence number": 40618451, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[65536, 2048]], "Ev Idx": 1190 + } + }, + { + "ph": "f", "id": 129, "pid": 1336756, "tid": 1381189, "ts": 1655274545867.794, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1381189, + "ts": 1655274545871.782, "dur": 2.051, + "args": { + "External id": 4054184,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[65536, 2048]], "Ev Idx": 1191 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1381189, + "ts": 1655274545872.367, "dur": 1.018, + "args": { + "External id": 4054185,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[65536, 2048], [], []], "Ev Idx": 1192 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274545872.960, "dur": 0.299, + "args": { + "External id": 4054186,"Record function id": 0, "Concrete Inputs": ["", "[2048, 65536]", "[1, 2048]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[65536, 2048], [], [], []], "Ev Idx": 1193 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655274545874.418, "dur": 25.169, + "args": { + "External id": 4054187,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048]], "Ev Idx": 1194 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1381189, + "ts": 1655274545900.453, "dur": 6.318, + "args": { + "External id": 4054188,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 1195 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1381189, + "ts": 1655274545900.913, "dur": 5.299, + "args": { + "External id": 4054189,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[2048, 2048], [], []], "Ev Idx": 1196 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274545905.504, "dur": 0.606, + "args": { + "External id": 4054190,"Record function id": 0, "Concrete Inputs": ["", "[2048, 2048]", "[1, 2048]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[2048, 2048], [], [], []], "Ev Idx": 1197 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1381189, + "ts": 1655274545907.584, "dur": 4.825, + "args": { + "External id": 4054191,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 2048]], "Input Dims": [[2048, 2048]], "Ev Idx": 1198 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1381189, + "ts": 1655274545908.493, "dur": 3.538, + "args": { + "External id": 4054192,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 2048], [], []], "Input Dims": [[2048, 2048], [], []], "Ev Idx": 1199 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274545909.369, "dur": 2.529, + "args": { + "External id": 4054193,"Record function id": 0, "Concrete Inputs": ["", "[2048, 2048]", "[2048, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 2048], [], [], []], "Input Dims": [[2048, 2048], [], [], []], "Ev Idx": 1200 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655274545912.992, "dur": 33.902, + "args": { + "External id": 4054194,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048]], "Ev Idx": 1201 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274545957.978, "dur": 74.092, + "args": { + "External id": 4054195,"Record function id": 0, "Sequence number": 40618450, "Fwd thread id": 1, "Ev Idx": 1202 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274545958.927, "dur": 6.713, + "args": { + "External id": 4054196,"Sequence number": 40618450, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[65536, 2048]], "Ev Idx": 1203 + } + }, + { + "ph": "f", "id": 130, "pid": 1336756, "tid": 1381189, "ts": 1655274545958.927, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1381189, + "ts": 1655274545961.907, "dur": 3.586, + "args": { + "External id": 4054197,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 1204 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274545964.174, "dur": 1.184, + "args": { + "External id": 4054198,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 1205 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add", "pid": 1336756, "tid": 1381189, + "ts": 1655274545968.628, "dur": 60.022, + "args": { + "External id": 4054199,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[8388608, 2048, 1], [8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], [16, 4096, 2048], []], "Ev Idx": 1206 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: TBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274546040.029, "dur": 8.258, + "args": { + "External id": 4054200,"Record function id": 0, "Sequence number": 40618449, "Fwd thread id": 1, "Ev Idx": 1207 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274546041.498, "dur": 5.061, + "args": { + "External id": 4054201,"Sequence number": 40618449, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 2048]], "Input Dims": [[2048, 2048]], "Ev Idx": 1208 + } + }, + { + "ph": "f", "id": 131, "pid": 1336756, "tid": 1381189, "ts": 1655274546041.498, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1381189, + "ts": 1655274546042.600, "dur": 3.743, + "args": { + "External id": 4054202,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 2048]], "Input Dims": [[2048, 2048]], "Ev Idx": 1209 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1381189, + "ts": 1655274546043.546, "dur": 2.147, + "args": { + "External id": 4054203,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 2048], [], []], "Input Dims": [[2048, 2048], [], []], "Ev Idx": 1210 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274546044.935, "dur": 0.629, + "args": { + "External id": 4054204,"Record function id": 0, "Concrete Inputs": ["", "[2048, 2048]", "[2048, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 2048], [], [], []], "Input Dims": [[2048, 2048], [], [], []], "Ev Idx": 1211 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274546052.409, "dur": 8.108, + "args": { + "External id": 4054205,"Record function id": 0, "Ev Idx": 1212 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274546053.703, "dur": 6.253, + "args": { + "External id": 4054206,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 1213 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274546054.996, "dur": 4.559, + "args": { + "External id": 4054207,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 1214 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274546057.708, "dur": 1.772, + "args": { + "External id": 4054208,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 1215 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: UnsafeViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274546063.659, "dur": 9.492, + "args": { + "External id": 4054209,"Record function id": 0, "Sequence number": 40618448, "Fwd thread id": 1, "Ev Idx": 1216 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274546064.372, "dur": 7.009, + "args": { + "External id": 4054210,"Sequence number": 40618448, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 1217 + } + }, + { + "ph": "f", "id": 132, "pid": 1336756, "tid": 1381189, "ts": 1655274546064.372, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1381189, + "ts": 1655274546065.104, "dur": 6.130, + "args": { + "External id": 4054211,"Record function id": 0, "Concrete Inputs": ["", "[65536, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 1218 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274546070.222, "dur": 0.914, + "args": { + "External id": 4054212,"Record function id": 0, "Concrete Inputs": ["", "[65536, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 1219 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: MmBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274546076.135, "dur": 94.506, + "args": { + "External id": 4054213,"Record function id": 0, "Sequence number": 40618447, "Fwd thread id": 1, "Ev Idx": 1220 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274546076.786, "dur": 85.994, + "args": { + "External id": 4054214,"Sequence number": 40618447, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[65536, 2048]], "Ev Idx": 1221 + } + }, + { + "ph": "f", "id": 133, "pid": 1336756, "tid": 1381189, "ts": 1655274546076.786, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1381189, + "ts": 1655274546080.600, "dur": 2.435, + "args": { + "External id": 4054215,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[65536, 2048]], "Ev Idx": 1222 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1381189, + "ts": 1655274546081.187, "dur": 1.430, + "args": { + "External id": 4054216,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[65536, 2048], [], []], "Ev Idx": 1223 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274546081.967, "dur": 0.535, + "args": { + "External id": 4054217,"Record function id": 0, "Concrete Inputs": ["", "[2048, 65536]", "[1, 2048]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[65536, 2048], [], [], []], "Ev Idx": 1224 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655274546083.720, "dur": 32.162, + "args": { + "External id": 4054218,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048]], "Ev Idx": 1225 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1381189, + "ts": 1655274546116.744, "dur": 5.946, + "args": { + "External id": 4054219,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 1226 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1381189, + "ts": 1655274546117.299, "dur": 4.907, + "args": { + "External id": 4054220,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[2048, 2048], [], []], "Ev Idx": 1227 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274546119.923, "dur": 2.143, + "args": { + "External id": 4054221,"Record function id": 0, "Concrete Inputs": ["", "[2048, 2048]", "[1, 2048]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[2048, 2048], [], [], []], "Ev Idx": 1228 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1381189, + "ts": 1655274546123.772, "dur": 4.671, + "args": { + "External id": 4054222,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 2048]], "Input Dims": [[2048, 2048]], "Ev Idx": 1229 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1381189, + "ts": 1655274546124.436, "dur": 3.622, + "args": { + "External id": 4054223,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 2048], [], []], "Input Dims": [[2048, 2048], [], []], "Ev Idx": 1230 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274546127.585, "dur": 0.365, + "args": { + "External id": 4054224,"Record function id": 0, "Concrete Inputs": ["", "[2048, 2048]", "[2048, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 2048], [], [], []], "Input Dims": [[2048, 2048], [], [], []], "Ev Idx": 1231 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655274546128.865, "dur": 33.315, + "args": { + "External id": 4054225,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048]], "Ev Idx": 1232 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274546175.095, "dur": 23.534, + "args": { + "External id": 4054226,"Record function id": 0, "Sequence number": 40618446, "Fwd thread id": 1, "Ev Idx": 1233 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274546175.929, "dur": 3.059, + "args": { + "External id": 4054227,"Sequence number": 40618446, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[65536, 2048]], "Ev Idx": 1234 + } + }, + { + "ph": "f", "id": 134, "pid": 1336756, "tid": 1381189, "ts": 1655274546175.929, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1381189, + "ts": 1655274546176.988, "dur": 1.843, + "args": { + "External id": 4054228,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 1235 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274546177.469, "dur": 1.220, + "args": { + "External id": 4054229,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 1236 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336756, "tid": 1381189, + "ts": 1655274546181.405, "dur": 15.448, + "args": { + "External id": 4054230,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[8388608, 2048, 1], [8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], [16, 4096, 2048], []], "Ev Idx": 1237 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: TBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274546204.371, "dur": 6.816, + "args": { + "External id": 4054231,"Record function id": 0, "Sequence number": 40618445, "Fwd thread id": 1, "Ev Idx": 1238 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274546205.359, "dur": 3.795, + "args": { + "External id": 4054232,"Sequence number": 40618445, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 2048]], "Input Dims": [[2048, 2048]], "Ev Idx": 1239 + } + }, + { + "ph": "f", "id": 135, "pid": 1336756, "tid": 1381189, "ts": 1655274546205.359, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1381189, + "ts": 1655274546206.261, "dur": 2.688, + "args": { + "External id": 4054233,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 2048]], "Input Dims": [[2048, 2048]], "Ev Idx": 1240 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1381189, + "ts": 1655274546207.006, "dur": 1.388, + "args": { + "External id": 4054234,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 2048], [], []], "Input Dims": [[2048, 2048], [], []], "Ev Idx": 1241 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274546207.878, "dur": 0.409, + "args": { + "External id": 4054235,"Record function id": 0, "Concrete Inputs": ["", "[2048, 2048]", "[2048, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 2048], [], [], []], "Input Dims": [[2048, 2048], [], [], []], "Ev Idx": 1242 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274546217.049, "dur": 4.341, + "args": { + "External id": 4054236,"Record function id": 0, "Ev Idx": 1243 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274546218.187, "dur": 2.721, + "args": { + "External id": 4054237,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 1244 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274546218.987, "dur": 1.645, + "args": { + "External id": 4054238,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 1245 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274546219.598, "dur": 0.961, + "args": { + "External id": 4054239,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 1246 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: LayerNormFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1655274546227.402, "dur": 364.878, + "args": { + "External id": 4054240,"Record function id": 0, "Sequence number": 40618444, "Fwd thread id": 1, "Ev Idx": 1247 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1655274546228.406, "dur": 332.725, + "args": { + "External id": 4054241,"Sequence number": 40618444, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 1248 + } + }, + { + "ph": "f", "id": 136, "pid": 1336756, "tid": 1381189, "ts": 1655274546228.406, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1381189, + "ts": 1655274546260.598, "dur": 1.564, + "args": { + "External id": 4054242,"Record function id": 0, "Concrete Inputs": ["", "[-1, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 1249 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274546261.131, "dur": 0.894, + "args": { + "External id": 4054243,"Record function id": 0, "Concrete Inputs": ["", "[-1, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 1250 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655274546275.643, "dur": 5.327, + "args": { + "External id": 4054244,"Record function id": 0, "Concrete Inputs": ["[65536, 2048]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1251 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655274546290.397, "dur": 1.798, + "args": { + "External id": 4054245,"Record function id": 0, "Concrete Inputs": ["[132, 2048]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1252 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274546455.883, "dur": 2.704, + "args": { + "External id": 4054246,"Record function id": 0, "Concrete Inputs": ["", "[1, -1, 2048]"], "Input type": ["float", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[132, 2048], []], "Ev Idx": 1253 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 1336756, "tid": 1381189, + "ts": 1655274546463.005, "dur": 35.249, + "args": { + "External id": 4054247,"Record function id": 0, "Concrete Inputs": ["", "[1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", ""], "Input Strides": [[270336, 2048, 1], [], [], []], "Input Dims": [[1, 132, 2048], [], [], []], "Ev Idx": 1254 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274546473.253, "dur": 1.274, + "args": { + "External id": 4054248,"Record function id": 0, "Concrete Inputs": ["", "[1, 1, 2048]", "[2048, 0, 1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[1, 2048], [], [], []], "Ev Idx": 1255 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1381189, + "ts": 1655274546503.918, "dur": 33.789, + "args": { + "External id": 4054249,"Record function id": 0, "Concrete Inputs": ["", "", "15", "False", "False", ""], "Input type": ["float", "", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[2048, 1], [], [], [], [], []], "Input Dims": [[1, 2048], [], [], [], [], []], "Ev Idx": 1256 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336756, "tid": 1381189, + "ts": 1655274546507.923, "dur": 29.504, + "args": { + "External id": 4054250,"Record function id": 0, "Concrete Inputs": ["", "15", "", "", "", "False", ""], "Input type": ["float", "Scalar", "", "", "", "Scalar", ""], "Input Strides": [[2048, 1], [], [], [], [], [], []], "Input Dims": [[1, 2048], [], [], [], [], [], []], "Ev Idx": 1257 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274546513.798, "dur": 5.240, + "args": { + "External id": 4054251,"Record function id": 0, "Concrete Inputs": ["[1, 2048]", "[2048, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1258 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1381189, + "ts": 1655274546520.537, "dur": 16.219, + "args": { + "External id": 4054252,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "float", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[1, 2048], [1, 2048], []], "Ev Idx": 1259 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 1336756, "tid": 1381189, + "ts": 1655274546542.262, "dur": 2.214, + "args": { + "External id": 4054253,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1]], "Input Dims": [[1, 2048], [2048]], "Ev Idx": 1260 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274546543.217, "dur": 1.112, + "args": { + "External id": 4054254,"Record function id": 0, "Concrete Inputs": ["", "[2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[1, 2048], []], "Ev Idx": 1261 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1381189, + "ts": 1655274546550.495, "dur": 3.953, + "args": { + "External id": 4054255,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 1262 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274546553.434, "dur": 0.912, + "args": { + "External id": 4054256,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 1263 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336756, "tid": 1381189, + "ts": 1655274546572.203, "dur": 15.890, + "args": { + "External id": 4054257,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[8388608, 2048, 1], [8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], [16, 4096, 2048], []], "Ev Idx": 1264 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274546604.694, "dur": 8.515, + "args": { + "External id": 4054258,"Record function id": 0, "Ev Idx": 1265 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274546606.463, "dur": 5.994, + "args": { + "External id": 4054259,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 1266 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274546608.496, "dur": 2.995, + "args": { + "External id": 4054260,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 1267 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274546609.522, "dur": 1.851, + "args": { + "External id": 4054261,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 1268 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: AddBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274546616.989, "dur": 5.212, + "args": { + "External id": 4054262,"Record function id": 0, "Sequence number": 40618443, "Fwd thread id": 1, "Ev Idx": 1269 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "AddBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274546618.410, "dur": 1.190, + "args": { + "External id": 4054263,"Sequence number": 40618443, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[33554432, 8192, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 1270 + } + }, + { + "ph": "f", "id": 137, "pid": 1336756, "tid": 1381189, "ts": 1655274546618.410, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: SwiGLULinearFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1655274546625.706, "dur": 446.824, + "args": { + "External id": 4054264,"Record function id": 0, "Sequence number": 40618442, "Fwd thread id": 1, "Ev Idx": 1271 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SwiGLULinearFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1655274546629.071, "dur": 431.643, + "args": { + "External id": 4054265,"Sequence number": 40618442, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[33554432, 8192, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 1272 + } + }, + { + "ph": "f", "id": 138, "pid": 1336756, "tid": 1381189, "ts": 1655274546629.071, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1381189, + "ts": 1655274546661.490, "dur": 7.863, + "args": { + "External id": 4054266,"Record function id": 0, "Concrete Inputs": ["", "[-1, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[33554432, 8192, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 1273 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_reshape_alias", "pid": 1336756, "tid": 1381189, + "ts": 1655274546666.033, "dur": 3.105, + "args": { + "External id": 4054267,"Record function id": 0, "Concrete Inputs": ["", "[65536, 2048]", "[8192, 1]"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList"], "Input Strides": [[33554432, 8192, 1], [], []], "Input Dims": [[16, 4096, 2048], [], []], "Ev Idx": 1274 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1381189, + "ts": 1655274546672.323, "dur": 6.550, + "args": { + "External id": 4054268,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 1275 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1381189, + "ts": 1655274546673.801, "dur": 4.449, + "args": { + "External id": 4054269,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[5632, 1], [], []], "Input Dims": [[2048, 5632], [], []], "Ev Idx": 1276 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274546675.054, "dur": 3.027, + "args": { + "External id": 4054270,"Record function id": 0, "Concrete Inputs": ["", "[5632, 2048]", "[1, 5632]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[5632, 1], [], [], []], "Input Dims": [[2048, 5632], [], [], []], "Ev Idx": 1277 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336756, "tid": 1381189, + "ts": 1655274546682.306, "dur": 89.004, + "args": { + "External id": 4054271,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[8192, 1], [1, 5632], []], "Input Dims": [[65536, 2048], [5632, 2048], []], "Ev Idx": 1278 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1381189, + "ts": 1655274546685.488, "dur": 4.652, + "args": { + "External id": 4054272,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 5632]], "Input Dims": [[5632, 2048]], "Ev Idx": 1279 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1381189, + "ts": 1655274546686.035, "dur": 3.679, + "args": { + "External id": 4054273,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 5632], [], []], "Input Dims": [[5632, 2048], [], []], "Ev Idx": 1280 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274546689.102, "dur": 0.486, + "args": { + "External id": 4054274,"Record function id": 0, "Concrete Inputs": ["", "[2048, 5632]", "[5632, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 5632], [], [], []], "Input Dims": [[5632, 2048], [], [], []], "Ev Idx": 1281 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336756, "tid": 1381189, + "ts": 1655274546691.460, "dur": 79.241, + "args": { + "External id": 4054275,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[8192, 1], [5632, 1]], "Input Dims": [[65536, 2048], [2048, 5632]], "Ev Idx": 1282 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655274546692.875, "dur": 76.863, + "args": { + "External id": 4054276,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[8192, 1], [5632, 1]], "Input Dims": [[65536, 2048], [2048, 5632]], "Ev Idx": 1283 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 1336756, "tid": 1381189, + "ts": 1655274546774.996, "dur": 2.407, + "args": { + "External id": 4054277,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [23068672, 5632, 1]], "Input Dims": [[65536, 5632], [16, 4096, 5632]], "Ev Idx": 1284 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274546775.957, "dur": 1.336, + "args": { + "External id": 4054278,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 5632]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[5632, 1], []], "Input Dims": [[65536, 5632], []], "Ev Idx": 1285 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655274546810.495, "dur": 4.966, + "args": { + "External id": 4054279,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 5632]", "15", "", "", "", "0"], "Input type": ["ScalarList", "Scalar", "", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1286 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655274546818.449, "dur": 1.799, + "args": { + "External id": 4054280,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 5632]", "15", "", "", "", "0"], "Input type": ["ScalarList", "Scalar", "", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1287 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655274546820.968, "dur": 1.566, + "args": { + "External id": 4054281,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 5632]", "15", "", "", "", "0"], "Input type": ["ScalarList", "Scalar", "", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1288 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1381189, + "ts": 1655274546852.509, "dur": 2.037, + "args": { + "External id": 4054282,"Record function id": 0, "Concrete Inputs": ["", "[-1, 5632]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[23068672, 5632, 1], []], "Input Dims": [[16, 4096, 5632], []], "Ev Idx": 1289 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274546853.247, "dur": 1.143, + "args": { + "External id": 4054283,"Record function id": 0, "Concrete Inputs": ["", "[-1, 5632]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[23068672, 5632, 1], []], "Input Dims": [[16, 4096, 5632], []], "Ev Idx": 1290 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::einsum", "pid": 1336756, "tid": 1381189, + "ts": 1655274546875.309, "dur": 164.005, + "args": { + "External id": 4054284,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["", "TensorList", ""], "Input Strides": [[], [[8192, 1], [5632, 1]], []], "Input Dims": [[], [[65536, 2048], [65536, 5632]], []], "Ev Idx": 1291 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1381189, + "ts": 1655274546880.340, "dur": 9.718, + "args": { + "External id": 4054285,"Record function id": 0, "Concrete Inputs": ["", "2"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[8192, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 1292 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274546885.544, "dur": 3.762, + "args": { + "External id": 4054286,"Record function id": 0, "Concrete Inputs": ["", "[65536, 2048, 1]", "[8192, 1, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[8192, 1], [], [], []], "Input Dims": [[65536, 2048], [], [], []], "Ev Idx": 1293 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::permute", "pid": 1336756, "tid": 1381189, + "ts": 1655274546891.220, "dur": 6.193, + "args": { + "External id": 4054287,"Record function id": 0, "Concrete Inputs": ["", "[1, 2, 0]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8192, 1, 1], []], "Input Dims": [[65536, 2048, 1], []], "Ev Idx": 1294 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274546895.897, "dur": 0.765, + "args": { + "External id": 4054288,"Record function id": 0, "Concrete Inputs": ["", "[2048, 1, 65536]", "[1, 1, 8192]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[8192, 1, 1], [], [], []], "Input Dims": [[65536, 2048, 1], [], [], []], "Ev Idx": 1295 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1381189, + "ts": 1655274546898.556, "dur": 1.920, + "args": { + "External id": 4054289,"Record function id": 0, "Concrete Inputs": ["", "2"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[5632, 1], []], "Input Dims": [[65536, 5632], []], "Ev Idx": 1296 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274546899.586, "dur": 0.585, + "args": { + "External id": 4054290,"Record function id": 0, "Concrete Inputs": ["", "[65536, 5632, 1]", "[5632, 1, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[5632, 1], [], [], []], "Input Dims": [[65536, 5632], [], [], []], "Ev Idx": 1297 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::permute", "pid": 1336756, "tid": 1381189, + "ts": 1655274546903.146, "dur": 2.102, + "args": { + "External id": 4054291,"Record function id": 0, "Concrete Inputs": ["", "[2, 1, 0]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[5632, 1, 1], []], "Input Dims": [[65536, 5632, 1], []], "Ev Idx": 1298 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274546904.330, "dur": 0.472, + "args": { + "External id": 4054292,"Record function id": 0, "Concrete Inputs": ["", "[1, 5632, 65536]", "[1, 1, 5632]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[5632, 1, 1], [], [], []], "Input Dims": [[65536, 5632, 1], [], [], []], "Ev Idx": 1299 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::permute", "pid": 1336756, "tid": 1381189, + "ts": 1655274546908.370, "dur": 3.686, + "args": { + "External id": 4054293,"Record function id": 0, "Concrete Inputs": ["", "[0, 2, 1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1, 1, 8192], []], "Input Dims": [[2048, 1, 65536], []], "Ev Idx": 1300 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274546911.277, "dur": 0.500, + "args": { + "External id": 4054294,"Record function id": 0, "Concrete Inputs": ["", "[2048, 65536, 1]", "[1, 8192, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1, 8192], [], [], []], "Input Dims": [[2048, 1, 65536], [], [], []], "Ev Idx": 1301 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1381189, + "ts": 1655274546912.850, "dur": 6.122, + "args": { + "External id": 4054295,"Record function id": 0, "Concrete Inputs": ["", "[1, 2048, 65536]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1, 8192, 1], []], "Input Dims": [[2048, 65536, 1], []], "Ev Idx": 1302 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_reshape_alias", "pid": 1336756, "tid": 1381189, + "ts": 1655274546917.304, "dur": 1.493, + "args": { + "External id": 4054296,"Record function id": 0, "Concrete Inputs": ["", "[1, 2048, 65536]", "[2048, 1, 8192]"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList"], "Input Strides": [[1, 8192, 1], [], []], "Input Dims": [[2048, 65536, 1], [], []], "Ev Idx": 1303 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::permute", "pid": 1336756, "tid": 1381189, + "ts": 1655274546921.891, "dur": 3.424, + "args": { + "External id": 4054297,"Record function id": 0, "Concrete Inputs": ["", "[2, 1, 0]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1, 1, 5632], []], "Input Dims": [[1, 5632, 65536], []], "Ev Idx": 1304 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274546924.743, "dur": 0.327, + "args": { + "External id": 4054298,"Record function id": 0, "Concrete Inputs": ["", "[65536, 5632, 1]", "[5632, 1, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1, 5632], [], [], []], "Input Dims": [[1, 5632, 65536], [], [], []], "Ev Idx": 1305 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1381189, + "ts": 1655274546925.902, "dur": 3.188, + "args": { + "External id": 4054299,"Record function id": 0, "Concrete Inputs": ["", "[1, 65536, 5632]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[5632, 1, 1], []], "Input Dims": [[65536, 5632, 1], []], "Ev Idx": 1306 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274546926.753, "dur": 2.251, + "args": { + "External id": 4054300,"Record function id": 0, "Concrete Inputs": ["", "[1, 65536, 5632]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[5632, 1, 1], []], "Input Dims": [[65536, 5632, 1], []], "Ev Idx": 1307 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 1336756, "tid": 1381189, + "ts": 1655274546930.078, "dur": 52.122, + "args": { + "External id": 4054301,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1, 8192], [369098752, 5632, 1]], "Input Dims": [[1, 2048, 65536], [1, 65536, 5632]], "Ev Idx": 1308 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274547027.468, "dur": 2.109, + "args": { + "External id": 4054302,"Record function id": 0, "Concrete Inputs": ["", "[2048, 1, 5632]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[11534336, 5632, 1], []], "Input Dims": [[1, 2048, 5632], []], "Ev Idx": 1309 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::permute", "pid": 1336756, "tid": 1381189, + "ts": 1655274547030.621, "dur": 2.431, + "args": { + "External id": 4054303,"Record function id": 0, "Concrete Inputs": ["", "[0, 2, 1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[5632, 5632, 1], []], "Input Dims": [[2048, 1, 5632], []], "Ev Idx": 1310 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274547032.141, "dur": 0.566, + "args": { + "External id": 4054304,"Record function id": 0, "Concrete Inputs": ["", "[2048, 5632, 1]", "[5632, 1, 5632]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[5632, 5632, 1], [], [], []], "Input Dims": [[2048, 1, 5632], [], [], []], "Ev Idx": 1311 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274547037.072, "dur": 1.053, + "args": { + "External id": 4054305,"Record function id": 0, "Concrete Inputs": ["", "[2048, 5632]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[5632, 1, 5632], []], "Input Dims": [[2048, 5632, 1], []], "Ev Idx": 1312 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274547084.946, "dur": 9.548, + "args": { + "External id": 4054306,"Record function id": 0, "Ev Idx": 1313 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274547087.392, "dur": 6.442, + "args": { + "External id": 4054307,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 1314 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274547089.701, "dur": 3.200, + "args": { + "External id": 4054308,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 1315 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274547090.801, "dur": 1.980, + "args": { + "External id": 4054309,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 1316 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: UnsafeViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274547098.113, "dur": 5.723, + "args": { + "External id": 4054310,"Record function id": 0, "Sequence number": 40618441, "Fwd thread id": 1, "Ev Idx": 1317 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274547099.064, "dur": 2.895, + "args": { + "External id": 4054311,"Sequence number": 40618441, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[23068672, 5632, 1]], "Input Dims": [[16, 4096, 5632]], "Ev Idx": 1318 + } + }, + { + "ph": "f", "id": 139, "pid": 1336756, "tid": 1381189, "ts": 1655274547099.064, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1381189, + "ts": 1655274547100.417, "dur": 1.348, + "args": { + "External id": 4054312,"Record function id": 0, "Concrete Inputs": ["", "[65536, 5632]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[23068672, 5632, 1], []], "Input Dims": [[16, 4096, 5632], []], "Ev Idx": 1319 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274547100.899, "dur": 0.744, + "args": { + "External id": 4054313,"Record function id": 0, "Concrete Inputs": ["", "[65536, 5632]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[23068672, 5632, 1], []], "Input Dims": [[16, 4096, 5632], []], "Ev Idx": 1320 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: MmBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274547107.152, "dur": 128.899, + "args": { + "External id": 4054314,"Record function id": 0, "Sequence number": 40618440, "Fwd thread id": 1, "Ev Idx": 1321 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274547107.933, "dur": 122.299, + "args": { + "External id": 4054315,"Sequence number": 40618440, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[65536, 5632]], "Ev Idx": 1322 + } + }, + { + "ph": "f", "id": 140, "pid": 1336756, "tid": 1381189, "ts": 1655274547107.933, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1381189, + "ts": 1655274547110.606, "dur": 5.550, + "args": { + "External id": 4054316,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[65536, 5632]], "Ev Idx": 1323 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1381189, + "ts": 1655274547112.021, "dur": 3.645, + "args": { + "External id": 4054317,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[5632, 1], [], []], "Input Dims": [[65536, 5632], [], []], "Ev Idx": 1324 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274547114.972, "dur": 0.493, + "args": { + "External id": 4054318,"Record function id": 0, "Concrete Inputs": ["", "[5632, 65536]", "[1, 5632]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[5632, 1], [], [], []], "Input Dims": [[65536, 5632], [], [], []], "Ev Idx": 1325 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655274547117.302, "dur": 47.026, + "args": { + "External id": 4054319,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 5632], [2048, 1]], "Input Dims": [[5632, 65536], [65536, 2048]], "Ev Idx": 1326 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1381189, + "ts": 1655274547165.451, "dur": 6.160, + "args": { + "External id": 4054320,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 1327 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1381189, + "ts": 1655274547166.233, "dur": 4.730, + "args": { + "External id": 4054321,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[5632, 2048], [], []], "Ev Idx": 1328 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274547169.836, "dur": 0.949, + "args": { + "External id": 4054322,"Record function id": 0, "Concrete Inputs": ["", "[2048, 5632]", "[1, 2048]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[5632, 2048], [], [], []], "Ev Idx": 1329 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1381189, + "ts": 1655274547173.051, "dur": 7.669, + "args": { + "External id": 4054323,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 2048]], "Input Dims": [[2048, 5632]], "Ev Idx": 1330 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1381189, + "ts": 1655274547176.484, "dur": 3.751, + "args": { + "External id": 4054324,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 2048], [], []], "Input Dims": [[2048, 5632], [], []], "Ev Idx": 1331 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274547177.347, "dur": 2.820, + "args": { + "External id": 4054325,"Record function id": 0, "Concrete Inputs": ["", "[5632, 2048]", "[2048, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 2048], [], [], []], "Input Dims": [[2048, 5632], [], [], []], "Ev Idx": 1332 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655274547181.423, "dur": 48.107, + "args": { + "External id": 4054326,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [2048, 1]], "Input Dims": [[65536, 5632], [5632, 2048]], "Ev Idx": 1333 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274547240.878, "dur": 5.400, + "args": { + "External id": 4054327,"Record function id": 0, "Sequence number": 40618439, "Fwd thread id": 1, "Ev Idx": 1334 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274547241.799, "dur": 3.223, + "args": { + "External id": 4054328,"Sequence number": 40618439, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[65536, 2048]], "Ev Idx": 1335 + } + }, + { + "ph": "f", "id": 141, "pid": 1336756, "tid": 1381189, "ts": 1655274547241.799, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1381189, + "ts": 1655274547242.796, "dur": 2.075, + "args": { + "External id": 4054329,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 1336 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274547243.470, "dur": 1.272, + "args": { + "External id": 4054330,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 1337 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: TBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274547249.575, "dur": 10.096, + "args": { + "External id": 4054331,"Record function id": 0, "Sequence number": 40618438, "Fwd thread id": 1, "Ev Idx": 1338 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274547250.452, "dur": 7.574, + "args": { + "External id": 4054332,"Sequence number": 40618438, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 2048]], "Input Dims": [[2048, 5632]], "Ev Idx": 1339 + } + }, + { + "ph": "f", "id": 142, "pid": 1336756, "tid": 1381189, "ts": 1655274547250.452, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1381189, + "ts": 1655274547253.262, "dur": 4.557, + "args": { + "External id": 4054333,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 2048]], "Input Dims": [[2048, 5632]], "Ev Idx": 1340 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1381189, + "ts": 1655274547253.911, "dur": 3.452, + "args": { + "External id": 4054334,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 2048], [], []], "Input Dims": [[2048, 5632], [], []], "Ev Idx": 1341 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274547256.700, "dur": 0.539, + "args": { + "External id": 4054335,"Record function id": 0, "Concrete Inputs": ["", "[5632, 2048]", "[2048, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 2048], [], [], []], "Input Dims": [[2048, 5632], [], [], []], "Ev Idx": 1342 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274547263.335, "dur": 4.817, + "args": { + "External id": 4054336,"Record function id": 0, "Ev Idx": 1343 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274547264.544, "dur": 3.029, + "args": { + "External id": 4054337,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 1344 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274547265.446, "dur": 1.829, + "args": { + "External id": 4054338,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 1345 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274547265.979, "dur": 1.204, + "args": { + "External id": 4054339,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 1346 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: UnsafeViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274547271.111, "dur": 7.030, + "args": { + "External id": 4054340,"Record function id": 0, "Sequence number": 40618437, "Fwd thread id": 1, "Ev Idx": 1347 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274547271.940, "dur": 4.461, + "args": { + "External id": 4054341,"Sequence number": 40618437, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[23068672, 5632, 1]], "Input Dims": [[16, 4096, 5632]], "Ev Idx": 1348 + } + }, + { + "ph": "f", "id": 143, "pid": 1336756, "tid": 1381189, "ts": 1655274547271.940, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1381189, + "ts": 1655274547272.830, "dur": 3.436, + "args": { + "External id": 4054342,"Record function id": 0, "Concrete Inputs": ["", "[65536, 5632]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[23068672, 5632, 1], []], "Input Dims": [[16, 4096, 5632], []], "Ev Idx": 1349 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274547275.493, "dur": 0.651, + "args": { + "External id": 4054343,"Record function id": 0, "Concrete Inputs": ["", "[65536, 5632]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[23068672, 5632, 1], []], "Input Dims": [[16, 4096, 5632], []], "Ev Idx": 1350 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: MmBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274547281.211, "dur": 107.932, + "args": { + "External id": 4054344,"Record function id": 0, "Sequence number": 40618436, "Fwd thread id": 1, "Ev Idx": 1351 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274547281.980, "dur": 100.375, + "args": { + "External id": 4054345,"Sequence number": 40618436, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[65536, 5632]], "Ev Idx": 1352 + } + }, + { + "ph": "f", "id": 144, "pid": 1336756, "tid": 1381189, "ts": 1655274547281.980, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1381189, + "ts": 1655274547283.745, "dur": 4.457, + "args": { + "External id": 4054346,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[65536, 5632]], "Ev Idx": 1353 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1381189, + "ts": 1655274547284.266, "dur": 3.529, + "args": { + "External id": 4054347,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[5632, 1], [], []], "Input Dims": [[65536, 5632], [], []], "Ev Idx": 1354 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274547287.137, "dur": 0.520, + "args": { + "External id": 4054348,"Record function id": 0, "Concrete Inputs": ["", "[5632, 65536]", "[1, 5632]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[5632, 1], [], [], []], "Input Dims": [[65536, 5632], [], [], []], "Ev Idx": 1355 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655274547288.765, "dur": 32.165, + "args": { + "External id": 4054349,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 5632], [2048, 1]], "Input Dims": [[5632, 65536], [65536, 2048]], "Ev Idx": 1356 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1381189, + "ts": 1655274547324.199, "dur": 5.340, + "args": { + "External id": 4054350,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 1357 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1381189, + "ts": 1655274547324.783, "dur": 4.199, + "args": { + "External id": 4054351,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[5632, 2048], [], []], "Ev Idx": 1358 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274547325.678, "dur": 3.123, + "args": { + "External id": 4054352,"Record function id": 0, "Concrete Inputs": ["", "[2048, 5632]", "[1, 2048]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[5632, 2048], [], [], []], "Ev Idx": 1359 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1381189, + "ts": 1655274547330.644, "dur": 2.557, + "args": { + "External id": 4054353,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 2048]], "Input Dims": [[2048, 5632]], "Ev Idx": 1360 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1381189, + "ts": 1655274547331.601, "dur": 1.211, + "args": { + "External id": 4054354,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 2048], [], []], "Input Dims": [[2048, 5632], [], []], "Ev Idx": 1361 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274547332.334, "dur": 0.413, + "args": { + "External id": 4054355,"Record function id": 0, "Concrete Inputs": ["", "[5632, 2048]", "[2048, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 2048], [], [], []], "Input Dims": [[2048, 5632], [], [], []], "Ev Idx": 1362 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655274547335.688, "dur": 46.013, + "args": { + "External id": 4054356,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [2048, 1]], "Input Dims": [[65536, 5632], [5632, 2048]], "Ev Idx": 1363 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274547395.557, "dur": 52.785, + "args": { + "External id": 4054357,"Record function id": 0, "Sequence number": 40618435, "Fwd thread id": 1, "Ev Idx": 1364 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274547396.575, "dur": 5.561, + "args": { + "External id": 4054358,"Sequence number": 40618435, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[65536, 2048]], "Ev Idx": 1365 + } + }, + { + "ph": "f", "id": 145, "pid": 1336756, "tid": 1381189, "ts": 1655274547396.575, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1381189, + "ts": 1655274547399.977, "dur": 2.010, + "args": { + "External id": 4054359,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 1366 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274547400.753, "dur": 1.097, + "args": { + "External id": 4054360,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 1367 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add", "pid": 1336756, "tid": 1381189, + "ts": 1655274547405.142, "dur": 38.873, + "args": { + "External id": 4054361,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[8388608, 2048, 1], [8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], [16, 4096, 2048], []], "Ev Idx": 1368 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: TBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274547453.901, "dur": 10.859, + "args": { + "External id": 4054362,"Record function id": 0, "Sequence number": 40618434, "Fwd thread id": 1, "Ev Idx": 1369 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274547455.032, "dur": 7.639, + "args": { + "External id": 4054363,"Sequence number": 40618434, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 2048]], "Input Dims": [[2048, 5632]], "Ev Idx": 1370 + } + }, + { + "ph": "f", "id": 146, "pid": 1336756, "tid": 1381189, "ts": 1655274547455.032, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1381189, + "ts": 1655274547456.367, "dur": 6.077, + "args": { + "External id": 4054364,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 2048]], "Input Dims": [[2048, 5632]], "Ev Idx": 1371 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1381189, + "ts": 1655274547457.575, "dur": 4.234, + "args": { + "External id": 4054365,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 2048], [], []], "Input Dims": [[2048, 5632], [], []], "Ev Idx": 1372 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274547460.927, "dur": 0.787, + "args": { + "External id": 4054366,"Record function id": 0, "Concrete Inputs": ["", "[5632, 2048]", "[2048, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 2048], [], [], []], "Input Dims": [[2048, 5632], [], [], []], "Ev Idx": 1373 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274547468.873, "dur": 8.274, + "args": { + "External id": 4054367,"Record function id": 0, "Ev Idx": 1374 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274547472.487, "dur": 4.189, + "args": { + "External id": 4054368,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 1375 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274547474.167, "dur": 2.205, + "args": { + "External id": 4054369,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 1376 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274547474.914, "dur": 1.364, + "args": { + "External id": 4054370,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 1377 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: LayerNormFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1655274547481.229, "dur": 405.316, + "args": { + "External id": 4054371,"Record function id": 0, "Sequence number": 40618433, "Fwd thread id": 1, "Ev Idx": 1378 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1655274547485.774, "dur": 369.878, + "args": { + "External id": 4054372,"Sequence number": 40618433, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[8388608, 2048, 1], [33554432, 8192, 1]], "Input Dims": [[16, 4096, 2048], [16, 4096, 2048]], "Ev Idx": 1379 + } + }, + { + "ph": "f", "id": 147, "pid": 1336756, "tid": 1381189, "ts": 1655274547485.774, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::contiguous", "pid": 1336756, "tid": 1381189, + "ts": 1655274547511.278, "dur": 33.164, + "args": { + "External id": 4054373,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[33554432, 8192, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 1380 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 1336756, "tid": 1381189, + "ts": 1655274547512.702, "dur": 31.528, + "args": { + "External id": 4054374,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[33554432, 8192, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 1381 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336756, "tid": 1381189, + "ts": 1655274547515.492, "dur": 6.113, + "args": { + "External id": 4054375,"Record function id": 0, "Concrete Inputs": ["", "15", "0", "", "", "0"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[33554432, 8192, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 2048], [], [], [], [], []], "Ev Idx": 1382 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655274547517.978, "dur": 3.142, + "args": { + "External id": 4054376,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 2048]", "15", "0", "", "", "0"], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1383 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1381189, + "ts": 1655274547523.080, "dur": 20.658, + "args": { + "External id": 4054377,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[8388608, 2048, 1], [33554432, 8192, 1], []], "Input Dims": [[16, 4096, 2048], [16, 4096, 2048], []], "Ev Idx": 1384 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1381189, + "ts": 1655274547557.184, "dur": 5.601, + "args": { + "External id": 4054378,"Record function id": 0, "Concrete Inputs": ["", "[-1, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 1385 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274547559.544, "dur": 3.092, + "args": { + "External id": 4054379,"Record function id": 0, "Concrete Inputs": ["", "[-1, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 1386 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1381189, + "ts": 1655274547566.971, "dur": 1.465, + "args": { + "External id": 4054380,"Record function id": 0, "Concrete Inputs": ["", "[-1, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 1387 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274547567.526, "dur": 0.815, + "args": { + "External id": 4054381,"Record function id": 0, "Concrete Inputs": ["", "[-1, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 1388 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655274547582.521, "dur": 2.200, + "args": { + "External id": 4054382,"Record function id": 0, "Concrete Inputs": ["[65536, 2048]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1389 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655274547595.475, "dur": 2.480, + "args": { + "External id": 4054383,"Record function id": 0, "Concrete Inputs": ["[132, 2048]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1390 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274547751.456, "dur": 2.823, + "args": { + "External id": 4054384,"Record function id": 0, "Concrete Inputs": ["", "[1, -1, 2048]"], "Input type": ["float", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[132, 2048], []], "Ev Idx": 1391 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 1336756, "tid": 1381189, + "ts": 1655274547758.176, "dur": 31.220, + "args": { + "External id": 4054385,"Record function id": 0, "Concrete Inputs": ["", "[1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", ""], "Input Strides": [[270336, 2048, 1], [], [], []], "Input Dims": [[1, 132, 2048], [], [], []], "Ev Idx": 1392 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274547768.188, "dur": 1.052, + "args": { + "External id": 4054386,"Record function id": 0, "Concrete Inputs": ["", "[1, 1, 2048]", "[2048, 0, 1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[1, 2048], [], [], []], "Ev Idx": 1393 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1381189, + "ts": 1655274547794.723, "dur": 27.324, + "args": { + "External id": 4054387,"Record function id": 0, "Concrete Inputs": ["", "", "15", "False", "False", ""], "Input type": ["float", "", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[2048, 1], [], [], [], [], []], "Input Dims": [[1, 2048], [], [], [], [], []], "Ev Idx": 1394 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336756, "tid": 1381189, + "ts": 1655274547796.389, "dur": 25.455, + "args": { + "External id": 4054388,"Record function id": 0, "Concrete Inputs": ["", "15", "", "", "", "False", ""], "Input type": ["float", "Scalar", "", "", "", "Scalar", ""], "Input Strides": [[2048, 1], [], [], [], [], [], []], "Input Dims": [[1, 2048], [], [], [], [], [], []], "Ev Idx": 1395 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274547799.750, "dur": 3.817, + "args": { + "External id": 4054389,"Record function id": 0, "Concrete Inputs": ["[1, 2048]", "[2048, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1396 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1381189, + "ts": 1655274547806.888, "dur": 14.399, + "args": { + "External id": 4054390,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "float", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[1, 2048], [1, 2048], []], "Ev Idx": 1397 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 1336756, "tid": 1381189, + "ts": 1655274547826.553, "dur": 4.283, + "args": { + "External id": 4054391,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1]], "Input Dims": [[1, 2048], [2048]], "Ev Idx": 1398 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274547829.660, "dur": 1.042, + "args": { + "External id": 4054392,"Record function id": 0, "Concrete Inputs": ["", "[2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[1, 2048], []], "Ev Idx": 1399 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1381189, + "ts": 1655274547836.644, "dur": 3.615, + "args": { + "External id": 4054393,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 1400 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274547837.307, "dur": 2.834, + "args": { + "External id": 4054394,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 1401 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1381189, + "ts": 1655274547841.961, "dur": 3.149, + "args": { + "External id": 4054395,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 1402 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274547844.460, "dur": 0.552, + "args": { + "External id": 4054396,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 1403 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336756, "tid": 1381189, + "ts": 1655274547869.633, "dur": 15.225, + "args": { + "External id": 4054397,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[8388608, 2048, 1], [8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], [16, 4096, 2048], []], "Ev Idx": 1404 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274547895.435, "dur": 6.956, + "args": { + "External id": 4054398,"Record function id": 0, "Ev Idx": 1405 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274547897.185, "dur": 4.522, + "args": { + "External id": 4054399,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 1406 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274547898.744, "dur": 2.162, + "args": { + "External id": 4054400,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 1407 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274547899.529, "dur": 1.285, + "args": { + "External id": 4054401,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 1408 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: UnsafeViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274547905.961, "dur": 8.034, + "args": { + "External id": 4054402,"Record function id": 0, "Sequence number": 40618432, "Fwd thread id": 1, "Ev Idx": 1409 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274547906.739, "dur": 5.043, + "args": { + "External id": 4054403,"Sequence number": 40618432, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 1410 + } + }, + { + "ph": "f", "id": 148, "pid": 1336756, "tid": 1381189, "ts": 1655274547906.739, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1381189, + "ts": 1655274547907.944, "dur": 3.651, + "args": { + "External id": 4054404,"Record function id": 0, "Concrete Inputs": ["", "[65536, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 1411 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274547910.419, "dur": 1.022, + "args": { + "External id": 4054405,"Record function id": 0, "Concrete Inputs": ["", "[65536, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 1412 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: MmBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274547917.412, "dur": 176.163, + "args": { + "External id": 4054406,"Record function id": 0, "Sequence number": 40618431, "Fwd thread id": 1, "Ev Idx": 1413 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274547918.282, "dur": 167.405, + "args": { + "External id": 4054407,"Sequence number": 40618431, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[65536, 2048]], "Ev Idx": 1414 + } + }, + { + "ph": "f", "id": 149, "pid": 1336756, "tid": 1381189, "ts": 1655274547918.282, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1381189, + "ts": 1655274547920.483, "dur": 3.701, + "args": { + "External id": 4054408,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[65536, 2048]], "Ev Idx": 1415 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1381189, + "ts": 1655274547921.576, "dur": 2.133, + "args": { + "External id": 4054409,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[65536, 2048], [], []], "Ev Idx": 1416 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274547922.891, "dur": 0.629, + "args": { + "External id": 4054410,"Record function id": 0, "Concrete Inputs": ["", "[2048, 65536]", "[1, 2048]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[65536, 2048], [], [], []], "Ev Idx": 1417 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655274547925.386, "dur": 52.182, + "args": { + "External id": 4054411,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048]], "Ev Idx": 1418 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1381189, + "ts": 1655274547980.890, "dur": 49.577, + "args": { + "External id": 4054412,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 1419 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1381189, + "ts": 1655274547981.537, "dur": 47.897, + "args": { + "External id": 4054413,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[2048, 2048], [], []], "Ev Idx": 1420 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274548026.572, "dur": 2.387, + "args": { + "External id": 4054414,"Record function id": 0, "Concrete Inputs": ["", "[2048, 2048]", "[1, 2048]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[2048, 2048], [], [], []], "Ev Idx": 1421 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1381189, + "ts": 1655274548032.463, "dur": 2.556, + "args": { + "External id": 4054415,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 2048]], "Input Dims": [[2048, 2048]], "Ev Idx": 1422 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1381189, + "ts": 1655274548033.339, "dur": 1.225, + "args": { + "External id": 4054416,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 2048], [], []], "Input Dims": [[2048, 2048], [], []], "Ev Idx": 1423 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274548034.160, "dur": 0.340, + "args": { + "External id": 4054417,"Record function id": 0, "Concrete Inputs": ["", "[2048, 2048]", "[2048, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 2048], [], [], []], "Input Dims": [[2048, 2048], [], [], []], "Ev Idx": 1424 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655274548037.785, "dur": 47.168, + "args": { + "External id": 4054418,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048]], "Ev Idx": 1425 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274548100.861, "dur": 10.077, + "args": { + "External id": 4054419,"Record function id": 0, "Sequence number": 40618430, "Fwd thread id": 1, "Ev Idx": 1426 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274548101.805, "dur": 7.690, + "args": { + "External id": 4054420,"Sequence number": 40618430, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[65536, 2048]], "Ev Idx": 1427 + } + }, + { + "ph": "f", "id": 150, "pid": 1336756, "tid": 1381189, "ts": 1655274548101.805, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1381189, + "ts": 1655274548103.178, "dur": 6.156, + "args": { + "External id": 4054421,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 1428 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274548105.801, "dur": 3.435, + "args": { + "External id": 4054422,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 1429 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: TBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274548114.128, "dur": 8.731, + "args": { + "External id": 4054423,"Record function id": 0, "Sequence number": 40618429, "Fwd thread id": 1, "Ev Idx": 1430 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274548114.992, "dur": 6.376, + "args": { + "External id": 4054424,"Sequence number": 40618429, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 2048]], "Input Dims": [[2048, 2048]], "Ev Idx": 1431 + } + }, + { + "ph": "f", "id": 151, "pid": 1336756, "tid": 1381189, "ts": 1655274548114.992, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1381189, + "ts": 1655274548115.866, "dur": 5.284, + "args": { + "External id": 4054425,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 2048]], "Input Dims": [[2048, 2048]], "Ev Idx": 1432 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1381189, + "ts": 1655274548116.893, "dur": 3.730, + "args": { + "External id": 4054426,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 2048], [], []], "Input Dims": [[2048, 2048], [], []], "Ev Idx": 1433 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274548119.987, "dur": 0.511, + "args": { + "External id": 4054427,"Record function id": 0, "Concrete Inputs": ["", "[2048, 2048]", "[2048, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 2048], [], [], []], "Input Dims": [[2048, 2048], [], [], []], "Ev Idx": 1434 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274548127.116, "dur": 5.043, + "args": { + "External id": 4054428,"Record function id": 0, "Ev Idx": 1435 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274548128.278, "dur": 3.388, + "args": { + "External id": 4054429,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 1436 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274548129.381, "dur": 2.025, + "args": { + "External id": 4054430,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 1437 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274548130.031, "dur": 1.277, + "args": { + "External id": 4054431,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 1438 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274548135.120, "dur": 5.509, + "args": { + "External id": 4054432,"Record function id": 0, "Sequence number": 40618428, "Fwd thread id": 1, "Ev Idx": 1439 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274548135.796, "dur": 2.930, + "args": { + "External id": 4054433,"Sequence number": 40618428, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 1440 + } + }, + { + "ph": "f", "id": 152, "pid": 1336756, "tid": 1381189, "ts": 1655274548135.796, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1381189, + "ts": 1655274548136.786, "dur": 1.807, + "args": { + "External id": 4054434,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 32, 64]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 1441 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274548137.300, "dur": 1.164, + "args": { + "External id": 4054435,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 32, 64]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 1442 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: FlashAttnFuncBackward", "pid": 1336756, "tid": 1381189, + "ts": 1655274548144.412, "dur": 302.997, + "args": { + "External id": 4054436,"Record function id": 0, "Sequence number": 40618427, "Fwd thread id": 1, "Ev Idx": 1443 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "FlashAttnFuncBackward", "pid": 1336756, "tid": 1381189, + "ts": 1655274548147.426, "dur": 264.924, + "args": { + "External id": 4054437,"Sequence number": 40618427, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 64, 1]], "Input Dims": [[16, 4096, 32, 64]], "Ev Idx": 1444 + } + }, + { + "ph": "f", "id": 153, "pid": 1336756, "tid": 1381189, "ts": 1655274548147.426, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336756, "tid": 1381189, + "ts": 1655274548162.739, "dur": 8.931, + "args": { + "External id": 4054438,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[8388608, 2048, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [], [], [], [], []], "Ev Idx": 1445 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274548166.965, "dur": 4.254, + "args": { + "External id": 4054439,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "[8388608, 2048, 64, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1446 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336756, "tid": 1381189, + "ts": 1655274548173.524, "dur": 5.341, + "args": { + "External id": 4054440,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[8388608, 2048, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [], [], [], [], []], "Ev Idx": 1447 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274548176.431, "dur": 2.240, + "args": { + "External id": 4054441,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "[8388608, 2048, 64, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1448 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336756, "tid": 1381189, + "ts": 1655274548180.251, "dur": 2.312, + "args": { + "External id": 4054442,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[8388608, 2048, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [], [], [], [], []], "Ev Idx": 1449 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274548180.898, "dur": 1.481, + "args": { + "External id": 4054443,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "[8388608, 2048, 64, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1450 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 1336756, "tid": 1381189, + "ts": 1655274548206.957, "dur": 180.960, + "args": { + "External id": 4054444,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.125", "True", "-1", "-1", "0.", "", "False", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar", "long int"], "Input Strides": [[8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [131072, 4096, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 32, 4096], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 1451 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655274548286.971, "dur": 4.386, + "args": { + "External id": 4054445,"Record function id": 0, "Concrete Inputs": ["[16, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1452 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655274548295.252, "dur": 3.995, + "args": { + "External id": 4054446,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1453 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::alias", "pid": 1336756, "tid": 1381189, + "ts": 1655274548400.238, "dur": 3.338, + "args": { + "External id": 4054447,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 64, 1]], "Input Dims": [[16, 4096, 32, 64]], "Ev Idx": 1454 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::alias", "pid": 1336756, "tid": 1381189, + "ts": 1655274548406.724, "dur": 0.805, + "args": { + "External id": 4054448,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 64, 1]], "Input Dims": [[16, 4096, 32, 64]], "Ev Idx": 1455 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::alias", "pid": 1336756, "tid": 1381189, + "ts": 1655274548409.365, "dur": 0.714, + "args": { + "External id": 4054449,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 64, 1]], "Input Dims": [[16, 4096, 32, 64]], "Ev Idx": 1456 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RotaryEmbeddingFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1655274548457.076, "dur": 228.520, + "args": { + "External id": 4054450,"Record function id": 0, "Sequence number": 40618426, "Fwd thread id": 1, "Ev Idx": 1457 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1655274548458.688, "dur": 220.422, + "args": { + "External id": 4054451,"Sequence number": 40618426, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 64, 1]], "Input Dims": [[16, 4096, 32, 64]], "Ev Idx": 1458 + } + }, + { + "ph": "f", "id": 154, "pid": 1336756, "tid": 1381189, "ts": 1655274548458.688, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 1336756, "tid": 1381189, + "ts": 1655274548479.749, "dur": 55.687, + "args": { + "External id": 4054452,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", ""], "Input Strides": [[8388608, 2048, 64, 1], []], "Input Dims": [[16, 4096, 32, 64], []], "Ev Idx": 1459 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274548484.885, "dur": 3.745, + "args": { + "External id": 4054453,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "[8388608, 2048, 64, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1460 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1381189, + "ts": 1655274548490.117, "dur": 44.618, + "args": { + "External id": 4054454,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [8388608, 2048, 64, 1], []], "Input Dims": [[16, 4096, 32, 64], [16, 4096, 32, 64], []], "Ev Idx": 1461 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336756, "tid": 1381189, + "ts": 1655274548544.331, "dur": 4.325, + "args": { + "External id": 4054455,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[8388608, 2048, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [], [], [], [], []], "Ev Idx": 1462 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274548545.997, "dur": 2.282, + "args": { + "External id": 4054456,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "[8388608, 2048, 64, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1463 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RotaryEmbeddingFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1655274548692.201, "dur": 147.949, + "args": { + "External id": 4054457,"Record function id": 0, "Sequence number": 40618425, "Fwd thread id": 1, "Ev Idx": 1464 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1655274548695.389, "dur": 139.093, + "args": { + "External id": 4054458,"Sequence number": 40618425, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 64, 1]], "Input Dims": [[16, 4096, 32, 64]], "Ev Idx": 1465 + } + }, + { + "ph": "f", "id": 155, "pid": 1336756, "tid": 1381189, "ts": 1655274548695.389, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 1336756, "tid": 1381189, + "ts": 1655274548706.967, "dur": 31.338, + "args": { + "External id": 4054459,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", ""], "Input Strides": [[8388608, 2048, 64, 1], []], "Input Dims": [[16, 4096, 32, 64], []], "Ev Idx": 1466 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274548708.846, "dur": 2.595, + "args": { + "External id": 4054460,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "[8388608, 2048, 64, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1467 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1381189, + "ts": 1655274548712.463, "dur": 25.317, + "args": { + "External id": 4054461,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [8388608, 2048, 64, 1], []], "Input Dims": [[16, 4096, 32, 64], [16, 4096, 32, 64], []], "Ev Idx": 1468 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336756, "tid": 1381189, + "ts": 1655274548744.925, "dur": 4.056, + "args": { + "External id": 4054462,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[8388608, 2048, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [], [], [], [], []], "Ev Idx": 1469 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274548746.168, "dur": 2.501, + "args": { + "External id": 4054463,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "[8388608, 2048, 64, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1470 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274548846.832, "dur": 15.319, + "args": { + "External id": 4054464,"Record function id": 0, "Sequence number": 40618424, "Fwd thread id": 1, "Ev Idx": 1471 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274548848.166, "dur": 11.875, + "args": { + "External id": 4054465,"Sequence number": 40618424, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 64, 1]], "Input Dims": [[16, 4096, 32, 64]], "Ev Idx": 1472 + } + }, + { + "ph": "f", "id": 156, "pid": 1336756, "tid": 1381189, "ts": 1655274548848.166, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1381189, + "ts": 1655274548852.756, "dur": 7.043, + "args": { + "External id": 4054466,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 64, 1], []], "Input Dims": [[16, 4096, 32, 64], []], "Ev Idx": 1473 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274548853.915, "dur": 5.675, + "args": { + "External id": 4054467,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 64, 1], []], "Input Dims": [[16, 4096, 32, 64], []], "Ev Idx": 1474 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274548865.677, "dur": 5.357, + "args": { + "External id": 4054468,"Record function id": 0, "Sequence number": 40618423, "Fwd thread id": 1, "Ev Idx": 1475 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274548866.471, "dur": 2.953, + "args": { + "External id": 4054469,"Sequence number": 40618423, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 64, 1]], "Input Dims": [[16, 4096, 32, 64]], "Ev Idx": 1476 + } + }, + { + "ph": "f", "id": 157, "pid": 1336756, "tid": 1381189, "ts": 1655274548866.471, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1381189, + "ts": 1655274548867.487, "dur": 1.808, + "args": { + "External id": 4054470,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 64, 1], []], "Input Dims": [[16, 4096, 32, 64], []], "Ev Idx": 1477 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274548868.227, "dur": 0.940, + "args": { + "External id": 4054471,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 64, 1], []], "Input Dims": [[16, 4096, 32, 64], []], "Ev Idx": 1478 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274548874.231, "dur": 8.672, + "args": { + "External id": 4054472,"Record function id": 0, "Sequence number": 40618422, "Fwd thread id": 1, "Ev Idx": 1479 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274548875.060, "dur": 5.810, + "args": { + "External id": 4054473,"Sequence number": 40618422, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 64, 1]], "Input Dims": [[16, 4096, 32, 64]], "Ev Idx": 1480 + } + }, + { + "ph": "f", "id": 158, "pid": 1336756, "tid": 1381189, "ts": 1655274548875.060, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1381189, + "ts": 1655274548879.430, "dur": 1.302, + "args": { + "External id": 4054474,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 64, 1], []], "Input Dims": [[16, 4096, 32, 64], []], "Ev Idx": 1481 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274548879.851, "dur": 0.754, + "args": { + "External id": 4054475,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 64, 1], []], "Input Dims": [[16, 4096, 32, 64], []], "Ev Idx": 1482 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: UnsafeViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274548886.046, "dur": 5.002, + "args": { + "External id": 4054476,"Record function id": 0, "Sequence number": 40618421, "Fwd thread id": 1, "Ev Idx": 1483 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274548886.833, "dur": 2.418, + "args": { + "External id": 4054477,"Sequence number": 40618421, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 1484 + } + }, + { + "ph": "f", "id": 159, "pid": 1336756, "tid": 1381189, "ts": 1655274548886.833, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1381189, + "ts": 1655274548887.657, "dur": 1.456, + "args": { + "External id": 4054478,"Record function id": 0, "Concrete Inputs": ["", "[65536, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 1485 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274548888.219, "dur": 0.806, + "args": { + "External id": 4054479,"Record function id": 0, "Concrete Inputs": ["", "[65536, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 1486 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: MmBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274548894.348, "dur": 204.267, + "args": { + "External id": 4054480,"Record function id": 0, "Sequence number": 40618420, "Fwd thread id": 1, "Ev Idx": 1487 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274548895.319, "dur": 194.567, + "args": { + "External id": 4054481,"Sequence number": 40618420, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[65536, 2048]], "Ev Idx": 1488 + } + }, + { + "ph": "f", "id": 160, "pid": 1336756, "tid": 1381189, "ts": 1655274548895.319, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1381189, + "ts": 1655274548898.624, "dur": 10.349, + "args": { + "External id": 4054482,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[65536, 2048]], "Ev Idx": 1489 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1381189, + "ts": 1655274548902.608, "dur": 5.684, + "args": { + "External id": 4054483,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[65536, 2048], [], []], "Ev Idx": 1490 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274548906.439, "dur": 1.600, + "args": { + "External id": 4054484,"Record function id": 0, "Concrete Inputs": ["", "[2048, 65536]", "[1, 2048]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[65536, 2048], [], [], []], "Ev Idx": 1491 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655274548910.437, "dur": 64.348, + "args": { + "External id": 4054485,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048]], "Ev Idx": 1492 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1381189, + "ts": 1655274548975.810, "dur": 3.836, + "args": { + "External id": 4054486,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 1493 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1381189, + "ts": 1655274548976.565, "dur": 2.330, + "args": { + "External id": 4054487,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[2048, 2048], [], []], "Ev Idx": 1494 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274548977.789, "dur": 0.926, + "args": { + "External id": 4054488,"Record function id": 0, "Concrete Inputs": ["", "[2048, 2048]", "[1, 2048]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[2048, 2048], [], [], []], "Ev Idx": 1495 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1381189, + "ts": 1655274548981.159, "dur": 51.194, + "args": { + "External id": 4054489,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 2048]], "Input Dims": [[2048, 2048]], "Ev Idx": 1496 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1381189, + "ts": 1655274549028.525, "dur": 2.919, + "args": { + "External id": 4054490,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 2048], [], []], "Input Dims": [[2048, 2048], [], []], "Ev Idx": 1497 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274549030.299, "dur": 0.873, + "args": { + "External id": 4054491,"Record function id": 0, "Concrete Inputs": ["", "[2048, 2048]", "[2048, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 2048], [], [], []], "Input Dims": [[2048, 2048], [], [], []], "Ev Idx": 1498 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655274549033.312, "dur": 55.187, + "args": { + "External id": 4054492,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048]], "Ev Idx": 1499 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274549106.848, "dur": 9.221, + "args": { + "External id": 4054493,"Record function id": 0, "Sequence number": 40618419, "Fwd thread id": 1, "Ev Idx": 1500 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274549108.082, "dur": 6.159, + "args": { + "External id": 4054494,"Sequence number": 40618419, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[65536, 2048]], "Ev Idx": 1501 + } + }, + { + "ph": "f", "id": 161, "pid": 1336756, "tid": 1381189, "ts": 1655274549108.082, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1381189, + "ts": 1655274549111.777, "dur": 2.321, + "args": { + "External id": 4054495,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 1502 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274549112.545, "dur": 1.449, + "args": { + "External id": 4054496,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 1503 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: TBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274549119.207, "dur": 9.217, + "args": { + "External id": 4054497,"Record function id": 0, "Sequence number": 40618418, "Fwd thread id": 1, "Ev Idx": 1504 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274549120.262, "dur": 6.573, + "args": { + "External id": 4054498,"Sequence number": 40618418, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 2048]], "Input Dims": [[2048, 2048]], "Ev Idx": 1505 + } + }, + { + "ph": "f", "id": 162, "pid": 1336756, "tid": 1381189, "ts": 1655274549120.262, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1381189, + "ts": 1655274549123.780, "dur": 2.839, + "args": { + "External id": 4054499,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 2048]], "Input Dims": [[2048, 2048]], "Ev Idx": 1506 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1381189, + "ts": 1655274549124.634, "dur": 1.534, + "args": { + "External id": 4054500,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 2048], [], []], "Input Dims": [[2048, 2048], [], []], "Ev Idx": 1507 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274549125.602, "dur": 0.458, + "args": { + "External id": 4054501,"Record function id": 0, "Concrete Inputs": ["", "[2048, 2048]", "[2048, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 2048], [], [], []], "Input Dims": [[2048, 2048], [], [], []], "Ev Idx": 1508 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274549134.440, "dur": 8.657, + "args": { + "External id": 4054502,"Record function id": 0, "Ev Idx": 1509 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274549135.746, "dur": 6.592, + "args": { + "External id": 4054503,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 1510 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274549138.413, "dur": 3.549, + "args": { + "External id": 4054504,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 1511 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274549139.378, "dur": 2.481, + "args": { + "External id": 4054505,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 1512 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: UnsafeViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274549146.617, "dur": 9.444, + "args": { + "External id": 4054506,"Record function id": 0, "Sequence number": 40618417, "Fwd thread id": 1, "Ev Idx": 1513 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274549149.343, "dur": 4.901, + "args": { + "External id": 4054507,"Sequence number": 40618417, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 1514 + } + }, + { + "ph": "f", "id": 163, "pid": 1336756, "tid": 1381189, "ts": 1655274549149.343, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1381189, + "ts": 1655274549150.267, "dur": 3.819, + "args": { + "External id": 4054508,"Record function id": 0, "Concrete Inputs": ["", "[65536, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 1515 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274549153.198, "dur": 0.737, + "args": { + "External id": 4054509,"Record function id": 0, "Concrete Inputs": ["", "[65536, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 1516 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: MmBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274549159.259, "dur": 90.783, + "args": { + "External id": 4054510,"Record function id": 0, "Sequence number": 40618416, "Fwd thread id": 1, "Ev Idx": 1517 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274549159.934, "dur": 85.101, + "args": { + "External id": 4054511,"Sequence number": 40618416, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[65536, 2048]], "Ev Idx": 1518 + } + }, + { + "ph": "f", "id": 164, "pid": 1336756, "tid": 1381189, "ts": 1655274549159.934, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1381189, + "ts": 1655274549161.725, "dur": 2.662, + "args": { + "External id": 4054512,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[65536, 2048]], "Ev Idx": 1519 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1381189, + "ts": 1655274549162.627, "dur": 1.361, + "args": { + "External id": 4054513,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[65536, 2048], [], []], "Ev Idx": 1520 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274549163.375, "dur": 0.503, + "args": { + "External id": 4054514,"Record function id": 0, "Concrete Inputs": ["", "[2048, 65536]", "[1, 2048]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[65536, 2048], [], [], []], "Ev Idx": 1521 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655274549165.098, "dur": 28.234, + "args": { + "External id": 4054515,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048]], "Ev Idx": 1522 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1381189, + "ts": 1655274549196.510, "dur": 3.009, + "args": { + "External id": 4054516,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 1523 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1381189, + "ts": 1655274549197.074, "dur": 1.938, + "args": { + "External id": 4054517,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[2048, 2048], [], []], "Ev Idx": 1524 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274549197.842, "dur": 1.048, + "args": { + "External id": 4054518,"Record function id": 0, "Concrete Inputs": ["", "[2048, 2048]", "[1, 2048]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[2048, 2048], [], [], []], "Ev Idx": 1525 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1381189, + "ts": 1655274549200.651, "dur": 6.618, + "args": { + "External id": 4054519,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 2048]], "Input Dims": [[2048, 2048]], "Ev Idx": 1526 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1381189, + "ts": 1655274549201.390, "dur": 5.445, + "args": { + "External id": 4054520,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 2048], [], []], "Input Dims": [[2048, 2048], [], []], "Ev Idx": 1527 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274549204.284, "dur": 2.478, + "args": { + "External id": 4054521,"Record function id": 0, "Concrete Inputs": ["", "[2048, 2048]", "[2048, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 2048], [], [], []], "Input Dims": [[2048, 2048], [], [], []], "Ev Idx": 1528 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655274549209.783, "dur": 34.362, + "args": { + "External id": 4054522,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048]], "Ev Idx": 1529 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274549256.857, "dur": 36.597, + "args": { + "External id": 4054523,"Record function id": 0, "Sequence number": 40618415, "Fwd thread id": 1, "Ev Idx": 1530 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274549257.838, "dur": 7.799, + "args": { + "External id": 4054524,"Sequence number": 40618415, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[65536, 2048]], "Ev Idx": 1531 + } + }, + { + "ph": "f", "id": 165, "pid": 1336756, "tid": 1381189, "ts": 1655274549257.838, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1381189, + "ts": 1655274549259.239, "dur": 6.249, + "args": { + "External id": 4054525,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 1532 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274549264.145, "dur": 1.234, + "args": { + "External id": 4054526,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 1533 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add", "pid": 1336756, "tid": 1381189, + "ts": 1655274549268.734, "dur": 22.580, + "args": { + "External id": 4054527,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[8388608, 2048, 1], [8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], [16, 4096, 2048], []], "Ev Idx": 1534 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: TBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274549297.025, "dur": 30.206, + "args": { + "External id": 4054528,"Record function id": 0, "Sequence number": 40618414, "Fwd thread id": 1, "Ev Idx": 1535 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274549317.601, "dur": 7.990, + "args": { + "External id": 4054529,"Sequence number": 40618414, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 2048]], "Input Dims": [[2048, 2048]], "Ev Idx": 1536 + } + }, + { + "ph": "f", "id": 166, "pid": 1336756, "tid": 1381189, "ts": 1655274549317.601, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1381189, + "ts": 1655274549320.667, "dur": 4.729, + "args": { + "External id": 4054530,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 2048]], "Input Dims": [[2048, 2048]], "Ev Idx": 1537 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1381189, + "ts": 1655274549321.334, "dur": 3.572, + "args": { + "External id": 4054531,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 2048], [], []], "Input Dims": [[2048, 2048], [], []], "Ev Idx": 1538 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274549324.179, "dur": 0.582, + "args": { + "External id": 4054532,"Record function id": 0, "Concrete Inputs": ["", "[2048, 2048]", "[2048, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 2048], [], [], []], "Input Dims": [[2048, 2048], [], [], []], "Ev Idx": 1539 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274549331.075, "dur": 4.239, + "args": { + "External id": 4054533,"Record function id": 0, "Ev Idx": 1540 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274549332.087, "dur": 2.752, + "args": { + "External id": 4054534,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 1541 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274549332.987, "dur": 1.580, + "args": { + "External id": 4054535,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 1542 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274549333.460, "dur": 0.990, + "args": { + "External id": 4054536,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 1543 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: UnsafeViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274549338.298, "dur": 7.720, + "args": { + "External id": 4054537,"Record function id": 0, "Sequence number": 40618413, "Fwd thread id": 1, "Ev Idx": 1544 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274549339.316, "dur": 4.873, + "args": { + "External id": 4054538,"Sequence number": 40618413, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 1545 + } + }, + { + "ph": "f", "id": 167, "pid": 1336756, "tid": 1381189, "ts": 1655274549339.316, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1381189, + "ts": 1655274549340.300, "dur": 3.732, + "args": { + "External id": 4054539,"Record function id": 0, "Concrete Inputs": ["", "[65536, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 1546 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274549343.104, "dur": 0.785, + "args": { + "External id": 4054540,"Record function id": 0, "Concrete Inputs": ["", "[65536, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 1547 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: MmBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274549348.993, "dur": 111.323, + "args": { + "External id": 4054541,"Record function id": 0, "Sequence number": 40618412, "Fwd thread id": 1, "Ev Idx": 1548 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274549349.658, "dur": 102.271, + "args": { + "External id": 4054542,"Sequence number": 40618412, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[65536, 2048]], "Ev Idx": 1549 + } + }, + { + "ph": "f", "id": 168, "pid": 1336756, "tid": 1381189, "ts": 1655274549349.658, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1381189, + "ts": 1655274549351.418, "dur": 4.303, + "args": { + "External id": 4054543,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[65536, 2048]], "Ev Idx": 1550 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1381189, + "ts": 1655274549351.981, "dur": 3.334, + "args": { + "External id": 4054544,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[65536, 2048], [], []], "Ev Idx": 1551 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274549354.817, "dur": 0.378, + "args": { + "External id": 4054545,"Record function id": 0, "Concrete Inputs": ["", "[2048, 65536]", "[1, 2048]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[65536, 2048], [], [], []], "Ev Idx": 1552 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655274549356.302, "dur": 27.930, + "args": { + "External id": 4054546,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048]], "Ev Idx": 1553 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1381189, + "ts": 1655274549386.987, "dur": 2.511, + "args": { + "External id": 4054547,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 1554 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1381189, + "ts": 1655274549387.549, "dur": 1.434, + "args": { + "External id": 4054548,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[2048, 2048], [], []], "Ev Idx": 1555 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274549388.293, "dur": 0.533, + "args": { + "External id": 4054549,"Record function id": 0, "Concrete Inputs": ["", "[2048, 2048]", "[1, 2048]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[2048, 2048], [], [], []], "Ev Idx": 1556 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1381189, + "ts": 1655274549390.625, "dur": 2.303, + "args": { + "External id": 4054550,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 2048]], "Input Dims": [[2048, 2048]], "Ev Idx": 1557 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1381189, + "ts": 1655274549391.500, "dur": 1.012, + "args": { + "External id": 4054551,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 2048], [], []], "Input Dims": [[2048, 2048], [], []], "Ev Idx": 1558 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274549392.082, "dur": 0.361, + "args": { + "External id": 4054552,"Record function id": 0, "Concrete Inputs": ["", "[2048, 2048]", "[2048, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 2048], [], [], []], "Input Dims": [[2048, 2048], [], [], []], "Ev Idx": 1559 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655274549395.100, "dur": 55.473, + "args": { + "External id": 4054553,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048]], "Ev Idx": 1560 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: ViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274549467.288, "dur": 28.156, + "args": { + "External id": 4054554,"Record function id": 0, "Sequence number": 40618411, "Fwd thread id": 1, "Ev Idx": 1561 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274549468.469, "dur": 5.740, + "args": { + "External id": 4054555,"Sequence number": 40618411, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[65536, 2048]], "Ev Idx": 1562 + } + }, + { + "ph": "f", "id": 169, "pid": 1336756, "tid": 1381189, "ts": 1655274549468.469, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1381189, + "ts": 1655274549471.880, "dur": 2.155, + "args": { + "External id": 4054556,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 1563 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274549472.424, "dur": 1.505, + "args": { + "External id": 4054557,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 1564 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336756, "tid": 1381189, + "ts": 1655274549476.692, "dur": 16.632, + "args": { + "External id": 4054558,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[8388608, 2048, 1], [8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], [16, 4096, 2048], []], "Ev Idx": 1565 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: TBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274549498.980, "dur": 8.893, + "args": { + "External id": 4054559,"Record function id": 0, "Sequence number": 40618410, "Fwd thread id": 1, "Ev Idx": 1566 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1655274549499.973, "dur": 6.046, + "args": { + "External id": 4054560,"Sequence number": 40618410, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 2048]], "Input Dims": [[2048, 2048]], "Ev Idx": 1567 + } + }, + { + "ph": "f", "id": 170, "pid": 1336756, "tid": 1381189, "ts": 1655274549499.973, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1381189, + "ts": 1655274549500.766, "dur": 5.060, + "args": { + "External id": 4054561,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1, 2048]], "Input Dims": [[2048, 2048]], "Ev Idx": 1568 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1381189, + "ts": 1655274549501.661, "dur": 3.679, + "args": { + "External id": 4054562,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[1, 2048], [], []], "Input Dims": [[2048, 2048], [], []], "Ev Idx": 1569 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274549504.707, "dur": 0.521, + "args": { + "External id": 4054563,"Record function id": 0, "Concrete Inputs": ["", "[2048, 2048]", "[2048, 1]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 2048], [], [], []], "Input Dims": [[2048, 2048], [], [], []], "Ev Idx": 1570 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274549511.723, "dur": 5.164, + "args": { + "External id": 4054564,"Record function id": 0, "Ev Idx": 1571 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274549512.901, "dur": 3.462, + "args": { + "External id": 4054565,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 1572 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274549513.950, "dur": 2.118, + "args": { + "External id": 4054566,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 1573 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274549514.407, "dur": 1.568, + "args": { + "External id": 4054567,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 1574 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: LayerNormFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1655274549520.727, "dur": 350.113, + "args": { + "External id": 4054568,"Record function id": 0, "Sequence number": 40618409, "Fwd thread id": 1, "Ev Idx": 1575 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1655274549524.007, "dur": 316.208, + "args": { + "External id": 4054569,"Sequence number": 40618409, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 1576 + } + }, + { + "ph": "f", "id": 171, "pid": 1336756, "tid": 1381189, "ts": 1655274549524.007, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1381189, + "ts": 1655274549558.102, "dur": 1.871, + "args": { + "External id": 4054570,"Record function id": 0, "Concrete Inputs": ["", "[-1, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 1577 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274549558.697, "dur": 1.112, + "args": { + "External id": 4054571,"Record function id": 0, "Concrete Inputs": ["", "[-1, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 1578 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655274549576.392, "dur": 6.264, + "args": { + "External id": 4054572,"Record function id": 0, "Concrete Inputs": ["[65536, 2048]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1579 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655274549592.094, "dur": 1.901, + "args": { + "External id": 4054573,"Record function id": 0, "Concrete Inputs": ["[132, 2048]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1580 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274549740.311, "dur": 1.675, + "args": { + "External id": 4054574,"Record function id": 0, "Concrete Inputs": ["", "[1, -1, 2048]"], "Input type": ["float", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[132, 2048], []], "Ev Idx": 1581 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 1336756, "tid": 1381189, + "ts": 1655274549745.927, "dur": 35.706, + "args": { + "External id": 4054575,"Record function id": 0, "Concrete Inputs": ["", "[1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", ""], "Input Strides": [[270336, 2048, 1], [], [], []], "Input Dims": [[1, 132, 2048], [], [], []], "Ev Idx": 1582 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274549758.169, "dur": 0.798, + "args": { + "External id": 4054576,"Record function id": 0, "Concrete Inputs": ["", "[1, 1, 2048]", "[2048, 0, 1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[1, 2048], [], [], []], "Ev Idx": 1583 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1381189, + "ts": 1655274549787.330, "dur": 30.585, + "args": { + "External id": 4054577,"Record function id": 0, "Concrete Inputs": ["", "", "15", "False", "False", ""], "Input type": ["float", "", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[2048, 1], [], [], [], [], []], "Input Dims": [[1, 2048], [], [], [], [], []], "Ev Idx": 1584 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336756, "tid": 1381189, + "ts": 1655274549789.046, "dur": 28.591, + "args": { + "External id": 4054578,"Record function id": 0, "Concrete Inputs": ["", "15", "", "", "", "False", ""], "Input type": ["float", "Scalar", "", "", "", "Scalar", ""], "Input Strides": [[2048, 1], [], [], [], [], [], []], "Input Dims": [[1, 2048], [], [], [], [], [], []], "Ev Idx": 1585 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274549792.674, "dur": 4.466, + "args": { + "External id": 4054579,"Record function id": 0, "Concrete Inputs": ["[1, 2048]", "[2048, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1586 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1381189, + "ts": 1655274549800.675, "dur": 16.267, + "args": { + "External id": 4054580,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "float", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[1, 2048], [1, 2048], []], "Ev Idx": 1587 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 1336756, "tid": 1381189, + "ts": 1655274549822.209, "dur": 4.284, + "args": { + "External id": 4054581,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1]], "Input Dims": [[1, 2048], [2048]], "Ev Idx": 1588 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274549825.133, "dur": 1.264, + "args": { + "External id": 4054582,"Record function id": 0, "Concrete Inputs": ["", "[2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[1, 2048], []], "Ev Idx": 1589 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1381189, + "ts": 1655274549832.071, "dur": 1.937, + "args": { + "External id": 4054583,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 1590 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274549833.005, "dur": 0.911, + "args": { + "External id": 4054584,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 1591 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336756, "tid": 1381189, + "ts": 1655274549852.069, "dur": 14.505, + "args": { + "External id": 4054585,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[8388608, 2048, 1], [8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], [16, 4096, 2048], []], "Ev Idx": 1592 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274549879.940, "dur": 9.074, + "args": { + "External id": 4054586,"Record function id": 0, "Ev Idx": 1593 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274549881.645, "dur": 6.757, + "args": { + "External id": 4054587,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 1594 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274549883.043, "dur": 4.325, + "args": { + "External id": 4054588,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 1595 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274549885.937, "dur": 1.324, + "args": { + "External id": 4054589,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 1596 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: CompiledFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1655274549892.934, "dur": 2575.980, + "args": { + "External id": 4054590,"Record function id": 0, "Ev Idx": 1597 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.27)", "pid": 1336756, "tid": 1381189, + "ts": 1655274549922.665, "dur": 882.977, + "args": { + "External id": 4054591,"Record function id": 0, "Ev Idx": 1598 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::backward_prefetch for model.layers.26", "pid": 1336756, "tid": 1381189, + "ts": 1655274549947.232, "dur": 850.281, + "args": { + "External id": 4054592,"Record function id": 0, "Ev Idx": 1599 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.26)", "pid": 1336756, "tid": 1381189, + "ts": 1655274549958.829, "dur": 824.548, + "args": { + "External id": 4054593,"Record function id": 0, "Ev Idx": 1600 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655274550071.145, "dur": 7.468, + "args": { + "External id": 4054594,"Record function id": 0, "Concrete Inputs": ["[6423040]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1601 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336756, "tid": 1381189, + "ts": 1655274550095.623, "dur": 35.198, + "args": { + "External id": 4054595,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 1602 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274550101.256, "dur": 3.158, + "args": { + "External id": 4054596,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 1603 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274550106.024, "dur": 0.676, + "args": { + "External id": 4054597,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 1604 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274550110.682, "dur": 0.484, + "args": { + "External id": 4054598,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 1605 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274550112.042, "dur": 0.387, + "args": { + "External id": 4054599,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 1606 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274550113.419, "dur": 0.269, + "args": { + "External id": 4054600,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 1607 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274550117.378, "dur": 0.440, + "args": { + "External id": 4054601,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 1608 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274550118.313, "dur": 0.485, + "args": { + "External id": 4054602,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 1609 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274550119.507, "dur": 1.757, + "args": { + "External id": 4054603,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 1610 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274550123.995, "dur": 2.366, + "args": { + "External id": 4054604,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 1611 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336756, "tid": 1381189, + "ts": 1655274550144.048, "dur": 33.174, + "args": { + "External id": 4054605,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 1612 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 1336756, "tid": 1381189, + "ts": 1655274550211.717, "dur": 106.029, + "args": { + "External id": 4054606,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "6423040", "8", "3", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [], [], [], [], [], []], "Ev Idx": 1613 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655274550225.159, "dur": 5.607, + "args": { + "External id": 4054607,"Record function id": 0, "Concrete Inputs": ["[51384320]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1614 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 1336756, "tid": 1381189, + "ts": 1655274550236.197, "dur": 8.578, + "args": { + "External id": 4054608,"Record function id": 0, "Concrete Inputs": ["", "0", "19269120", "6423040"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 1615 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1381189, + "ts": 1655274550240.059, "dur": 4.335, + "args": { + "External id": 4054609,"Record function id": 0, "Concrete Inputs": ["", "0", "19269120", "25692160", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[51384320], [], [], [], []], "Ev Idx": 1616 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274550242.806, "dur": 0.489, + "args": { + "External id": 4054610,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "[1]", "19269120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 1617 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336756, "tid": 1381189, + "ts": 1655274550251.561, "dur": 27.272, + "args": { + "External id": 4054611,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 1618 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274550254.691, "dur": 0.421, + "args": { + "External id": 4054612,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "19269120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 1619 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274550256.008, "dur": 1.883, + "args": { + "External id": 4054613,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "19269376"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 1620 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274550258.519, "dur": 0.484, + "args": { + "External id": 4054614,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "19793664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 1621 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274550261.631, "dur": 0.309, + "args": { + "External id": 4054615,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "20317952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 1622 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274550263.874, "dur": 0.372, + "args": { + "External id": 4054616,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "20842240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 1623 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274550265.030, "dur": 2.289, + "args": { + "External id": 4054617,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "21366528"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 1624 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274550269.597, "dur": 0.399, + "args": { + "External id": 4054618,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "21366784"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 1625 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274550272.073, "dur": 0.365, + "args": { + "External id": 4054619,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "22808576"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 1626 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274550275.102, "dur": 0.285, + "args": { + "External id": 4054620,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "24250368"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 1627 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336756, "tid": 1381189, + "ts": 1655274550287.872, "dur": 21.820, + "args": { + "External id": 4054621,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 1628 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 1336756, "tid": 1381189, + "ts": 1655274550372.996, "dur": 310.760, + "args": { + "External id": 4054622,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[51384320], [6423040], [], [], []], "Ev Idx": 1629 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336756, "tid": 1381189, + "ts": 1655274550406.992, "dur": 271.400, + "args": { + "External id": 4054623,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 3, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "3", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 51384320, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[6423040], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 1630, "In msg nelems": 6423040 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 1336756, "tid": 1381189, + "ts": 1655274550434.093, "dur": 238.807, + "args": { + "External id": 4054624,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[6423040]], "Ev Idx": 1631 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336756, "tid": 1381189, + "ts": 1655274550709.003, "dur": 2.563, + "args": { + "External id": 4054625,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "3", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 1632, "In msg nelems": 0, "Rank": 3, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1655274550813.006, "dur": 1633.206, + "args": { + "External id": 4054626,"Sequence number": 40618408, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 1633 + } + }, + { + "ph": "f", "id": 172, "pid": 1336756, "tid": 1381189, "ts": 1655274550813.006, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655274550926.419, "dur": 151.977, + "args": { + "External id": 4054627,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [5632, 1], [5632, 1]], "Input Dims": [[65536, 2048], [2048, 5632], [65536, 5632]], "Ev Idx": 1634 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_add_mul_rsub_silu_0", "pid": 1336756, "tid": 1381189, + "ts": 1655274551128.920, "dur": 37.087, + "args": { + "External id": 4054628,"kernel_hash": "c2zszzsomz26dv2qwvmiurvgyrl5qxtyn6ocoqkdpzzhfzwqp5q6", "grid": "grid(369098752,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "369098752"], "kernel_file": "/tmp/torchinductor_cvm/2z/c2zszzsomz26dv2qwvmiurvgyrl5qxtyn6ocoqkdpzzhfzwqp5q6.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[5632, 1], [5632, 1], [5632, 1], [23068672, 5632, 1], [23068672, 5632, 1], [23068672, 5632, 1], []], "Input Dims": [[65536, 5632], [65536, 5632], [65536, 5632], [16, 4096, 5632], [16, 4096, 5632], [16, 4096, 5632], []], "Ev Idx": 1635 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 1336756, "tid": 1381189, + "ts": 1655274551185.141, "dur": 54.464, + "args": { + "External id": 4054629,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[0, 1, 2048], [0, 5632, 1], [11534336, 5632, 1]], "Input Dims": [[1, 2048, 65536], [1, 65536, 5632], [1, 2048, 5632]], "Ev Idx": 1636 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655274551249.615, "dur": 31.698, + "args": { + "External id": 4054630,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 5632], [2048, 1], [2048, 1]], "Input Dims": [[5632, 65536], [65536, 2048], [5632, 2048]], "Ev Idx": 1637 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655274551287.519, "dur": 45.998, + "args": { + "External id": 4054631,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 5632], [5632, 2048], [65536, 2048]], "Ev Idx": 1638 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655274551341.796, "dur": 28.377, + "args": { + "External id": 4054632,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 5632], [2048, 1], [2048, 1]], "Input Dims": [[5632, 65536], [65536, 2048], [5632, 2048]], "Ev Idx": 1639 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655274551378.393, "dur": 56.264, + "args": { + "External id": 4054633,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 5632], [5632, 2048], [65536, 2048]], "Ev Idx": 1640 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_1", "pid": 1336756, "tid": 1381189, + "ts": 1655274551465.771, "dur": 23.238, + "args": { + "External id": 4054634,"kernel_hash": "cjd6g3jfgntyoifzno6l2urmnhif7alxtw6zz7miov66vywxwv7d", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/jd/cjd6g3jfgntyoifzno6l2urmnhif7alxtw6zz7miov66vywxwv7d.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[65536, 2048], [65536, 2048], []], "Ev Idx": 1641 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 1336756, "tid": 1381189, + "ts": 1655274551507.920, "dur": 26.665, + "args": { + "External id": 4054635,"kernel_hash": "cxhg545cyph4gbk5vymzyh72vho7oogk3ycan2lp4cxntklp5hew", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "65536", "2048", "1", "497", "132", "True", "2048", "True", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/xh/cxhg545cyph4gbk5vymzyh72vho7oogk3ycan2lp4cxntklp5hew.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [1], [2048, 1], [2048, 1], [2048, 1], [2048, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [2048], [65536, 2048], [65536, 2048], [132, 2048], [65536, 2048], [65536], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 1642 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 1336756, "tid": 1381189, + "ts": 1655274551558.235, "dur": 18.031, + "args": { + "External id": 4054636,"kernel_hash": "cu42i6zmxtvs2i7cs6x4ixaexke3lhgdiaye5oxwm7s3u6em6co4", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "66"], "kernel_file": "/tmp/torchinductor_cvm/u4/cu42i6zmxtvs2i7cs6x4ixaexke3lhgdiaye5oxwm7s3u6em6co4.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [4096, 1, 2048], [], []], "Input Dims": [[132, 2048], [1, 2048, 2], [], []], "Ev Idx": 1643 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 1336756, "tid": 1381189, + "ts": 1655274551591.024, "dur": 16.448, + "args": { + "External id": 4054637,"kernel_hash": "ckihofrorhmzazt2wfn2dz2m5wfx3auisu2gvfo2jsepr4zyekmq", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "2"], "kernel_file": "/tmp/torchinductor_cvm/ki/ckihofrorhmzazt2wfn2dz2m5wfx3auisu2gvfo2jsepr4zyekmq.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1, 2048], [2048, 1], [], []], "Input Dims": [[1, 2048, 2], [1, 2048], [], []], "Ev Idx": 1644 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655274551615.971, "dur": 30.717, + "args": { + "External id": 4054638,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 1645 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655274551649.978, "dur": 33.522, + "args": { + "External id": 4054639,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 1646 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 1336756, "tid": 1381189, + "ts": 1655274551711.043, "dur": 168.463, + "args": { + "External id": 4054640,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.125", "True", "-1", "-1", "0.", "", "False", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar", "long int"], "Input Strides": [[8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [131072, 4096, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 32, 4096], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 1647 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655274551788.720, "dur": 7.873, + "args": { + "External id": 4054641,"Record function id": 0, "Concrete Inputs": ["[16, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1648 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655274551798.619, "dur": 2.167, + "args": { + "External id": 4054642,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1649 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336756, "tid": 1381189, + "ts": 1655274551911.630, "dur": 24.194, + "args": { + "External id": 4054643,"kernel_hash": "cb6oumcqb462ndf2ivcd2sc6qg6mfjahptjw4ih7cesqhfpziv3b", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/b6/cb6oumcqb462ndf2ivcd2sc6qg6mfjahptjw4ih7cesqhfpziv3b.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 1650 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336756, "tid": 1381189, + "ts": 1655274551953.227, "dur": 13.567, + "args": { + "External id": 4054644,"kernel_hash": "cb6oumcqb462ndf2ivcd2sc6qg6mfjahptjw4ih7cesqhfpziv3b", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/b6/cb6oumcqb462ndf2ivcd2sc6qg6mfjahptjw4ih7cesqhfpziv3b.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 1651 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655274551974.408, "dur": 77.787, + "args": { + "External id": 4054645,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 1652 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655274552061.552, "dur": 37.743, + "args": { + "External id": 4054646,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 1653 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655274552107.150, "dur": 20.314, + "args": { + "External id": 4054647,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 1654 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655274552134.176, "dur": 29.956, + "args": { + "External id": 4054648,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 1655 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655274552168.856, "dur": 19.376, + "args": { + "External id": 4054649,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 1656 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655274552194.841, "dur": 29.971, + "args": { + "External id": 4054650,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 1657 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_4", "pid": 1336756, "tid": 1381189, + "ts": 1655274552247.072, "dur": 23.630, + "args": { + "External id": 4054651,"kernel_hash": "c7pqhdjojzeazwsh5g3ibnyk4m2nfh3q73e3zc7hljz4yvhe7c4h", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/7p/c7pqhdjojzeazwsh5g3ibnyk4m2nfh3q73e3zc7hljz4yvhe7c4h.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1], []], "Input Dims": [[65536, 2048], [65536, 2048], [65536, 2048], []], "Ev Idx": 1658 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_2", "pid": 1336756, "tid": 1381189, + "ts": 1655274552288.894, "dur": 22.103, + "args": { + "External id": 4054652,"kernel_hash": "cvgvwkysjpcw75q5t3guce5bep2so25f7i5zxc6ipt5f56shof73", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "65536", "2048", "1", "497", "132", "True", "2048", "False", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/vg/cvgvwkysjpcw75q5t3guce5bep2so25f7i5zxc6ipt5f56shof73.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [1], [2048, 1], [2048, 1], [2048, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [2048], [65536, 2048], [65536, 2048], [132, 2048], [65536], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 1659 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 1336756, "tid": 1381189, + "ts": 1655274552330.627, "dur": 15.191, + "args": { + "External id": 4054653,"kernel_hash": "cu42i6zmxtvs2i7cs6x4ixaexke3lhgdiaye5oxwm7s3u6em6co4", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "66"], "kernel_file": "/tmp/torchinductor_cvm/u4/cu42i6zmxtvs2i7cs6x4ixaexke3lhgdiaye5oxwm7s3u6em6co4.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [4096, 1, 2048], [], []], "Input Dims": [[132, 2048], [1, 2048, 2], [], []], "Ev Idx": 1660 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 1336756, "tid": 1381189, + "ts": 1655274552358.956, "dur": 12.324, + "args": { + "External id": 4054654,"kernel_hash": "ckihofrorhmzazt2wfn2dz2m5wfx3auisu2gvfo2jsepr4zyekmq", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "2"], "kernel_file": "/tmp/torchinductor_cvm/ki/ckihofrorhmzazt2wfn2dz2m5wfx3auisu2gvfo2jsepr4zyekmq.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1, 2048], [2048, 1], [], []], "Input Dims": [[1, 2048, 2], [1, 2048], [], []], "Ev Idx": 1661 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_5", "pid": 1336756, "tid": 1381189, + "ts": 1655274552389.527, "dur": 15.284, + "args": { + "External id": 4054655,"kernel_hash": "cckrpn5uuxyvbancoio3sz2onrjto236n54xx4ycphq5p6r3jlfj", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/ck/cckrpn5uuxyvbancoio3sz2onrjto236n54xx4ycphq5p6r3jlfj.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [8388608, 2048, 1], []], "Input Dims": [[65536, 2048], [65536, 2048], [16, 4096, 2048], []], "Ev Idx": 1662 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274552491.631, "dur": 14.486, + "args": { + "External id": 4054656,"Record function id": 0, "Ev Idx": 1663 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274552494.723, "dur": 10.453, + "args": { + "External id": 4054657,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 1664 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274552498.839, "dur": 5.513, + "args": { + "External id": 4054658,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 1665 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274552500.262, "dur": 4.001, + "args": { + "External id": 4054659,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 1666 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274552509.799, "dur": 6.187, + "args": { + "External id": 4054660,"Record function id": 0, "Ev Idx": 1667 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274552513.074, "dur": 2.412, + "args": { + "External id": 4054661,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 1668 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274552513.606, "dur": 1.329, + "args": { + "External id": 4054662,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 1669 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274552514.035, "dur": 0.830, + "args": { + "External id": 4054663,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 1670 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274552519.228, "dur": 4.647, + "args": { + "External id": 4054664,"Record function id": 0, "Ev Idx": 1671 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274552520.734, "dur": 2.701, + "args": { + "External id": 4054665,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 1672 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274552521.322, "dur": 1.677, + "args": { + "External id": 4054666,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 1673 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274552522.209, "dur": 0.679, + "args": { + "External id": 4054667,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 1674 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274552527.009, "dur": 6.487, + "args": { + "External id": 4054668,"Record function id": 0, "Ev Idx": 1675 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274552528.013, "dur": 5.064, + "args": { + "External id": 4054669,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 1676 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274552528.866, "dur": 3.803, + "args": { + "External id": 4054670,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 1677 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274552529.295, "dur": 3.286, + "args": { + "External id": 4054671,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 1678 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274552536.553, "dur": 4.166, + "args": { + "External id": 4054672,"Record function id": 0, "Ev Idx": 1679 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274552537.581, "dur": 2.719, + "args": { + "External id": 4054673,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 1680 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274552538.023, "dur": 1.709, + "args": { + "External id": 4054674,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 1681 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274552538.932, "dur": 0.714, + "args": { + "External id": 4054675,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 1682 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274552543.723, "dur": 3.536, + "args": { + "External id": 4054676,"Record function id": 0, "Ev Idx": 1683 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274552544.774, "dur": 2.016, + "args": { + "External id": 4054677,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 1684 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274552545.207, "dur": 1.070, + "args": { + "External id": 4054678,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 1685 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274552545.572, "dur": 0.633, + "args": { + "External id": 4054679,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 1686 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274552550.280, "dur": 3.522, + "args": { + "External id": 4054680,"Record function id": 0, "Ev Idx": 1687 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274552551.207, "dur": 2.173, + "args": { + "External id": 4054681,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 1688 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274552552.001, "dur": 0.949, + "args": { + "External id": 4054682,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 1689 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274552552.253, "dur": 0.628, + "args": { + "External id": 4054683,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 1690 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274552556.836, "dur": 5.174, + "args": { + "External id": 4054684,"Record function id": 0, "Ev Idx": 1691 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274552557.835, "dur": 3.777, + "args": { + "External id": 4054685,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 1692 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274552558.313, "dur": 2.865, + "args": { + "External id": 4054686,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 1693 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274552560.557, "dur": 0.546, + "args": { + "External id": 4054687,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 1694 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274552566.249, "dur": 3.740, + "args": { + "External id": 4054688,"Record function id": 0, "Ev Idx": 1695 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274552567.192, "dur": 2.386, + "args": { + "External id": 4054689,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 1696 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274552567.756, "dur": 1.387, + "args": { + "External id": 4054690,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 1697 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274552568.397, "dur": 0.674, + "args": { + "External id": 4054691,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 1698 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RegisterPostBackwardFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1655274552573.614, "dur": 164773.235, + "args": { + "External id": 4054692,"Record function id": 0, "Sequence number": 40618407, "Fwd thread id": 1, "Ev Idx": 1699 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1655274552574.818, "dur": 164763.043, + "args": { + "External id": 4054693,"Sequence number": 40618407, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 1700 + } + }, + { + "ph": "f", "id": 173, "pid": 1336756, "tid": 1381189, "ts": 1655274552574.818, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.27)", "pid": 1336756, "tid": 1381189, + "ts": 1655274552604.642, "dur": 39.873, + "args": { + "External id": 4054694,"Record function id": 0, "Ev Idx": 1701 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.27)", "pid": 1336756, "tid": 1381189, + "ts": 1655274552653.068, "dur": 64.151, + "args": { + "External id": 4054695,"Record function id": 0, "Ev Idx": 1702 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.27)", "pid": 1336756, "tid": 1381189, + "ts": 1655274552724.436, "dur": 164604.965, + "args": { + "External id": 4054696,"Record function id": 0, "Ev Idx": 1703 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655274552777.733, "dur": 6.472, + "args": { + "External id": 4054697,"Record function id": 0, "Concrete Inputs": ["[51384320]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1704 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274552795.787, "dur": 4.526, + "args": { + "External id": 4054698,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[51384320], []], "Ev Idx": 1705 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::chunk_cat", "pid": 1336756, "tid": 1381189, + "ts": 1655274552817.690, "dur": 163679.255, + "args": { + "External id": 4054699,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [2048, 1], [2048, 1], [2048, 1], [2048, 1], [1], [2048, 1], [2048, 1], [5632, 1]], [], [], [6423040, 1]], "Input Dims": [[[2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048], [5632, 2048], [5632, 2048], [2048, 5632]], [], [], [8, 6423040]], "Ev Idx": 1706 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_chunk_cat", "pid": 1336756, "tid": 1381189, + "ts": 1655274552831.841, "dur": 163653.998, + "args": { + "External id": 4054700,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [2048, 1], [2048, 1], [2048, 1], [2048, 1], [1], [2048, 1], [2048, 1], [5632, 1]], [], [], [6423040, 1]], "Input Dims": [[[2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048], [5632, 2048], [5632, 2048], [2048, 5632]], [], [], [8, 6423040]], "Ev Idx": 1707 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655274552881.124, "dur": 5.372, + "args": { + "External id": 4054701,"Record function id": 0, "Concrete Inputs": ["[12602]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1708 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1381189, + "ts": 1655274552892.730, "dur": 163548.933, + "args": { + "External id": 4054702,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[12602], [], [], [], [], [], [], []], "Ev Idx": 1709 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336756, "tid": 1381189, + "ts": 1655274552895.095, "dur": 163545.530, + "args": { + "External id": 4054703,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[12602], [], [], [], [], [], []], "Ev Idx": 1710 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274552898.322, "dur": 7.058, + "args": { + "External id": 4054704,"Record function id": 0, "Concrete Inputs": ["[12602]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1711 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1381189, + "ts": 1655274552907.141, "dur": 163528.993, + "args": { + "External id": 4054705,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[12602], [12602], []], "Ev Idx": 1712 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 1336756, "tid": 1381189, + "ts": 1655274716595.807, "dur": 10.292, + "args": { + "External id": 4054706,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "", "", "", "False"], "Input type": ["float", "ScalarList", "", "", "", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[51384320], [], [], [], [], []], "Ev Idx": 1713 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655274716599.070, "dur": 6.636, + "args": { + "External id": 4054707,"Record function id": 0, "Concrete Inputs": ["[6423040]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1714 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_reduce_scatter_base_", "pid": 1336756, "tid": 1381189, + "ts": 1655274716639.106, "dur": 386.145, + "args": { + "External id": 4054708,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "-1"], "Input type": ["float", "float", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], [], []], "Input Dims": [[6423040], [51384320], [], [], [], []], "Ev Idx": 1715 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336756, "tid": 1381189, + "ts": 1655274716673.814, "dur": 345.939, + "args": { + "External id": 4054709,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 3, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "3", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 6423040, "Process Group Name": "0", "Input type": ["float", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[51384320], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 1716, "In msg nelems": 51384320 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_reduce_scatter_base", "pid": 1336756, "tid": 1381189, + "ts": 1655274716688.642, "dur": 291.823, + "args": { + "External id": 4054710,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[51384320]], "Ev Idx": 1717 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336756, "tid": 1381189, + "ts": 1655274717052.882, "dur": 2.743, + "args": { + "External id": 4054711,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "3", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 1718, "In msg nelems": 0, "Rank": 3, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274717117.629, "dur": 7.220, + "args": { + "External id": 4054712,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 1719 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274717172.145, "dur": 1.416, + "args": { + "External id": 4054713,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "256"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 1720 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274717188.709, "dur": 1.433, + "args": { + "External id": 4054714,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "524544"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 1721 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274717204.794, "dur": 1.042, + "args": { + "External id": 4054715,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "1048832"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 1722 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274717216.501, "dur": 0.722, + "args": { + "External id": 4054716,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "1573120"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 1723 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274717226.323, "dur": 0.902, + "args": { + "External id": 4054717,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 1724 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274717239.522, "dur": 0.977, + "args": { + "External id": 4054718,"Record function id": 0, "Concrete Inputs": ["", "[704, 2048]", "[2048, 1]", "2097664"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 1725 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274717252.950, "dur": 1.785, + "args": { + "External id": 4054719,"Record function id": 0, "Concrete Inputs": ["", "[704, 2048]", "[2048, 1]", "3539456"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 1726 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274717267.684, "dur": 0.774, + "args": { + "External id": 4054720,"Record function id": 0, "Concrete Inputs": ["", "[256, 5632]", "[5632, 1]", "4981248"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 1727 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: CompiledFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1655274717361.188, "dur": 2701.377, + "args": { + "External id": 4054721,"Record function id": 0, "Ev Idx": 1728 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.26)", "pid": 1336756, "tid": 1381189, + "ts": 1655274717380.055, "dur": 1023.603, + "args": { + "External id": 4054722,"Record function id": 0, "Ev Idx": 1729 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.26)", "pid": 1336756, "tid": 1381189, + "ts": 1655274717394.775, "dur": 338.371, + "args": { + "External id": 4054723,"Record function id": 0, "Ev Idx": 1730 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274717489.213, "dur": 4.626, + "args": { + "External id": 4054724,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[51384320], []], "Ev Idx": 1731 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274717496.970, "dur": 0.842, + "args": { + "External id": 4054725,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 1732 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274717499.649, "dur": 0.710, + "args": { + "External id": 4054726,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 1733 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274717501.774, "dur": 2.529, + "args": { + "External id": 4054727,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 1734 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274717507.553, "dur": 0.939, + "args": { + "External id": 4054728,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 1735 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274717509.745, "dur": 0.689, + "args": { + "External id": 4054729,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 1736 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274717511.695, "dur": 1.712, + "args": { + "External id": 4054730,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 1737 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274717517.450, "dur": 0.928, + "args": { + "External id": 4054731,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 1738 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274717521.639, "dur": 0.858, + "args": { + "External id": 4054732,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 1739 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274717523.778, "dur": 0.956, + "args": { + "External id": 4054733,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 1740 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 1336756, "tid": 1381189, + "ts": 1655274717543.990, "dur": 157.262, + "args": { + "External id": 4054734,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 1741 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 1336756, "tid": 1381189, + "ts": 1655274717562.462, "dur": 134.581, + "args": { + "External id": 4054735,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 1742 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655274717583.811, "dur": 12.112, + "args": { + "External id": 4054736,"Record function id": 0, "Concrete Inputs": ["[2133]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1743 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1381189, + "ts": 1655274717598.818, "dur": 70.099, + "args": { + "External id": 4054737,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], [], []], "Ev Idx": 1744 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336756, "tid": 1381189, + "ts": 1655274717603.119, "dur": 65.468, + "args": { + "External id": 4054738,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], []], "Ev Idx": 1745 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274717606.562, "dur": 9.004, + "args": { + "External id": 4054739,"Record function id": 0, "Concrete Inputs": ["[2133]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1746 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1381189, + "ts": 1655274717617.297, "dur": 50.591, + "args": { + "External id": 4054740,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[2133], [2133], []], "Ev Idx": 1747 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::backward_prefetch for model.layers.25", "pid": 1336756, "tid": 1381189, + "ts": 1655274717803.791, "dur": 592.293, + "args": { + "External id": 4054741,"Record function id": 0, "Ev Idx": 1748 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.25)", "pid": 1336756, "tid": 1381189, + "ts": 1655274717819.858, "dur": 564.905, + "args": { + "External id": 4054742,"Record function id": 0, "Ev Idx": 1749 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655274717871.732, "dur": 4.310, + "args": { + "External id": 4054743,"Record function id": 0, "Concrete Inputs": ["[6423040]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1750 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336756, "tid": 1381189, + "ts": 1655274717891.065, "dur": 35.077, + "args": { + "External id": 4054744,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 1751 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274717897.386, "dur": 2.410, + "args": { + "External id": 4054745,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 1752 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274717900.797, "dur": 0.709, + "args": { + "External id": 4054746,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 1753 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274717902.708, "dur": 0.401, + "args": { + "External id": 4054747,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 1754 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274717907.472, "dur": 0.460, + "args": { + "External id": 4054748,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 1755 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274717908.562, "dur": 0.527, + "args": { + "External id": 4054749,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 1756 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274717909.897, "dur": 0.610, + "args": { + "External id": 4054750,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 1757 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274717914.343, "dur": 2.181, + "args": { + "External id": 4054751,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 1758 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274717917.164, "dur": 0.473, + "args": { + "External id": 4054752,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 1759 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274717920.050, "dur": 1.640, + "args": { + "External id": 4054753,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 1760 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336756, "tid": 1381189, + "ts": 1655274717943.387, "dur": 28.922, + "args": { + "External id": 4054754,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 1761 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 1336756, "tid": 1381189, + "ts": 1655274718041.834, "dur": 108.765, + "args": { + "External id": 4054755,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "6423040", "8", "3", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [], [], [], [], [], []], "Ev Idx": 1762 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655274718052.566, "dur": 5.668, + "args": { + "External id": 4054756,"Record function id": 0, "Concrete Inputs": ["[51384320]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1763 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 1336756, "tid": 1381189, + "ts": 1655274718063.460, "dur": 12.088, + "args": { + "External id": 4054757,"Record function id": 0, "Concrete Inputs": ["", "0", "19269120", "6423040"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 1764 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1381189, + "ts": 1655274718067.589, "dur": 7.529, + "args": { + "External id": 4054758,"Record function id": 0, "Concrete Inputs": ["", "0", "19269120", "25692160", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[51384320], [], [], [], []], "Ev Idx": 1765 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274718073.081, "dur": 0.600, + "args": { + "External id": 4054759,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "[1]", "19269120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 1766 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336756, "tid": 1381189, + "ts": 1655274718082.399, "dur": 26.380, + "args": { + "External id": 4054760,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 1767 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274718083.983, "dur": 0.476, + "args": { + "External id": 4054761,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "19269120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 1768 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274718087.167, "dur": 1.569, + "args": { + "External id": 4054762,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "19269376"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 1769 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274718089.368, "dur": 0.313, + "args": { + "External id": 4054763,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "19793664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 1770 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274718090.288, "dur": 2.704, + "args": { + "External id": 4054764,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "20317952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 1771 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274718097.121, "dur": 0.426, + "args": { + "External id": 4054765,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "20842240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 1772 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274718098.271, "dur": 0.429, + "args": { + "External id": 4054766,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "21366528"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 1773 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274718101.032, "dur": 0.393, + "args": { + "External id": 4054767,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "21366784"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 1774 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274718103.183, "dur": 0.356, + "args": { + "External id": 4054768,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "22808576"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 1775 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274718104.176, "dur": 0.398, + "args": { + "External id": 4054769,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "24250368"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 1776 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336756, "tid": 1381189, + "ts": 1655274718122.005, "dur": 20.902, + "args": { + "External id": 4054770,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 1777 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 1336756, "tid": 1381189, + "ts": 1655274718195.991, "dur": 123.080, + "args": { + "External id": 4054771,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[51384320], [6423040], [], [], []], "Ev Idx": 1778 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336756, "tid": 1381189, + "ts": 1655274718226.707, "dur": 89.082, + "args": { + "External id": 4054772,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 3, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "3", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 51384320, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[6423040], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 1779, "In msg nelems": 6423040 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 1336756, "tid": 1381189, + "ts": 1655274718237.855, "dur": 73.880, + "args": { + "External id": 4054773,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[6423040]], "Ev Idx": 1780 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336756, "tid": 1381189, + "ts": 1655274718335.615, "dur": 1.646, + "args": { + "External id": 4054774,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "3", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 1781, "In msg nelems": 0, "Rank": 3, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1655274718410.037, "dur": 1632.447, + "args": { + "External id": 4054775,"Sequence number": 40618406, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 1782 + } + }, + { + "ph": "f", "id": 174, "pid": 1336756, "tid": 1381189, "ts": 1655274718410.037, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655274718535.940, "dur": 105.292, + "args": { + "External id": 4054776,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [5632, 1], [5632, 1]], "Input Dims": [[65536, 2048], [2048, 5632], [65536, 5632]], "Ev Idx": 1783 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_add_mul_rsub_silu_0", "pid": 1336756, "tid": 1381189, + "ts": 1655274718682.917, "dur": 35.049, + "args": { + "External id": 4054777,"kernel_hash": "c2zszzsomz26dv2qwvmiurvgyrl5qxtyn6ocoqkdpzzhfzwqp5q6", "grid": "grid(369098752,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "369098752"], "kernel_file": "/tmp/torchinductor_cvm/2z/c2zszzsomz26dv2qwvmiurvgyrl5qxtyn6ocoqkdpzzhfzwqp5q6.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[5632, 1], [5632, 1], [5632, 1], [23068672, 5632, 1], [23068672, 5632, 1], [23068672, 5632, 1], []], "Input Dims": [[65536, 5632], [65536, 5632], [65536, 5632], [16, 4096, 5632], [16, 4096, 5632], [16, 4096, 5632], []], "Ev Idx": 1784 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 1336756, "tid": 1381189, + "ts": 1655274718733.316, "dur": 47.790, + "args": { + "External id": 4054778,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[0, 1, 2048], [0, 5632, 1], [11534336, 5632, 1]], "Input Dims": [[1, 2048, 65536], [1, 65536, 5632], [1, 2048, 5632]], "Ev Idx": 1785 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655274718790.206, "dur": 33.599, + "args": { + "External id": 4054779,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 5632], [2048, 1], [2048, 1]], "Input Dims": [[5632, 65536], [65536, 2048], [5632, 2048]], "Ev Idx": 1786 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655274718833.174, "dur": 46.043, + "args": { + "External id": 4054780,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 5632], [5632, 2048], [65536, 2048]], "Ev Idx": 1787 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655274718886.045, "dur": 27.941, + "args": { + "External id": 4054781,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 5632], [2048, 1], [2048, 1]], "Input Dims": [[5632, 65536], [65536, 2048], [5632, 2048]], "Ev Idx": 1788 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655274718921.484, "dur": 42.871, + "args": { + "External id": 4054782,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 5632], [5632, 2048], [65536, 2048]], "Ev Idx": 1789 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_1", "pid": 1336756, "tid": 1381189, + "ts": 1655274719026.306, "dur": 25.486, + "args": { + "External id": 4054783,"kernel_hash": "cjd6g3jfgntyoifzno6l2urmnhif7alxtw6zz7miov66vywxwv7d", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/jd/cjd6g3jfgntyoifzno6l2urmnhif7alxtw6zz7miov66vywxwv7d.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[65536, 2048], [65536, 2048], []], "Ev Idx": 1790 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 1336756, "tid": 1381189, + "ts": 1655274719076.486, "dur": 28.624, + "args": { + "External id": 4054784,"kernel_hash": "cxhg545cyph4gbk5vymzyh72vho7oogk3ycan2lp4cxntklp5hew", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "65536", "2048", "1", "497", "132", "True", "2048", "True", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/xh/cxhg545cyph4gbk5vymzyh72vho7oogk3ycan2lp4cxntklp5hew.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [1], [2048, 1], [2048, 1], [2048, 1], [2048, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [2048], [65536, 2048], [65536, 2048], [132, 2048], [65536, 2048], [65536], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 1791 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 1336756, "tid": 1381189, + "ts": 1655274719129.128, "dur": 18.438, + "args": { + "External id": 4054785,"kernel_hash": "cu42i6zmxtvs2i7cs6x4ixaexke3lhgdiaye5oxwm7s3u6em6co4", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "66"], "kernel_file": "/tmp/torchinductor_cvm/u4/cu42i6zmxtvs2i7cs6x4ixaexke3lhgdiaye5oxwm7s3u6em6co4.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [4096, 1, 2048], [], []], "Input Dims": [[132, 2048], [1, 2048, 2], [], []], "Ev Idx": 1792 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 1336756, "tid": 1381189, + "ts": 1655274719166.272, "dur": 15.460, + "args": { + "External id": 4054786,"kernel_hash": "ckihofrorhmzazt2wfn2dz2m5wfx3auisu2gvfo2jsepr4zyekmq", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "2"], "kernel_file": "/tmp/torchinductor_cvm/ki/ckihofrorhmzazt2wfn2dz2m5wfx3auisu2gvfo2jsepr4zyekmq.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1, 2048], [2048, 1], [], []], "Input Dims": [[1, 2048, 2], [1, 2048], [], []], "Ev Idx": 1793 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655274719189.504, "dur": 34.031, + "args": { + "External id": 4054787,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 1794 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655274719227.170, "dur": 33.558, + "args": { + "External id": 4054788,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 1795 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 1336756, "tid": 1381189, + "ts": 1655274719289.131, "dur": 181.100, + "args": { + "External id": 4054789,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.125", "True", "-1", "-1", "0.", "", "False", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar", "long int"], "Input Strides": [[8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [131072, 4096, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 32, 4096], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 1796 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655274719365.212, "dur": 5.241, + "args": { + "External id": 4054790,"Record function id": 0, "Concrete Inputs": ["[16, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1797 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655274719372.404, "dur": 2.183, + "args": { + "External id": 4054791,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1798 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336756, "tid": 1381189, + "ts": 1655274719511.070, "dur": 26.296, + "args": { + "External id": 4054792,"kernel_hash": "cb6oumcqb462ndf2ivcd2sc6qg6mfjahptjw4ih7cesqhfpziv3b", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/b6/cb6oumcqb462ndf2ivcd2sc6qg6mfjahptjw4ih7cesqhfpziv3b.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 1799 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336756, "tid": 1381189, + "ts": 1655274719550.270, "dur": 13.832, + "args": { + "External id": 4054793,"kernel_hash": "cb6oumcqb462ndf2ivcd2sc6qg6mfjahptjw4ih7cesqhfpziv3b", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/b6/cb6oumcqb462ndf2ivcd2sc6qg6mfjahptjw4ih7cesqhfpziv3b.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 1800 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655274719572.153, "dur": 37.568, + "args": { + "External id": 4054794,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 1801 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655274719615.618, "dur": 34.696, + "args": { + "External id": 4054795,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 1802 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655274719660.065, "dur": 19.958, + "args": { + "External id": 4054796,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 1803 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655274719684.165, "dur": 29.938, + "args": { + "External id": 4054797,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 1804 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655274719720.077, "dur": 19.786, + "args": { + "External id": 4054798,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 1805 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655274719746.092, "dur": 29.081, + "args": { + "External id": 4054799,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 1806 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_4", "pid": 1336756, "tid": 1381189, + "ts": 1655274719797.742, "dur": 34.999, + "args": { + "External id": 4054800,"kernel_hash": "c7pqhdjojzeazwsh5g3ibnyk4m2nfh3q73e3zc7hljz4yvhe7c4h", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/7p/c7pqhdjojzeazwsh5g3ibnyk4m2nfh3q73e3zc7hljz4yvhe7c4h.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1], []], "Input Dims": [[65536, 2048], [65536, 2048], [65536, 2048], []], "Ev Idx": 1807 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_2", "pid": 1336756, "tid": 1381189, + "ts": 1655274719858.858, "dur": 25.153, + "args": { + "External id": 4054801,"kernel_hash": "cvgvwkysjpcw75q5t3guce5bep2so25f7i5zxc6ipt5f56shof73", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "65536", "2048", "1", "497", "132", "True", "2048", "False", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/vg/cvgvwkysjpcw75q5t3guce5bep2so25f7i5zxc6ipt5f56shof73.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [1], [2048, 1], [2048, 1], [2048, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [2048], [65536, 2048], [65536, 2048], [132, 2048], [65536], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 1808 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 1336756, "tid": 1381189, + "ts": 1655274719897.601, "dur": 15.783, + "args": { + "External id": 4054802,"kernel_hash": "cu42i6zmxtvs2i7cs6x4ixaexke3lhgdiaye5oxwm7s3u6em6co4", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "66"], "kernel_file": "/tmp/torchinductor_cvm/u4/cu42i6zmxtvs2i7cs6x4ixaexke3lhgdiaye5oxwm7s3u6em6co4.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [4096, 1, 2048], [], []], "Input Dims": [[132, 2048], [1, 2048, 2], [], []], "Ev Idx": 1809 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 1336756, "tid": 1381189, + "ts": 1655274719933.638, "dur": 13.293, + "args": { + "External id": 4054803,"kernel_hash": "ckihofrorhmzazt2wfn2dz2m5wfx3auisu2gvfo2jsepr4zyekmq", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "2"], "kernel_file": "/tmp/torchinductor_cvm/ki/ckihofrorhmzazt2wfn2dz2m5wfx3auisu2gvfo2jsepr4zyekmq.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1, 2048], [2048, 1], [], []], "Input Dims": [[1, 2048, 2], [1, 2048], [], []], "Ev Idx": 1810 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_5", "pid": 1336756, "tid": 1381189, + "ts": 1655274719961.150, "dur": 14.457, + "args": { + "External id": 4054804,"kernel_hash": "cckrpn5uuxyvbancoio3sz2onrjto236n54xx4ycphq5p6r3jlfj", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/ck/cckrpn5uuxyvbancoio3sz2onrjto236n54xx4ycphq5p6r3jlfj.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [8388608, 2048, 1], []], "Input Dims": [[65536, 2048], [65536, 2048], [16, 4096, 2048], []], "Ev Idx": 1811 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274720088.474, "dur": 15.062, + "args": { + "External id": 4054805,"Record function id": 0, "Ev Idx": 1812 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274720091.525, "dur": 11.161, + "args": { + "External id": 4054806,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 1813 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274720095.838, "dur": 5.885, + "args": { + "External id": 4054807,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 1814 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274720097.509, "dur": 4.100, + "args": { + "External id": 4054808,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 1815 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274720107.275, "dur": 4.792, + "args": { + "External id": 4054809,"Record function id": 0, "Ev Idx": 1816 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274720108.829, "dur": 2.809, + "args": { + "External id": 4054810,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 1817 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274720109.535, "dur": 1.510, + "args": { + "External id": 4054811,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 1818 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274720110.189, "dur": 0.768, + "args": { + "External id": 4054812,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 1819 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274720115.318, "dur": 6.061, + "args": { + "External id": 4054813,"Record function id": 0, "Ev Idx": 1820 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274720116.435, "dur": 4.526, + "args": { + "External id": 4054814,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 1821 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274720117.248, "dur": 3.279, + "args": { + "External id": 4054815,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 1822 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274720117.879, "dur": 2.549, + "args": { + "External id": 4054816,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 1823 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274720124.596, "dur": 5.760, + "args": { + "External id": 4054817,"Record function id": 0, "Ev Idx": 1824 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274720127.242, "dur": 2.656, + "args": { + "External id": 4054818,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 1825 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274720128.066, "dur": 1.429, + "args": { + "External id": 4054819,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 1826 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274720128.594, "dur": 0.819, + "args": { + "External id": 4054820,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 1827 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274720133.605, "dur": 3.852, + "args": { + "External id": 4054821,"Record function id": 0, "Ev Idx": 1828 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274720134.647, "dur": 2.385, + "args": { + "External id": 4054822,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 1829 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274720135.384, "dur": 1.214, + "args": { + "External id": 4054823,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 1830 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274720135.802, "dur": 0.730, + "args": { + "External id": 4054824,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 1831 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274720140.636, "dur": 3.711, + "args": { + "External id": 4054825,"Record function id": 0, "Ev Idx": 1832 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274720141.651, "dur": 2.304, + "args": { + "External id": 4054826,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 1833 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274720142.233, "dur": 1.308, + "args": { + "External id": 4054827,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 1834 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274720142.853, "dur": 0.614, + "args": { + "External id": 4054828,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 1835 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274720147.872, "dur": 3.441, + "args": { + "External id": 4054829,"Record function id": 0, "Ev Idx": 1836 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274720148.785, "dur": 2.101, + "args": { + "External id": 4054830,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 1837 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274720149.356, "dur": 1.126, + "args": { + "External id": 4054831,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 1838 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274720149.760, "dur": 0.660, + "args": { + "External id": 4054832,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 1839 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274720154.489, "dur": 5.371, + "args": { + "External id": 4054833,"Record function id": 0, "Ev Idx": 1840 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274720155.382, "dur": 4.073, + "args": { + "External id": 4054834,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 1841 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274720155.960, "dur": 3.102, + "args": { + "External id": 4054835,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 1842 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274720158.336, "dur": 0.660, + "args": { + "External id": 4054836,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 1843 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274720162.920, "dur": 3.159, + "args": { + "External id": 4054837,"Record function id": 0, "Ev Idx": 1844 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274720163.816, "dur": 1.838, + "args": { + "External id": 4054838,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 1845 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274720164.282, "dur": 0.897, + "args": { + "External id": 4054839,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 1846 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274720164.549, "dur": 0.564, + "args": { + "External id": 4054840,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 1847 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RegisterPostBackwardFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1655274720169.592, "dur": 43110.155, + "args": { + "External id": 4054841,"Record function id": 0, "Sequence number": 40618405, "Fwd thread id": 1, "Ev Idx": 1848 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1655274720171.029, "dur": 43099.562, + "args": { + "External id": 4054842,"Sequence number": 40618405, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 1849 + } + }, + { + "ph": "f", "id": 175, "pid": 1336756, "tid": 1381189, "ts": 1655274720171.029, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.26)", "pid": 1336756, "tid": 1381189, + "ts": 1655274720200.635, "dur": 36.767, + "args": { + "External id": 4054843,"Record function id": 0, "Ev Idx": 1850 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.26)", "pid": 1336756, "tid": 1381189, + "ts": 1655274720244.888, "dur": 58.771, + "args": { + "External id": 4054844,"Record function id": 0, "Ev Idx": 1851 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.26)", "pid": 1336756, "tid": 1381189, + "ts": 1655274720311.112, "dur": 42951.533, + "args": { + "External id": 4054845,"Record function id": 0, "Ev Idx": 1852 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655274720397.953, "dur": 6.382, + "args": { + "External id": 4054846,"Record function id": 0, "Concrete Inputs": ["[51384320]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1853 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274720413.869, "dur": 22.332, + "args": { + "External id": 4054847,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[51384320], []], "Ev Idx": 1854 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::chunk_cat", "pid": 1336756, "tid": 1381189, + "ts": 1655274720455.548, "dur": 41957.773, + "args": { + "External id": 4054848,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [2048, 1], [2048, 1], [2048, 1], [2048, 1], [1], [2048, 1], [2048, 1], [5632, 1]], [], [], [6423040, 1]], "Input Dims": [[[2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048], [5632, 2048], [5632, 2048], [2048, 5632]], [], [], [8, 6423040]], "Ev Idx": 1855 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_chunk_cat", "pid": 1336756, "tid": 1381189, + "ts": 1655274720470.783, "dur": 41932.830, + "args": { + "External id": 4054849,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [2048, 1], [2048, 1], [2048, 1], [2048, 1], [1], [2048, 1], [2048, 1], [5632, 1]], [], [], [6423040, 1]], "Input Dims": [[[2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048], [5632, 2048], [5632, 2048], [2048, 5632]], [], [], [8, 6423040]], "Ev Idx": 1856 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655274720524.819, "dur": 13.914, + "args": { + "External id": 4054850,"Record function id": 0, "Concrete Inputs": ["[12602]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1857 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1381189, + "ts": 1655274720545.126, "dur": 41823.150, + "args": { + "External id": 4054851,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[12602], [], [], [], [], [], [], []], "Ev Idx": 1858 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336756, "tid": 1381189, + "ts": 1655274720547.439, "dur": 41820.268, + "args": { + "External id": 4054852,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[12602], [], [], [], [], [], []], "Ev Idx": 1859 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274720552.545, "dur": 5.561, + "args": { + "External id": 4054853,"Record function id": 0, "Concrete Inputs": ["[12602]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1860 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1381189, + "ts": 1655274720559.800, "dur": 41803.965, + "args": { + "External id": 4054854,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[12602], [12602], []], "Ev Idx": 1861 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 1336756, "tid": 1381189, + "ts": 1655274762514.318, "dur": 9.301, + "args": { + "External id": 4054855,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "", "", "", "False"], "Input type": ["float", "ScalarList", "", "", "", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[51384320], [], [], [], [], []], "Ev Idx": 1862 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655274762517.198, "dur": 5.972, + "args": { + "External id": 4054856,"Record function id": 0, "Concrete Inputs": ["[6423040]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1863 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_reduce_scatter_base_", "pid": 1336756, "tid": 1381189, + "ts": 1655274762554.335, "dur": 385.469, + "args": { + "External id": 4054857,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "-1"], "Input type": ["float", "float", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], [], []], "Input Dims": [[6423040], [51384320], [], [], [], []], "Ev Idx": 1864 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336756, "tid": 1381189, + "ts": 1655274762588.011, "dur": 346.726, + "args": { + "External id": 4054858,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 3, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "3", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 6423040, "Process Group Name": "0", "Input type": ["float", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[51384320], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 1865, "In msg nelems": 51384320 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_reduce_scatter_base", "pid": 1336756, "tid": 1381189, + "ts": 1655274762601.315, "dur": 328.423, + "args": { + "External id": 4054859,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[51384320]], "Ev Idx": 1866 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336756, "tid": 1381189, + "ts": 1655274762964.858, "dur": 2.093, + "args": { + "External id": 4054860,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "3", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 1867, "In msg nelems": 0, "Rank": 3, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274763062.499, "dur": 7.313, + "args": { + "External id": 4054861,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 1868 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274763114.536, "dur": 1.438, + "args": { + "External id": 4054862,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "256"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 1869 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274763131.152, "dur": 3.505, + "args": { + "External id": 4054863,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "524544"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 1870 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274763144.769, "dur": 0.868, + "args": { + "External id": 4054864,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "1048832"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 1871 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274763156.907, "dur": 0.804, + "args": { + "External id": 4054865,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "1573120"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 1872 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274763167.021, "dur": 1.132, + "args": { + "External id": 4054866,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 1873 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274763177.134, "dur": 2.895, + "args": { + "External id": 4054867,"Record function id": 0, "Concrete Inputs": ["", "[704, 2048]", "[2048, 1]", "2097664"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 1874 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274763191.198, "dur": 1.884, + "args": { + "External id": 4054868,"Record function id": 0, "Concrete Inputs": ["", "[704, 2048]", "[2048, 1]", "3539456"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 1875 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274763203.668, "dur": 0.725, + "args": { + "External id": 4054869,"Record function id": 0, "Concrete Inputs": ["", "[256, 5632]", "[5632, 1]", "4981248"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 1876 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: CompiledFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1655274763295.077, "dur": 2633.701, + "args": { + "External id": 4054870,"Record function id": 0, "Ev Idx": 1877 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.25)", "pid": 1336756, "tid": 1381189, + "ts": 1655274763313.910, "dur": 1008.345, + "args": { + "External id": 4054871,"Record function id": 0, "Ev Idx": 1878 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.25)", "pid": 1336756, "tid": 1381189, + "ts": 1655274763327.222, "dur": 334.166, + "args": { + "External id": 4054872,"Record function id": 0, "Ev Idx": 1879 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274763401.431, "dur": 4.114, + "args": { + "External id": 4054873,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[51384320], []], "Ev Idx": 1880 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274763408.311, "dur": 1.027, + "args": { + "External id": 4054874,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 1881 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274763410.829, "dur": 2.806, + "args": { + "External id": 4054875,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 1882 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274763433.643, "dur": 1.468, + "args": { + "External id": 4054876,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 1883 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274763440.479, "dur": 1.086, + "args": { + "External id": 4054877,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 1884 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274763442.946, "dur": 1.196, + "args": { + "External id": 4054878,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 1885 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274763445.414, "dur": 2.138, + "args": { + "External id": 4054879,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 1886 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274763448.840, "dur": 1.004, + "args": { + "External id": 4054880,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 1887 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274763453.115, "dur": 0.714, + "args": { + "External id": 4054881,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 1888 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274763454.950, "dur": 0.871, + "args": { + "External id": 4054882,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 1889 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 1336756, "tid": 1381189, + "ts": 1655274763475.368, "dur": 155.319, + "args": { + "External id": 4054883,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 1890 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 1336756, "tid": 1381189, + "ts": 1655274763492.136, "dur": 134.054, + "args": { + "External id": 4054884,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 1891 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655274763510.187, "dur": 15.941, + "args": { + "External id": 4054885,"Record function id": 0, "Concrete Inputs": ["[2133]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1892 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1381189, + "ts": 1655274763529.276, "dur": 69.508, + "args": { + "External id": 4054886,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], [], []], "Ev Idx": 1893 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336756, "tid": 1381189, + "ts": 1655274763533.406, "dur": 65.054, + "args": { + "External id": 4054887,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], []], "Ev Idx": 1894 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274763537.864, "dur": 5.463, + "args": { + "External id": 4054888,"Record function id": 0, "Concrete Inputs": ["[2133]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1895 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1381189, + "ts": 1655274763544.968, "dur": 52.933, + "args": { + "External id": 4054889,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[2133], [2133], []], "Ev Idx": 1896 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::backward_prefetch for model.layers.24", "pid": 1336756, "tid": 1381189, + "ts": 1655274763736.274, "dur": 578.732, + "args": { + "External id": 4054890,"Record function id": 0, "Ev Idx": 1897 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.24)", "pid": 1336756, "tid": 1381189, + "ts": 1655274763751.206, "dur": 551.639, + "args": { + "External id": 4054891,"Record function id": 0, "Ev Idx": 1898 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655274763803.038, "dur": 4.565, + "args": { + "External id": 4054892,"Record function id": 0, "Concrete Inputs": ["[6423040]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1899 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336756, "tid": 1381189, + "ts": 1655274763823.157, "dur": 29.323, + "args": { + "External id": 4054893,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 1900 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274763827.106, "dur": 1.906, + "args": { + "External id": 4054894,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 1901 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274763831.624, "dur": 0.385, + "args": { + "External id": 4054895,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 1902 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274763833.835, "dur": 0.497, + "args": { + "External id": 4054896,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 1903 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274763835.274, "dur": 1.393, + "args": { + "External id": 4054897,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 1904 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274763838.658, "dur": 0.470, + "args": { + "External id": 4054898,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 1905 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274763839.737, "dur": 2.441, + "args": { + "External id": 4054899,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 1906 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274763844.371, "dur": 0.398, + "args": { + "External id": 4054900,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 1907 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274763846.713, "dur": 0.395, + "args": { + "External id": 4054901,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 1908 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274763847.609, "dur": 0.505, + "args": { + "External id": 4054902,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 1909 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336756, "tid": 1381189, + "ts": 1655274763860.549, "dur": 29.163, + "args": { + "External id": 4054903,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 1910 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 1336756, "tid": 1381189, + "ts": 1655274763918.376, "dur": 152.227, + "args": { + "External id": 4054904,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "6423040", "8", "3", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [], [], [], [], [], []], "Ev Idx": 1911 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655274763927.513, "dur": 2.568, + "args": { + "External id": 4054905,"Record function id": 0, "Concrete Inputs": ["[51384320]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1912 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 1336756, "tid": 1381189, + "ts": 1655274763934.578, "dur": 10.443, + "args": { + "External id": 4054906,"Record function id": 0, "Concrete Inputs": ["", "0", "19269120", "6423040"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 1913 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1381189, + "ts": 1655274763938.791, "dur": 5.783, + "args": { + "External id": 4054907,"Record function id": 0, "Concrete Inputs": ["", "0", "19269120", "25692160", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[51384320], [], [], [], []], "Ev Idx": 1914 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274763941.384, "dur": 2.082, + "args": { + "External id": 4054908,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "[1]", "19269120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 1915 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336756, "tid": 1381189, + "ts": 1655274763951.324, "dur": 76.358, + "args": { + "External id": 4054909,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 1916 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274763954.282, "dur": 0.467, + "args": { + "External id": 4054910,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "19269120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 1917 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274763955.656, "dur": 0.700, + "args": { + "External id": 4054911,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "19269376"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 1918 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274763969.192, "dur": 2.512, + "args": { + "External id": 4054912,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "19793664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 1919 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274763973.413, "dur": 0.506, + "args": { + "External id": 4054913,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "20317952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 1920 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274763974.546, "dur": 0.475, + "args": { + "External id": 4054914,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "20842240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 1921 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274763977.002, "dur": 1.349, + "args": { + "External id": 4054915,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "21366528"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 1922 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274763978.951, "dur": 0.408, + "args": { + "External id": 4054916,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "21366784"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 1923 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274763979.808, "dur": 0.247, + "args": { + "External id": 4054917,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "22808576"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 1924 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274764022.279, "dur": 0.569, + "args": { + "External id": 4054918,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "24250368"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 1925 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336756, "tid": 1381189, + "ts": 1655274764039.105, "dur": 23.473, + "args": { + "External id": 4054919,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 1926 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 1336756, "tid": 1381189, + "ts": 1655274764116.274, "dur": 117.957, + "args": { + "External id": 4054920,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[51384320], [6423040], [], [], []], "Ev Idx": 1927 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336756, "tid": 1381189, + "ts": 1655274764147.706, "dur": 83.219, + "args": { + "External id": 4054921,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 3, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "3", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 51384320, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[6423040], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 1928, "In msg nelems": 6423040 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 1336756, "tid": 1381189, + "ts": 1655274764156.979, "dur": 69.938, + "args": { + "External id": 4054922,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[6423040]], "Ev Idx": 1929 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336756, "tid": 1381189, + "ts": 1655274764251.775, "dur": 1.698, + "args": { + "External id": 4054923,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "3", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 1930, "In msg nelems": 0, "Rank": 3, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1655274764328.570, "dur": 1580.221, + "args": { + "External id": 4054924,"Sequence number": 40618404, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 1931 + } + }, + { + "ph": "f", "id": 176, "pid": 1336756, "tid": 1381189, "ts": 1655274764328.570, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655274764454.896, "dur": 105.295, + "args": { + "External id": 4054925,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [5632, 1], [5632, 1]], "Input Dims": [[65536, 2048], [2048, 5632], [65536, 5632]], "Ev Idx": 1932 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_add_mul_rsub_silu_0", "pid": 1336756, "tid": 1381189, + "ts": 1655274764601.173, "dur": 35.887, + "args": { + "External id": 4054926,"kernel_hash": "c2zszzsomz26dv2qwvmiurvgyrl5qxtyn6ocoqkdpzzhfzwqp5q6", "grid": "grid(369098752,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "369098752"], "kernel_file": "/tmp/torchinductor_cvm/2z/c2zszzsomz26dv2qwvmiurvgyrl5qxtyn6ocoqkdpzzhfzwqp5q6.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[5632, 1], [5632, 1], [5632, 1], [23068672, 5632, 1], [23068672, 5632, 1], [23068672, 5632, 1], []], "Input Dims": [[65536, 5632], [65536, 5632], [65536, 5632], [16, 4096, 5632], [16, 4096, 5632], [16, 4096, 5632], []], "Ev Idx": 1933 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 1336756, "tid": 1381189, + "ts": 1655274764652.410, "dur": 47.201, + "args": { + "External id": 4054927,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[0, 1, 2048], [0, 5632, 1], [11534336, 5632, 1]], "Input Dims": [[1, 2048, 65536], [1, 65536, 5632], [1, 2048, 5632]], "Ev Idx": 1934 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655274764710.666, "dur": 31.708, + "args": { + "External id": 4054928,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 5632], [2048, 1], [2048, 1]], "Input Dims": [[5632, 65536], [65536, 2048], [5632, 2048]], "Ev Idx": 1935 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655274764748.692, "dur": 45.671, + "args": { + "External id": 4054929,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 5632], [5632, 2048], [65536, 2048]], "Ev Idx": 1936 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655274764800.471, "dur": 27.303, + "args": { + "External id": 4054930,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 5632], [2048, 1], [2048, 1]], "Input Dims": [[5632, 65536], [65536, 2048], [5632, 2048]], "Ev Idx": 1937 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655274764842.416, "dur": 42.870, + "args": { + "External id": 4054931,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 5632], [5632, 2048], [65536, 2048]], "Ev Idx": 1938 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_1", "pid": 1336756, "tid": 1381189, + "ts": 1655274764913.258, "dur": 21.953, + "args": { + "External id": 4054932,"kernel_hash": "cjd6g3jfgntyoifzno6l2urmnhif7alxtw6zz7miov66vywxwv7d", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/jd/cjd6g3jfgntyoifzno6l2urmnhif7alxtw6zz7miov66vywxwv7d.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[65536, 2048], [65536, 2048], []], "Ev Idx": 1939 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 1336756, "tid": 1381189, + "ts": 1655274764951.573, "dur": 27.610, + "args": { + "External id": 4054933,"kernel_hash": "cxhg545cyph4gbk5vymzyh72vho7oogk3ycan2lp4cxntklp5hew", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "65536", "2048", "1", "497", "132", "True", "2048", "True", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/xh/cxhg545cyph4gbk5vymzyh72vho7oogk3ycan2lp4cxntklp5hew.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [1], [2048, 1], [2048, 1], [2048, 1], [2048, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [2048], [65536, 2048], [65536, 2048], [132, 2048], [65536, 2048], [65536], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 1940 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 1336756, "tid": 1381189, + "ts": 1655274765043.504, "dur": 20.223, + "args": { + "External id": 4054934,"kernel_hash": "cu42i6zmxtvs2i7cs6x4ixaexke3lhgdiaye5oxwm7s3u6em6co4", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "66"], "kernel_file": "/tmp/torchinductor_cvm/u4/cu42i6zmxtvs2i7cs6x4ixaexke3lhgdiaye5oxwm7s3u6em6co4.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [4096, 1, 2048], [], []], "Input Dims": [[132, 2048], [1, 2048, 2], [], []], "Ev Idx": 1941 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 1336756, "tid": 1381189, + "ts": 1655274765081.932, "dur": 14.729, + "args": { + "External id": 4054935,"kernel_hash": "ckihofrorhmzazt2wfn2dz2m5wfx3auisu2gvfo2jsepr4zyekmq", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "2"], "kernel_file": "/tmp/torchinductor_cvm/ki/ckihofrorhmzazt2wfn2dz2m5wfx3auisu2gvfo2jsepr4zyekmq.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1, 2048], [2048, 1], [], []], "Input Dims": [[1, 2048, 2], [1, 2048], [], []], "Ev Idx": 1942 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655274765106.075, "dur": 32.968, + "args": { + "External id": 4054936,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 1943 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655274765141.965, "dur": 33.125, + "args": { + "External id": 4054937,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 1944 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 1336756, "tid": 1381189, + "ts": 1655274765202.926, "dur": 169.695, + "args": { + "External id": 4054938,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.125", "True", "-1", "-1", "0.", "", "False", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar", "long int"], "Input Strides": [[8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [131072, 4096, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 32, 4096], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 1945 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655274765282.958, "dur": 7.381, + "args": { + "External id": 4054939,"Record function id": 0, "Concrete Inputs": ["[16, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1946 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655274765292.322, "dur": 2.066, + "args": { + "External id": 4054940,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 1947 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336756, "tid": 1381189, + "ts": 1655274765404.980, "dur": 41.928, + "args": { + "External id": 4054941,"kernel_hash": "cb6oumcqb462ndf2ivcd2sc6qg6mfjahptjw4ih7cesqhfpziv3b", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/b6/cb6oumcqb462ndf2ivcd2sc6qg6mfjahptjw4ih7cesqhfpziv3b.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 1948 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336756, "tid": 1381189, + "ts": 1655274765460.545, "dur": 14.184, + "args": { + "External id": 4054942,"kernel_hash": "cb6oumcqb462ndf2ivcd2sc6qg6mfjahptjw4ih7cesqhfpziv3b", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/b6/cb6oumcqb462ndf2ivcd2sc6qg6mfjahptjw4ih7cesqhfpziv3b.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 1949 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655274765484.194, "dur": 37.835, + "args": { + "External id": 4054943,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 1950 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655274765527.476, "dur": 35.170, + "args": { + "External id": 4054944,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 1951 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655274765570.684, "dur": 20.508, + "args": { + "External id": 4054945,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 1952 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655274765595.345, "dur": 29.510, + "args": { + "External id": 4054946,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 1953 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655274765629.747, "dur": 19.377, + "args": { + "External id": 4054947,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 1954 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655274765655.143, "dur": 29.169, + "args": { + "External id": 4054948,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 1955 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_4", "pid": 1336756, "tid": 1381189, + "ts": 1655274765706.004, "dur": 33.712, + "args": { + "External id": 4054949,"kernel_hash": "c7pqhdjojzeazwsh5g3ibnyk4m2nfh3q73e3zc7hljz4yvhe7c4h", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/7p/c7pqhdjojzeazwsh5g3ibnyk4m2nfh3q73e3zc7hljz4yvhe7c4h.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1], []], "Input Dims": [[65536, 2048], [65536, 2048], [65536, 2048], []], "Ev Idx": 1956 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_2", "pid": 1336756, "tid": 1381189, + "ts": 1655274765766.422, "dur": 23.487, + "args": { + "External id": 4054950,"kernel_hash": "cvgvwkysjpcw75q5t3guce5bep2so25f7i5zxc6ipt5f56shof73", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "65536", "2048", "1", "497", "132", "True", "2048", "False", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/vg/cvgvwkysjpcw75q5t3guce5bep2so25f7i5zxc6ipt5f56shof73.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [1], [2048, 1], [2048, 1], [2048, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [2048], [65536, 2048], [65536, 2048], [132, 2048], [65536], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 1957 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 1336756, "tid": 1381189, + "ts": 1655274765804.045, "dur": 16.646, + "args": { + "External id": 4054951,"kernel_hash": "cu42i6zmxtvs2i7cs6x4ixaexke3lhgdiaye5oxwm7s3u6em6co4", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "66"], "kernel_file": "/tmp/torchinductor_cvm/u4/cu42i6zmxtvs2i7cs6x4ixaexke3lhgdiaye5oxwm7s3u6em6co4.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [4096, 1, 2048], [], []], "Input Dims": [[132, 2048], [1, 2048, 2], [], []], "Ev Idx": 1958 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 1336756, "tid": 1381189, + "ts": 1655274765839.898, "dur": 12.411, + "args": { + "External id": 4054952,"kernel_hash": "ckihofrorhmzazt2wfn2dz2m5wfx3auisu2gvfo2jsepr4zyekmq", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "2"], "kernel_file": "/tmp/torchinductor_cvm/ki/ckihofrorhmzazt2wfn2dz2m5wfx3auisu2gvfo2jsepr4zyekmq.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1, 2048], [2048, 1], [], []], "Input Dims": [[1, 2048, 2], [1, 2048], [], []], "Ev Idx": 1959 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_5", "pid": 1336756, "tid": 1381189, + "ts": 1655274765864.707, "dur": 14.600, + "args": { + "External id": 4054953,"kernel_hash": "cckrpn5uuxyvbancoio3sz2onrjto236n54xx4ycphq5p6r3jlfj", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/ck/cckrpn5uuxyvbancoio3sz2onrjto236n54xx4ycphq5p6r3jlfj.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [8388608, 2048, 1], []], "Input Dims": [[65536, 2048], [65536, 2048], [16, 4096, 2048], []], "Ev Idx": 1960 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274765950.671, "dur": 14.559, + "args": { + "External id": 4054954,"Record function id": 0, "Ev Idx": 1961 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274765953.657, "dur": 10.575, + "args": { + "External id": 4054955,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 1962 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274765957.672, "dur": 5.605, + "args": { + "External id": 4054956,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 1963 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274765959.246, "dur": 3.944, + "args": { + "External id": 4054957,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 1964 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274765968.906, "dur": 6.294, + "args": { + "External id": 4054958,"Record function id": 0, "Ev Idx": 1965 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274765970.148, "dur": 4.622, + "args": { + "External id": 4054959,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 1966 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274765970.843, "dur": 3.439, + "args": { + "External id": 4054960,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 1967 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274765971.344, "dur": 2.851, + "args": { + "External id": 4054961,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 1968 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274765978.403, "dur": 5.333, + "args": { + "External id": 4054962,"Record function id": 0, "Ev Idx": 1969 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274765980.367, "dur": 2.912, + "args": { + "External id": 4054963,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 1970 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274765980.969, "dur": 1.888, + "args": { + "External id": 4054964,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 1971 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274765981.943, "dur": 0.834, + "args": { + "External id": 4054965,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 1972 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274766024.310, "dur": 6.968, + "args": { + "External id": 4054966,"Record function id": 0, "Ev Idx": 1973 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274766026.129, "dur": 4.532, + "args": { + "External id": 4054967,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 1974 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274766027.218, "dur": 2.448, + "args": { + "External id": 4054968,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 1975 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274766028.056, "dur": 1.425, + "args": { + "External id": 4054969,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 1976 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274766034.409, "dur": 3.719, + "args": { + "External id": 4054970,"Record function id": 0, "Ev Idx": 1977 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274766035.569, "dur": 2.154, + "args": { + "External id": 4054971,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 1978 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274766036.275, "dur": 1.038, + "args": { + "External id": 4054972,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 1979 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274766036.688, "dur": 0.553, + "args": { + "External id": 4054973,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 1980 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274766041.073, "dur": 3.677, + "args": { + "External id": 4054974,"Record function id": 0, "Ev Idx": 1981 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274766042.223, "dur": 2.138, + "args": { + "External id": 4054975,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 1982 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274766042.737, "dur": 1.169, + "args": { + "External id": 4054976,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 1983 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274766043.250, "dur": 0.582, + "args": { + "External id": 4054977,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 1984 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274766047.957, "dur": 5.324, + "args": { + "External id": 4054978,"Record function id": 0, "Ev Idx": 1985 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274766048.888, "dur": 3.997, + "args": { + "External id": 4054979,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 1986 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274766049.362, "dur": 3.108, + "args": { + "External id": 4054980,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 1987 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274766051.743, "dur": 0.656, + "args": { + "External id": 4054981,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 1988 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274766056.324, "dur": 3.513, + "args": { + "External id": 4054982,"Record function id": 0, "Ev Idx": 1989 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274766057.303, "dur": 2.144, + "args": { + "External id": 4054983,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 1990 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274766057.882, "dur": 1.130, + "args": { + "External id": 4054984,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 1991 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274766058.179, "dur": 0.759, + "args": { + "External id": 4054985,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 1992 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274766062.854, "dur": 5.151, + "args": { + "External id": 4054986,"Record function id": 0, "Ev Idx": 1993 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274766063.883, "dur": 3.732, + "args": { + "External id": 4054987,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 1994 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274766064.404, "dur": 2.750, + "args": { + "External id": 4054988,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 1995 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274766064.678, "dur": 2.407, + "args": { + "External id": 4054989,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 1996 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RegisterPostBackwardFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1655274766071.510, "dur": 39755.704, + "args": { + "External id": 4054990,"Record function id": 0, "Sequence number": 40618403, "Fwd thread id": 1, "Ev Idx": 1997 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1655274766072.822, "dur": 39746.200, + "args": { + "External id": 4054991,"Sequence number": 40618403, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 1998 + } + }, + { + "ph": "f", "id": 177, "pid": 1336756, "tid": 1381189, "ts": 1655274766072.822, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.25)", "pid": 1336756, "tid": 1381189, + "ts": 1655274766104.067, "dur": 36.795, + "args": { + "External id": 4054992,"Record function id": 0, "Ev Idx": 1999 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.25)", "pid": 1336756, "tid": 1381189, + "ts": 1655274766148.963, "dur": 59.794, + "args": { + "External id": 4054993,"Record function id": 0, "Ev Idx": 2000 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.25)", "pid": 1336756, "tid": 1381189, + "ts": 1655274766218.234, "dur": 39593.574, + "args": { + "External id": 4054994,"Record function id": 0, "Ev Idx": 2001 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655274766304.975, "dur": 7.107, + "args": { + "External id": 4054995,"Record function id": 0, "Concrete Inputs": ["[51384320]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2002 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274766321.383, "dur": 4.745, + "args": { + "External id": 4054996,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[51384320], []], "Ev Idx": 2003 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::chunk_cat", "pid": 1336756, "tid": 1381189, + "ts": 1655274766340.528, "dur": 38764.170, + "args": { + "External id": 4054997,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [2048, 1], [2048, 1], [2048, 1], [2048, 1], [1], [2048, 1], [2048, 1], [5632, 1]], [], [], [6423040, 1]], "Input Dims": [[[2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048], [5632, 2048], [5632, 2048], [2048, 5632]], [], [], [8, 6423040]], "Ev Idx": 2004 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_chunk_cat", "pid": 1336756, "tid": 1381189, + "ts": 1655274766353.615, "dur": 38742.344, + "args": { + "External id": 4054998,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [2048, 1], [2048, 1], [2048, 1], [2048, 1], [1], [2048, 1], [2048, 1], [5632, 1]], [], [], [6423040, 1]], "Input Dims": [[[2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048], [5632, 2048], [5632, 2048], [2048, 5632]], [], [], [8, 6423040]], "Ev Idx": 2005 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655274766404.220, "dur": 30.721, + "args": { + "External id": 4054999,"Record function id": 0, "Concrete Inputs": ["[12602]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2006 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1381189, + "ts": 1655274766442.009, "dur": 38617.375, + "args": { + "External id": 4055000,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[12602], [], [], [], [], [], [], []], "Ev Idx": 2007 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336756, "tid": 1381189, + "ts": 1655274766444.506, "dur": 38614.302, + "args": { + "External id": 4055001,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[12602], [], [], [], [], [], []], "Ev Idx": 2008 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274766448.265, "dur": 6.897, + "args": { + "External id": 4055002,"Record function id": 0, "Concrete Inputs": ["[12602]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2009 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1381189, + "ts": 1655274766456.802, "dur": 38598.181, + "args": { + "External id": 4055003,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[12602], [12602], []], "Ev Idx": 2010 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 1336756, "tid": 1381189, + "ts": 1655274805190.277, "dur": 8.292, + "args": { + "External id": 4055004,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "", "", "", "False"], "Input type": ["float", "ScalarList", "", "", "", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[51384320], [], [], [], [], []], "Ev Idx": 2011 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655274805193.031, "dur": 5.134, + "args": { + "External id": 4055005,"Record function id": 0, "Concrete Inputs": ["[6423040]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2012 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_reduce_scatter_base_", "pid": 1336756, "tid": 1381189, + "ts": 1655274805230.812, "dur": 304.444, + "args": { + "External id": 4055006,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "-1"], "Input type": ["float", "float", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], [], []], "Input Dims": [[6423040], [51384320], [], [], [], []], "Ev Idx": 2013 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336756, "tid": 1381189, + "ts": 1655274805261.870, "dur": 268.466, + "args": { + "External id": 4055007,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 3, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "3", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 6423040, "Process Group Name": "0", "Input type": ["float", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[51384320], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 2014, "In msg nelems": 51384320 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_reduce_scatter_base", "pid": 1336756, "tid": 1381189, + "ts": 1655274805272.930, "dur": 251.798, + "args": { + "External id": 4055008,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[51384320]], "Ev Idx": 2015 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336756, "tid": 1381189, + "ts": 1655274805558.888, "dur": 2.498, + "args": { + "External id": 4055009,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "3", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 2016, "In msg nelems": 0, "Rank": 3, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274805617.036, "dur": 6.728, + "args": { + "External id": 4055010,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2017 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274805666.906, "dur": 3.564, + "args": { + "External id": 4055011,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "256"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2018 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274805685.524, "dur": 1.176, + "args": { + "External id": 4055012,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "524544"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2019 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274805696.916, "dur": 0.792, + "args": { + "External id": 4055013,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "1048832"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2020 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274805708.569, "dur": 0.933, + "args": { + "External id": 4055014,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "1573120"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2021 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274805718.000, "dur": 2.759, + "args": { + "External id": 4055015,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2022 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274805732.576, "dur": 0.926, + "args": { + "External id": 4055016,"Record function id": 0, "Concrete Inputs": ["", "[704, 2048]", "[2048, 1]", "2097664"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2023 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274805744.358, "dur": 2.110, + "args": { + "External id": 4055017,"Record function id": 0, "Concrete Inputs": ["", "[704, 2048]", "[2048, 1]", "3539456"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2024 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274805754.625, "dur": 0.677, + "args": { + "External id": 4055018,"Record function id": 0, "Concrete Inputs": ["", "[256, 5632]", "[5632, 1]", "4981248"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2025 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: CompiledFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1655274805840.926, "dur": 2664.830, + "args": { + "External id": 4055019,"Record function id": 0, "Ev Idx": 2026 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.24)", "pid": 1336756, "tid": 1381189, + "ts": 1655274805859.164, "dur": 1012.275, + "args": { + "External id": 4055020,"Record function id": 0, "Ev Idx": 2027 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.24)", "pid": 1336756, "tid": 1381189, + "ts": 1655274805871.594, "dur": 340.317, + "args": { + "External id": 4055021,"Record function id": 0, "Ev Idx": 2028 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274805944.057, "dur": 5.696, + "args": { + "External id": 4055022,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[51384320], []], "Ev Idx": 2029 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274805952.895, "dur": 0.854, + "args": { + "External id": 4055023,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 2030 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274805957.909, "dur": 0.772, + "args": { + "External id": 4055024,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 2031 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274805960.237, "dur": 0.693, + "args": { + "External id": 4055025,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 2032 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274805962.283, "dur": 0.824, + "args": { + "External id": 4055026,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 2033 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274805964.547, "dur": 0.560, + "args": { + "External id": 4055027,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 2034 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274805968.218, "dur": 1.529, + "args": { + "External id": 4055028,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 2035 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274805970.877, "dur": 0.717, + "args": { + "External id": 4055029,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 2036 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274805972.836, "dur": 2.317, + "args": { + "External id": 4055030,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 2037 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274805976.312, "dur": 0.820, + "args": { + "External id": 4055031,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 2038 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 1336756, "tid": 1381189, + "ts": 1655274806033.488, "dur": 148.379, + "args": { + "External id": 4055032,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 2039 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 1336756, "tid": 1381189, + "ts": 1655274806050.622, "dur": 126.852, + "args": { + "External id": 4055033,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 2040 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655274806070.082, "dur": 12.250, + "args": { + "External id": 4055034,"Record function id": 0, "Concrete Inputs": ["[2133]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2041 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1381189, + "ts": 1655274806085.280, "dur": 65.874, + "args": { + "External id": 4055035,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], [], []], "Ev Idx": 2042 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336756, "tid": 1381189, + "ts": 1655274806087.579, "dur": 63.252, + "args": { + "External id": 4055036,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], []], "Ev Idx": 2043 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274806092.153, "dur": 6.679, + "args": { + "External id": 4055037,"Record function id": 0, "Concrete Inputs": ["[2133]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2044 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1381189, + "ts": 1655274806100.524, "dur": 49.758, + "args": { + "External id": 4055038,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[2133], [2133], []], "Ev Idx": 2045 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::backward_prefetch for model.layers.23", "pid": 1336756, "tid": 1381189, + "ts": 1655274806282.498, "dur": 581.795, + "args": { + "External id": 4055039,"Record function id": 0, "Ev Idx": 2046 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.23)", "pid": 1336756, "tid": 1381189, + "ts": 1655274806297.278, "dur": 555.253, + "args": { + "External id": 4055040,"Record function id": 0, "Ev Idx": 2047 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655274806370.801, "dur": 5.119, + "args": { + "External id": 4055041,"Record function id": 0, "Concrete Inputs": ["[6423040]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2048 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336756, "tid": 1381189, + "ts": 1655274806391.023, "dur": 48.319, + "args": { + "External id": 4055042,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 2049 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274806394.837, "dur": 2.986, + "args": { + "External id": 4055043,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2050 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274806399.495, "dur": 0.491, + "args": { + "External id": 4055044,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2051 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274806401.475, "dur": 0.351, + "args": { + "External id": 4055045,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2052 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274806405.052, "dur": 2.072, + "args": { + "External id": 4055046,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2053 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274806408.363, "dur": 0.324, + "args": { + "External id": 4055047,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2054 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274806409.926, "dur": 0.331, + "args": { + "External id": 4055048,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2055 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274806412.469, "dur": 0.267, + "args": { + "External id": 4055049,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2056 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274806414.325, "dur": 15.959, + "args": { + "External id": 4055050,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2057 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274806432.929, "dur": 1.279, + "args": { + "External id": 4055051,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2058 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336756, "tid": 1381189, + "ts": 1655274806449.954, "dur": 34.250, + "args": { + "External id": 4055052,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 2059 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 1336756, "tid": 1381189, + "ts": 1655274806516.506, "dur": 103.491, + "args": { + "External id": 4055053,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "6423040", "8", "3", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [], [], [], [], [], []], "Ev Idx": 2060 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655274806526.767, "dur": 4.450, + "args": { + "External id": 4055054,"Record function id": 0, "Concrete Inputs": ["[51384320]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2061 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 1336756, "tid": 1381189, + "ts": 1655274806536.336, "dur": 9.587, + "args": { + "External id": 4055055,"Record function id": 0, "Concrete Inputs": ["", "0", "19269120", "6423040"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 2062 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1381189, + "ts": 1655274806540.441, "dur": 5.040, + "args": { + "External id": 4055056,"Record function id": 0, "Concrete Inputs": ["", "0", "19269120", "25692160", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[51384320], [], [], [], []], "Ev Idx": 2063 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274806543.899, "dur": 0.375, + "args": { + "External id": 4055057,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "[1]", "19269120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 2064 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336756, "tid": 1381189, + "ts": 1655274806553.351, "dur": 28.244, + "args": { + "External id": 4055058,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 2065 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274806555.829, "dur": 2.283, + "args": { + "External id": 4055059,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "19269120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2066 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274806559.899, "dur": 0.345, + "args": { + "External id": 4055060,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "19269376"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2067 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274806561.814, "dur": 1.015, + "args": { + "External id": 4055061,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "19793664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2068 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274806564.374, "dur": 0.267, + "args": { + "External id": 4055062,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "20317952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2069 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274806566.075, "dur": 0.244, + "args": { + "External id": 4055063,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "20842240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2070 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274806568.783, "dur": 0.336, + "args": { + "External id": 4055064,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "21366528"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2071 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274806570.868, "dur": 0.260, + "args": { + "External id": 4055065,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "21366784"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2072 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274806572.506, "dur": 0.353, + "args": { + "External id": 4055066,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "22808576"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2073 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274806575.515, "dur": 2.056, + "args": { + "External id": 4055067,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "24250368"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2074 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336756, "tid": 1381189, + "ts": 1655274806595.092, "dur": 17.779, + "args": { + "External id": 4055068,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 2075 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 1336756, "tid": 1381189, + "ts": 1655274806665.958, "dur": 118.461, + "args": { + "External id": 4055069,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[51384320], [6423040], [], [], []], "Ev Idx": 2076 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336756, "tid": 1381189, + "ts": 1655274806694.231, "dur": 86.813, + "args": { + "External id": 4055070,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 3, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "3", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 51384320, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[6423040], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 2077, "In msg nelems": 6423040 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 1336756, "tid": 1381189, + "ts": 1655274806703.554, "dur": 73.643, + "args": { + "External id": 4055071,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[6423040]], "Ev Idx": 2078 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336756, "tid": 1381189, + "ts": 1655274806802.165, "dur": 1.637, + "args": { + "External id": 4055072,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "3", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 2079, "In msg nelems": 0, "Rank": 3, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1655274806878.232, "dur": 1608.555, + "args": { + "External id": 4055073,"Sequence number": 40618402, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 2080 + } + }, + { + "ph": "f", "id": 178, "pid": 1336756, "tid": 1381189, "ts": 1655274806878.232, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655274807022.374, "dur": 106.523, + "args": { + "External id": 4055074,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [5632, 1], [5632, 1]], "Input Dims": [[65536, 2048], [2048, 5632], [65536, 5632]], "Ev Idx": 2081 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_add_mul_rsub_silu_0", "pid": 1336756, "tid": 1381189, + "ts": 1655274807172.269, "dur": 35.870, + "args": { + "External id": 4055075,"kernel_hash": "c2zszzsomz26dv2qwvmiurvgyrl5qxtyn6ocoqkdpzzhfzwqp5q6", "grid": "grid(369098752,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "369098752"], "kernel_file": "/tmp/torchinductor_cvm/2z/c2zszzsomz26dv2qwvmiurvgyrl5qxtyn6ocoqkdpzzhfzwqp5q6.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[5632, 1], [5632, 1], [5632, 1], [23068672, 5632, 1], [23068672, 5632, 1], [23068672, 5632, 1], []], "Input Dims": [[65536, 5632], [65536, 5632], [65536, 5632], [16, 4096, 5632], [16, 4096, 5632], [16, 4096, 5632], []], "Ev Idx": 2082 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 1336756, "tid": 1381189, + "ts": 1655274807226.294, "dur": 47.373, + "args": { + "External id": 4055076,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[0, 1, 2048], [0, 5632, 1], [11534336, 5632, 1]], "Input Dims": [[1, 2048, 65536], [1, 65536, 5632], [1, 2048, 5632]], "Ev Idx": 2083 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655274807283.250, "dur": 32.451, + "args": { + "External id": 4055077,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 5632], [2048, 1], [2048, 1]], "Input Dims": [[5632, 65536], [65536, 2048], [5632, 2048]], "Ev Idx": 2084 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655274807322.028, "dur": 45.362, + "args": { + "External id": 4055078,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 5632], [5632, 2048], [65536, 2048]], "Ev Idx": 2085 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655274807374.481, "dur": 27.641, + "args": { + "External id": 4055079,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 5632], [2048, 1], [2048, 1]], "Input Dims": [[5632, 65536], [65536, 2048], [5632, 2048]], "Ev Idx": 2086 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655274807411.172, "dur": 62.115, + "args": { + "External id": 4055080,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 5632], [5632, 2048], [65536, 2048]], "Ev Idx": 2087 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_1", "pid": 1336756, "tid": 1381189, + "ts": 1655274807501.433, "dur": 22.426, + "args": { + "External id": 4055081,"kernel_hash": "cjd6g3jfgntyoifzno6l2urmnhif7alxtw6zz7miov66vywxwv7d", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/jd/cjd6g3jfgntyoifzno6l2urmnhif7alxtw6zz7miov66vywxwv7d.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[65536, 2048], [65536, 2048], []], "Ev Idx": 2088 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 1336756, "tid": 1381189, + "ts": 1655274807545.109, "dur": 25.904, + "args": { + "External id": 4055082,"kernel_hash": "cxhg545cyph4gbk5vymzyh72vho7oogk3ycan2lp4cxntklp5hew", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "65536", "2048", "1", "497", "132", "True", "2048", "True", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/xh/cxhg545cyph4gbk5vymzyh72vho7oogk3ycan2lp4cxntklp5hew.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [1], [2048, 1], [2048, 1], [2048, 1], [2048, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [2048], [65536, 2048], [65536, 2048], [132, 2048], [65536, 2048], [65536], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 2089 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 1336756, "tid": 1381189, + "ts": 1655274807589.340, "dur": 19.233, + "args": { + "External id": 4055083,"kernel_hash": "cu42i6zmxtvs2i7cs6x4ixaexke3lhgdiaye5oxwm7s3u6em6co4", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "66"], "kernel_file": "/tmp/torchinductor_cvm/u4/cu42i6zmxtvs2i7cs6x4ixaexke3lhgdiaye5oxwm7s3u6em6co4.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [4096, 1, 2048], [], []], "Input Dims": [[132, 2048], [1, 2048, 2], [], []], "Ev Idx": 2090 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 1336756, "tid": 1381189, + "ts": 1655274807623.513, "dur": 12.900, + "args": { + "External id": 4055084,"kernel_hash": "ckihofrorhmzazt2wfn2dz2m5wfx3auisu2gvfo2jsepr4zyekmq", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "2"], "kernel_file": "/tmp/torchinductor_cvm/ki/ckihofrorhmzazt2wfn2dz2m5wfx3auisu2gvfo2jsepr4zyekmq.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1, 2048], [2048, 1], [], []], "Input Dims": [[1, 2048, 2], [1, 2048], [], []], "Ev Idx": 2091 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655274807646.525, "dur": 30.648, + "args": { + "External id": 4055085,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 2092 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655274807680.485, "dur": 32.567, + "args": { + "External id": 4055086,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 2093 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 1336756, "tid": 1381189, + "ts": 1655274807744.283, "dur": 164.376, + "args": { + "External id": 4055087,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.125", "True", "-1", "-1", "0.", "", "False", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar", "long int"], "Input Strides": [[8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [131072, 4096, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 32, 4096], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 2094 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655274807819.578, "dur": 5.230, + "args": { + "External id": 4055088,"Record function id": 0, "Concrete Inputs": ["[16, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2095 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655274807826.789, "dur": 2.303, + "args": { + "External id": 4055089,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2096 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336756, "tid": 1381189, + "ts": 1655274807939.017, "dur": 23.457, + "args": { + "External id": 4055090,"kernel_hash": "cb6oumcqb462ndf2ivcd2sc6qg6mfjahptjw4ih7cesqhfpziv3b", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/b6/cb6oumcqb462ndf2ivcd2sc6qg6mfjahptjw4ih7cesqhfpziv3b.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 2097 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336756, "tid": 1381189, + "ts": 1655274807973.654, "dur": 50.989, + "args": { + "External id": 4055091,"kernel_hash": "cb6oumcqb462ndf2ivcd2sc6qg6mfjahptjw4ih7cesqhfpziv3b", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/b6/cb6oumcqb462ndf2ivcd2sc6qg6mfjahptjw4ih7cesqhfpziv3b.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 2098 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655274808036.713, "dur": 40.896, + "args": { + "External id": 4055092,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 2099 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655274808084.916, "dur": 34.533, + "args": { + "External id": 4055093,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 2100 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655274808126.826, "dur": 19.697, + "args": { + "External id": 4055094,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 2101 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655274808150.513, "dur": 29.964, + "args": { + "External id": 4055095,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 2102 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655274808185.503, "dur": 19.252, + "args": { + "External id": 4055096,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 2103 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655274808213.336, "dur": 29.143, + "args": { + "External id": 4055097,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 2104 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_4", "pid": 1336756, "tid": 1381189, + "ts": 1655274808262.207, "dur": 22.460, + "args": { + "External id": 4055098,"kernel_hash": "c7pqhdjojzeazwsh5g3ibnyk4m2nfh3q73e3zc7hljz4yvhe7c4h", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/7p/c7pqhdjojzeazwsh5g3ibnyk4m2nfh3q73e3zc7hljz4yvhe7c4h.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1], []], "Input Dims": [[65536, 2048], [65536, 2048], [65536, 2048], []], "Ev Idx": 2105 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_2", "pid": 1336756, "tid": 1381189, + "ts": 1655274808318.817, "dur": 26.172, + "args": { + "External id": 4055099,"kernel_hash": "cvgvwkysjpcw75q5t3guce5bep2so25f7i5zxc6ipt5f56shof73", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "65536", "2048", "1", "497", "132", "True", "2048", "False", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/vg/cvgvwkysjpcw75q5t3guce5bep2so25f7i5zxc6ipt5f56shof73.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [1], [2048, 1], [2048, 1], [2048, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [2048], [65536, 2048], [65536, 2048], [132, 2048], [65536], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 2106 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 1336756, "tid": 1381189, + "ts": 1655274808359.744, "dur": 16.275, + "args": { + "External id": 4055100,"kernel_hash": "cu42i6zmxtvs2i7cs6x4ixaexke3lhgdiaye5oxwm7s3u6em6co4", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "66"], "kernel_file": "/tmp/torchinductor_cvm/u4/cu42i6zmxtvs2i7cs6x4ixaexke3lhgdiaye5oxwm7s3u6em6co4.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [4096, 1, 2048], [], []], "Input Dims": [[132, 2048], [1, 2048, 2], [], []], "Ev Idx": 2107 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 1336756, "tid": 1381189, + "ts": 1655274808393.682, "dur": 16.157, + "args": { + "External id": 4055101,"kernel_hash": "ckihofrorhmzazt2wfn2dz2m5wfx3auisu2gvfo2jsepr4zyekmq", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "2"], "kernel_file": "/tmp/torchinductor_cvm/ki/ckihofrorhmzazt2wfn2dz2m5wfx3auisu2gvfo2jsepr4zyekmq.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1, 2048], [2048, 1], [], []], "Input Dims": [[1, 2048, 2], [1, 2048], [], []], "Ev Idx": 2108 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_5", "pid": 1336756, "tid": 1381189, + "ts": 1655274808438.187, "dur": 20.979, + "args": { + "External id": 4055102,"kernel_hash": "cckrpn5uuxyvbancoio3sz2onrjto236n54xx4ycphq5p6r3jlfj", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/ck/cckrpn5uuxyvbancoio3sz2onrjto236n54xx4ycphq5p6r3jlfj.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [8388608, 2048, 1], []], "Input Dims": [[65536, 2048], [65536, 2048], [16, 4096, 2048], []], "Ev Idx": 2109 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274808527.778, "dur": 16.986, + "args": { + "External id": 4055103,"Record function id": 0, "Ev Idx": 2110 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274808531.433, "dur": 12.479, + "args": { + "External id": 4055104,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 2111 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274808535.892, "dur": 7.144, + "args": { + "External id": 4055105,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 2112 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274808537.146, "dur": 5.779, + "args": { + "External id": 4055106,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 2113 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274808548.603, "dur": 4.068, + "args": { + "External id": 4055107,"Record function id": 0, "Ev Idx": 2114 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274808549.862, "dur": 2.391, + "args": { + "External id": 4055108,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 2115 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274808550.508, "dur": 1.256, + "args": { + "External id": 4055109,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 2116 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274808550.944, "dur": 0.727, + "args": { + "External id": 4055110,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 2117 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274808555.870, "dur": 4.238, + "args": { + "External id": 4055111,"Record function id": 0, "Ev Idx": 2118 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274808557.098, "dur": 2.605, + "args": { + "External id": 4055112,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 2119 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274808557.605, "dur": 1.689, + "args": { + "External id": 4055113,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 2120 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274808558.291, "dur": 0.798, + "args": { + "External id": 4055114,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 2121 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274808563.296, "dur": 3.690, + "args": { + "External id": 4055115,"Record function id": 0, "Ev Idx": 2122 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274808564.451, "dur": 2.132, + "args": { + "External id": 4055116,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 2123 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274808565.039, "dur": 1.124, + "args": { + "External id": 4055117,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 2124 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274808565.463, "dur": 0.633, + "args": { + "External id": 4055118,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 2125 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274808570.131, "dur": 3.539, + "args": { + "External id": 4055119,"Record function id": 0, "Ev Idx": 2126 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274808571.223, "dur": 2.035, + "args": { + "External id": 4055120,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 2127 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274808571.907, "dur": 0.960, + "args": { + "External id": 4055121,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 2128 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274808572.158, "dur": 0.633, + "args": { + "External id": 4055122,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 2129 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274808576.744, "dur": 3.339, + "args": { + "External id": 4055123,"Record function id": 0, "Ev Idx": 2130 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274808577.856, "dur": 1.800, + "args": { + "External id": 4055124,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 2131 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274808578.304, "dur": 0.968, + "args": { + "External id": 4055125,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 2132 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274808578.640, "dur": 0.565, + "args": { + "External id": 4055126,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 2133 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274808583.342, "dur": 5.436, + "args": { + "External id": 4055127,"Record function id": 0, "Ev Idx": 2134 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274808584.395, "dur": 3.985, + "args": { + "External id": 4055128,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 2135 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274808584.824, "dur": 3.165, + "args": { + "External id": 4055129,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 2136 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274808587.282, "dur": 0.633, + "args": { + "External id": 4055130,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 2137 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274808591.858, "dur": 5.258, + "args": { + "External id": 4055131,"Record function id": 0, "Ev Idx": 2138 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274808592.960, "dur": 3.735, + "args": { + "External id": 4055132,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 2139 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274808593.449, "dur": 2.859, + "args": { + "External id": 4055133,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 2140 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274808593.766, "dur": 2.482, + "args": { + "External id": 4055134,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 2141 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274808600.088, "dur": 3.447, + "args": { + "External id": 4055135,"Record function id": 0, "Ev Idx": 2142 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274808601.152, "dur": 1.989, + "args": { + "External id": 4055136,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 2143 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274808601.672, "dur": 1.044, + "args": { + "External id": 4055137,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 2144 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274808601.948, "dur": 0.694, + "args": { + "External id": 4055138,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 2145 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RegisterPostBackwardFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1655274808607.282, "dur": 39552.205, + "args": { + "External id": 4055139,"Record function id": 0, "Sequence number": 40618401, "Fwd thread id": 1, "Ev Idx": 2146 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1655274808608.476, "dur": 39541.892, + "args": { + "External id": 4055140,"Sequence number": 40618401, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 2147 + } + }, + { + "ph": "f", "id": 179, "pid": 1336756, "tid": 1381189, "ts": 1655274808608.476, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.24)", "pid": 1336756, "tid": 1381189, + "ts": 1655274808635.605, "dur": 38.450, + "args": { + "External id": 4055141,"Record function id": 0, "Ev Idx": 2148 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.24)", "pid": 1336756, "tid": 1381189, + "ts": 1655274808681.630, "dur": 59.843, + "args": { + "External id": 4055142,"Record function id": 0, "Ev Idx": 2149 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.24)", "pid": 1336756, "tid": 1381189, + "ts": 1655274808752.297, "dur": 39390.051, + "args": { + "External id": 4055143,"Record function id": 0, "Ev Idx": 2150 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655274808839.605, "dur": 6.294, + "args": { + "External id": 4055144,"Record function id": 0, "Concrete Inputs": ["[51384320]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2151 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274808855.643, "dur": 4.811, + "args": { + "External id": 4055145,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[51384320], []], "Ev Idx": 2152 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::chunk_cat", "pid": 1336756, "tid": 1381189, + "ts": 1655274808874.282, "dur": 38373.446, + "args": { + "External id": 4055146,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [2048, 1], [2048, 1], [2048, 1], [2048, 1], [1], [2048, 1], [2048, 1], [5632, 1]], [], [], [6423040, 1]], "Input Dims": [[[2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048], [5632, 2048], [5632, 2048], [2048, 5632]], [], [], [8, 6423040]], "Ev Idx": 2153 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_chunk_cat", "pid": 1336756, "tid": 1381189, + "ts": 1655274808887.812, "dur": 38350.768, + "args": { + "External id": 4055147,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [2048, 1], [2048, 1], [2048, 1], [2048, 1], [1], [2048, 1], [2048, 1], [5632, 1]], [], [], [6423040, 1]], "Input Dims": [[[2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048], [5632, 2048], [5632, 2048], [2048, 5632]], [], [], [8, 6423040]], "Ev Idx": 2154 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655274808938.946, "dur": 13.304, + "args": { + "External id": 4055148,"Record function id": 0, "Concrete Inputs": ["[12602]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2155 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1381189, + "ts": 1655274808958.665, "dur": 38242.020, + "args": { + "External id": 4055149,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[12602], [], [], [], [], [], [], []], "Ev Idx": 2156 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336756, "tid": 1381189, + "ts": 1655274808962.317, "dur": 38237.681, + "args": { + "External id": 4055150,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[12602], [], [], [], [], [], []], "Ev Idx": 2157 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274808966.160, "dur": 4.517, + "args": { + "External id": 4055151,"Record function id": 0, "Concrete Inputs": ["[12602]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2158 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1381189, + "ts": 1655274808972.415, "dur": 38223.840, + "args": { + "External id": 4055152,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[12602], [12602], []], "Ev Idx": 2159 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 1336756, "tid": 1381189, + "ts": 1655274847339.408, "dur": 9.269, + "args": { + "External id": 4055153,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "", "", "", "False"], "Input type": ["float", "ScalarList", "", "", "", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[51384320], [], [], [], [], []], "Ev Idx": 2160 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655274847342.864, "dur": 5.293, + "args": { + "External id": 4055154,"Record function id": 0, "Concrete Inputs": ["[6423040]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2161 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_reduce_scatter_base_", "pid": 1336756, "tid": 1381189, + "ts": 1655274847377.760, "dur": 411.220, + "args": { + "External id": 4055155,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "-1"], "Input type": ["float", "float", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], [], []], "Input Dims": [[6423040], [51384320], [], [], [], []], "Ev Idx": 2162 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336756, "tid": 1381189, + "ts": 1655274847408.701, "dur": 375.184, + "args": { + "External id": 4055156,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 3, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "3", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 6423040, "Process Group Name": "0", "Input type": ["float", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[51384320], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 2163, "In msg nelems": 51384320 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_reduce_scatter_base", "pid": 1336756, "tid": 1381189, + "ts": 1655274847440.780, "dur": 336.903, + "args": { + "External id": 4055157,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[51384320]], "Ev Idx": 2164 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336756, "tid": 1381189, + "ts": 1655274847816.346, "dur": 2.414, + "args": { + "External id": 4055158,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "3", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 2165, "In msg nelems": 0, "Rank": 3, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274847881.869, "dur": 6.583, + "args": { + "External id": 4055159,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2166 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274847936.983, "dur": 1.064, + "args": { + "External id": 4055160,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "256"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2167 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274847954.825, "dur": 1.345, + "args": { + "External id": 4055161,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "524544"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2168 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274847968.998, "dur": 0.895, + "args": { + "External id": 4055162,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "1048832"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2169 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274848018.532, "dur": 1.549, + "args": { + "External id": 4055163,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "1573120"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2170 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274848037.817, "dur": 0.720, + "args": { + "External id": 4055164,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2171 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274848050.618, "dur": 0.701, + "args": { + "External id": 4055165,"Record function id": 0, "Concrete Inputs": ["", "[704, 2048]", "[2048, 1]", "2097664"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2172 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274848063.560, "dur": 1.912, + "args": { + "External id": 4055166,"Record function id": 0, "Concrete Inputs": ["", "[704, 2048]", "[2048, 1]", "3539456"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2173 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274848078.099, "dur": 0.630, + "args": { + "External id": 4055167,"Record function id": 0, "Concrete Inputs": ["", "[256, 5632]", "[5632, 1]", "4981248"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2174 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: CompiledFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1655274848175.962, "dur": 2670.024, + "args": { + "External id": 4055168,"Record function id": 0, "Ev Idx": 2175 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.23)", "pid": 1336756, "tid": 1381189, + "ts": 1655274848194.444, "dur": 1017.697, + "args": { + "External id": 4055169,"Record function id": 0, "Ev Idx": 2176 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.23)", "pid": 1336756, "tid": 1381189, + "ts": 1655274848209.001, "dur": 337.374, + "args": { + "External id": 4055170,"Record function id": 0, "Ev Idx": 2177 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274848288.441, "dur": 3.996, + "args": { + "External id": 4055171,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[51384320], []], "Ev Idx": 2178 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274848295.439, "dur": 0.902, + "args": { + "External id": 4055172,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 2179 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274848298.160, "dur": 0.880, + "args": { + "External id": 4055173,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 2180 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274848300.710, "dur": 0.726, + "args": { + "External id": 4055174,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 2181 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274848305.222, "dur": 0.694, + "args": { + "External id": 4055175,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 2182 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274848307.381, "dur": 0.764, + "args": { + "External id": 4055176,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 2183 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274848309.711, "dur": 1.412, + "args": { + "External id": 4055177,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 2184 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274848312.650, "dur": 2.568, + "args": { + "External id": 4055178,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 2185 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274848318.794, "dur": 0.625, + "args": { + "External id": 4055179,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 2186 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274848320.719, "dur": 0.596, + "args": { + "External id": 4055180,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 2187 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 1336756, "tid": 1381189, + "ts": 1655274848339.281, "dur": 171.458, + "args": { + "External id": 4055181,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 2188 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 1336756, "tid": 1381189, + "ts": 1655274848354.731, "dur": 150.972, + "args": { + "External id": 4055182,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 2189 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655274848374.009, "dur": 14.728, + "args": { + "External id": 4055183,"Record function id": 0, "Concrete Inputs": ["[2133]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2190 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1381189, + "ts": 1655274848391.685, "dur": 85.958, + "args": { + "External id": 4055184,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], [], []], "Ev Idx": 2191 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336756, "tid": 1381189, + "ts": 1655274848393.892, "dur": 83.424, + "args": { + "External id": 4055185,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], []], "Ev Idx": 2192 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274848397.948, "dur": 5.057, + "args": { + "External id": 4055186,"Record function id": 0, "Concrete Inputs": ["[2133]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2193 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1381189, + "ts": 1655274848406.661, "dur": 69.577, + "args": { + "External id": 4055187,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[2133], [2133], []], "Ev Idx": 2194 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::backward_prefetch for model.layers.22", "pid": 1336756, "tid": 1381189, + "ts": 1655274848624.984, "dur": 579.877, + "args": { + "External id": 4055188,"Record function id": 0, "Ev Idx": 2195 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.22)", "pid": 1336756, "tid": 1381189, + "ts": 1655274848641.276, "dur": 551.352, + "args": { + "External id": 4055189,"Record function id": 0, "Ev Idx": 2196 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655274848696.759, "dur": 5.372, + "args": { + "External id": 4055190,"Record function id": 0, "Concrete Inputs": ["[6423040]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2197 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336756, "tid": 1381189, + "ts": 1655274848717.570, "dur": 28.934, + "args": { + "External id": 4055191,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 2198 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274848721.903, "dur": 1.593, + "args": { + "External id": 4055192,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2199 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274848726.521, "dur": 0.452, + "args": { + "External id": 4055193,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2200 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274848728.221, "dur": 2.488, + "args": { + "External id": 4055194,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2201 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274848731.957, "dur": 1.001, + "args": { + "External id": 4055195,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2202 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274848734.087, "dur": 0.233, + "args": { + "External id": 4055196,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2203 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274848735.418, "dur": 0.226, + "args": { + "External id": 4055197,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2204 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274848738.167, "dur": 0.355, + "args": { + "External id": 4055198,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2205 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274848740.128, "dur": 0.252, + "args": { + "External id": 4055199,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2206 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274848741.744, "dur": 0.334, + "args": { + "External id": 4055200,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2207 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336756, "tid": 1381189, + "ts": 1655274848756.028, "dur": 28.964, + "args": { + "External id": 4055201,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 2208 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 1336756, "tid": 1381189, + "ts": 1655274848815.633, "dur": 100.186, + "args": { + "External id": 4055202,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "6423040", "8", "3", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [], [], [], [], [], []], "Ev Idx": 2209 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655274848825.205, "dur": 3.464, + "args": { + "External id": 4055203,"Record function id": 0, "Concrete Inputs": ["[51384320]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2210 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 1336756, "tid": 1381189, + "ts": 1655274848833.849, "dur": 13.350, + "args": { + "External id": 4055204,"Record function id": 0, "Concrete Inputs": ["", "0", "19269120", "6423040"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 2211 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1381189, + "ts": 1655274848838.175, "dur": 8.576, + "args": { + "External id": 4055205,"Record function id": 0, "Concrete Inputs": ["", "0", "19269120", "25692160", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[51384320], [], [], [], []], "Ev Idx": 2212 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274848841.793, "dur": 3.793, + "args": { + "External id": 4055206,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "[1]", "19269120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 2213 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336756, "tid": 1381189, + "ts": 1655274848854.111, "dur": 25.213, + "args": { + "External id": 4055207,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 2214 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274848855.919, "dur": 0.576, + "args": { + "External id": 4055208,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "19269120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2215 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274848858.034, "dur": 0.523, + "args": { + "External id": 4055209,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "19269376"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2216 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274848860.011, "dur": 0.376, + "args": { + "External id": 4055210,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "19793664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2217 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274848863.400, "dur": 0.377, + "args": { + "External id": 4055211,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "20317952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2218 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274848865.315, "dur": 0.358, + "args": { + "External id": 4055212,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "20842240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2219 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274848867.233, "dur": 1.043, + "args": { + "External id": 4055213,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "21366528"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2220 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274848869.433, "dur": 0.425, + "args": { + "External id": 4055214,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "21366784"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2221 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274848871.165, "dur": 2.012, + "args": { + "External id": 4055215,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "22808576"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2222 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274848875.743, "dur": 0.290, + "args": { + "External id": 4055216,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "24250368"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2223 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336756, "tid": 1381189, + "ts": 1655274848888.556, "dur": 20.321, + "args": { + "External id": 4055217,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 2224 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 1336756, "tid": 1381189, + "ts": 1655274848958.234, "dur": 157.842, + "args": { + "External id": 4055218,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[51384320], [6423040], [], [], []], "Ev Idx": 2225 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336756, "tid": 1381189, + "ts": 1655274849025.385, "dur": 86.944, + "args": { + "External id": 4055219,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 3, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "3", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 51384320, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[6423040], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 2226, "In msg nelems": 6423040 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 1336756, "tid": 1381189, + "ts": 1655274849036.834, "dur": 71.690, + "args": { + "External id": 4055220,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[6423040]], "Ev Idx": 2227 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336756, "tid": 1381189, + "ts": 1655274849137.551, "dur": 1.832, + "args": { + "External id": 4055221,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "3", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 2228, "In msg nelems": 0, "Rank": 3, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1655274849218.784, "dur": 1607.269, + "args": { + "External id": 4055222,"Sequence number": 40618400, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 2229 + } + }, + { + "ph": "f", "id": 180, "pid": 1336756, "tid": 1381189, "ts": 1655274849218.784, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655274849324.364, "dur": 122.393, + "args": { + "External id": 4055223,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [5632, 1], [5632, 1]], "Input Dims": [[65536, 2048], [2048, 5632], [65536, 5632]], "Ev Idx": 2230 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_add_mul_rsub_silu_0", "pid": 1336756, "tid": 1381189, + "ts": 1655274849491.085, "dur": 36.763, + "args": { + "External id": 4055224,"kernel_hash": "c2zszzsomz26dv2qwvmiurvgyrl5qxtyn6ocoqkdpzzhfzwqp5q6", "grid": "grid(369098752,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "369098752"], "kernel_file": "/tmp/torchinductor_cvm/2z/c2zszzsomz26dv2qwvmiurvgyrl5qxtyn6ocoqkdpzzhfzwqp5q6.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[5632, 1], [5632, 1], [5632, 1], [23068672, 5632, 1], [23068672, 5632, 1], [23068672, 5632, 1], []], "Input Dims": [[65536, 5632], [65536, 5632], [65536, 5632], [16, 4096, 5632], [16, 4096, 5632], [16, 4096, 5632], []], "Ev Idx": 2231 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 1336756, "tid": 1381189, + "ts": 1655274849545.046, "dur": 53.591, + "args": { + "External id": 4055225,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[0, 1, 2048], [0, 5632, 1], [11534336, 5632, 1]], "Input Dims": [[1, 2048, 65536], [1, 65536, 5632], [1, 2048, 5632]], "Ev Idx": 2232 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655274849608.295, "dur": 33.256, + "args": { + "External id": 4055226,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 5632], [2048, 1], [2048, 1]], "Input Dims": [[5632, 65536], [65536, 2048], [5632, 2048]], "Ev Idx": 2233 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655274849647.976, "dur": 45.764, + "args": { + "External id": 4055227,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 5632], [5632, 2048], [65536, 2048]], "Ev Idx": 2234 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655274849701.329, "dur": 28.109, + "args": { + "External id": 4055228,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 5632], [2048, 1], [2048, 1]], "Input Dims": [[5632, 65536], [65536, 2048], [5632, 2048]], "Ev Idx": 2235 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655274849738.192, "dur": 43.344, + "args": { + "External id": 4055229,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 5632], [5632, 2048], [65536, 2048]], "Ev Idx": 2236 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_1", "pid": 1336756, "tid": 1381189, + "ts": 1655274849805.088, "dur": 20.862, + "args": { + "External id": 4055230,"kernel_hash": "cjd6g3jfgntyoifzno6l2urmnhif7alxtw6zz7miov66vywxwv7d", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/jd/cjd6g3jfgntyoifzno6l2urmnhif7alxtw6zz7miov66vywxwv7d.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[65536, 2048], [65536, 2048], []], "Ev Idx": 2237 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 1336756, "tid": 1381189, + "ts": 1655274849842.769, "dur": 26.580, + "args": { + "External id": 4055231,"kernel_hash": "cxhg545cyph4gbk5vymzyh72vho7oogk3ycan2lp4cxntklp5hew", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "65536", "2048", "1", "497", "132", "True", "2048", "True", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/xh/cxhg545cyph4gbk5vymzyh72vho7oogk3ycan2lp4cxntklp5hew.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [1], [2048, 1], [2048, 1], [2048, 1], [2048, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [2048], [65536, 2048], [65536, 2048], [132, 2048], [65536, 2048], [65536], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 2238 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 1336756, "tid": 1381189, + "ts": 1655274849889.960, "dur": 17.352, + "args": { + "External id": 4055232,"kernel_hash": "cu42i6zmxtvs2i7cs6x4ixaexke3lhgdiaye5oxwm7s3u6em6co4", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "66"], "kernel_file": "/tmp/torchinductor_cvm/u4/cu42i6zmxtvs2i7cs6x4ixaexke3lhgdiaye5oxwm7s3u6em6co4.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [4096, 1, 2048], [], []], "Input Dims": [[132, 2048], [1, 2048, 2], [], []], "Ev Idx": 2239 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 1336756, "tid": 1381189, + "ts": 1655274849920.810, "dur": 13.757, + "args": { + "External id": 4055233,"kernel_hash": "ckihofrorhmzazt2wfn2dz2m5wfx3auisu2gvfo2jsepr4zyekmq", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "2"], "kernel_file": "/tmp/torchinductor_cvm/ki/ckihofrorhmzazt2wfn2dz2m5wfx3auisu2gvfo2jsepr4zyekmq.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1, 2048], [2048, 1], [], []], "Input Dims": [[1, 2048, 2], [1, 2048], [], []], "Ev Idx": 2240 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655274849944.091, "dur": 27.321, + "args": { + "External id": 4055234,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 2241 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655274849974.390, "dur": 74.492, + "args": { + "External id": 4055235,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 2242 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 1336756, "tid": 1381189, + "ts": 1655274850078.574, "dur": 172.432, + "args": { + "External id": 4055236,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.125", "True", "-1", "-1", "0.", "", "False", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar", "long int"], "Input Strides": [[8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [131072, 4096, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 32, 4096], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 2243 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655274850158.458, "dur": 6.511, + "args": { + "External id": 4055237,"Record function id": 0, "Concrete Inputs": ["[16, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2244 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655274850166.859, "dur": 2.436, + "args": { + "External id": 4055238,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2245 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336756, "tid": 1381189, + "ts": 1655274850284.876, "dur": 24.941, + "args": { + "External id": 4055239,"kernel_hash": "cb6oumcqb462ndf2ivcd2sc6qg6mfjahptjw4ih7cesqhfpziv3b", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/b6/cb6oumcqb462ndf2ivcd2sc6qg6mfjahptjw4ih7cesqhfpziv3b.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 2246 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336756, "tid": 1381189, + "ts": 1655274850323.721, "dur": 13.432, + "args": { + "External id": 4055240,"kernel_hash": "cb6oumcqb462ndf2ivcd2sc6qg6mfjahptjw4ih7cesqhfpziv3b", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/b6/cb6oumcqb462ndf2ivcd2sc6qg6mfjahptjw4ih7cesqhfpziv3b.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 2247 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655274850347.146, "dur": 37.732, + "args": { + "External id": 4055241,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 2248 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655274850390.213, "dur": 49.962, + "args": { + "External id": 4055242,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 2249 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655274850458.926, "dur": 24.101, + "args": { + "External id": 4055243,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 2250 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655274850487.584, "dur": 30.424, + "args": { + "External id": 4055244,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 2251 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655274850526.096, "dur": 33.912, + "args": { + "External id": 4055245,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 2252 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655274850573.425, "dur": 38.520, + "args": { + "External id": 4055246,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 2253 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_4", "pid": 1336756, "tid": 1381189, + "ts": 1655274850636.373, "dur": 25.591, + "args": { + "External id": 4055247,"kernel_hash": "c7pqhdjojzeazwsh5g3ibnyk4m2nfh3q73e3zc7hljz4yvhe7c4h", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/7p/c7pqhdjojzeazwsh5g3ibnyk4m2nfh3q73e3zc7hljz4yvhe7c4h.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1], []], "Input Dims": [[65536, 2048], [65536, 2048], [65536, 2048], []], "Ev Idx": 2254 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_2", "pid": 1336756, "tid": 1381189, + "ts": 1655274850681.215, "dur": 24.881, + "args": { + "External id": 4055248,"kernel_hash": "cvgvwkysjpcw75q5t3guce5bep2so25f7i5zxc6ipt5f56shof73", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "65536", "2048", "1", "497", "132", "True", "2048", "False", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/vg/cvgvwkysjpcw75q5t3guce5bep2so25f7i5zxc6ipt5f56shof73.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [1], [2048, 1], [2048, 1], [2048, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [2048], [65536, 2048], [65536, 2048], [132, 2048], [65536], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 2255 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 1336756, "tid": 1381189, + "ts": 1655274850722.193, "dur": 15.700, + "args": { + "External id": 4055249,"kernel_hash": "cu42i6zmxtvs2i7cs6x4ixaexke3lhgdiaye5oxwm7s3u6em6co4", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "66"], "kernel_file": "/tmp/torchinductor_cvm/u4/cu42i6zmxtvs2i7cs6x4ixaexke3lhgdiaye5oxwm7s3u6em6co4.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [4096, 1, 2048], [], []], "Input Dims": [[132, 2048], [1, 2048, 2], [], []], "Ev Idx": 2256 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 1336756, "tid": 1381189, + "ts": 1655274850755.744, "dur": 13.298, + "args": { + "External id": 4055250,"kernel_hash": "ckihofrorhmzazt2wfn2dz2m5wfx3auisu2gvfo2jsepr4zyekmq", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "2"], "kernel_file": "/tmp/torchinductor_cvm/ki/ckihofrorhmzazt2wfn2dz2m5wfx3auisu2gvfo2jsepr4zyekmq.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1, 2048], [2048, 1], [], []], "Input Dims": [[1, 2048, 2], [1, 2048], [], []], "Ev Idx": 2257 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_5", "pid": 1336756, "tid": 1381189, + "ts": 1655274850781.673, "dur": 14.856, + "args": { + "External id": 4055251,"kernel_hash": "cckrpn5uuxyvbancoio3sz2onrjto236n54xx4ycphq5p6r3jlfj", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/ck/cckrpn5uuxyvbancoio3sz2onrjto236n54xx4ycphq5p6r3jlfj.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [8388608, 2048, 1], []], "Input Dims": [[65536, 2048], [65536, 2048], [16, 4096, 2048], []], "Ev Idx": 2258 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274850868.132, "dur": 14.672, + "args": { + "External id": 4055252,"Record function id": 0, "Ev Idx": 2259 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274850871.564, "dur": 10.357, + "args": { + "External id": 4055253,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 2260 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274850875.608, "dur": 5.461, + "args": { + "External id": 4055254,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 2261 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274850877.091, "dur": 3.862, + "args": { + "External id": 4055255,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 2262 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274850886.817, "dur": 4.267, + "args": { + "External id": 4055256,"Record function id": 0, "Ev Idx": 2263 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274850888.324, "dur": 2.330, + "args": { + "External id": 4055257,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 2264 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274850889.059, "dur": 1.178, + "args": { + "External id": 4055258,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 2265 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274850889.461, "dur": 0.697, + "args": { + "External id": 4055259,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 2266 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274850894.296, "dur": 4.447, + "args": { + "External id": 4055260,"Record function id": 0, "Ev Idx": 2267 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274850895.625, "dur": 2.704, + "args": { + "External id": 4055261,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 2268 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274850896.296, "dur": 1.649, + "args": { + "External id": 4055262,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 2269 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274850897.021, "dur": 0.816, + "args": { + "External id": 4055263,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 2270 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274850901.910, "dur": 3.952, + "args": { + "External id": 4055264,"Record function id": 0, "Ev Idx": 2271 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274850903.403, "dur": 2.065, + "args": { + "External id": 4055265,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 2272 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274850904.065, "dur": 1.025, + "args": { + "External id": 4055266,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 2273 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274850904.402, "dur": 0.594, + "args": { + "External id": 4055267,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 2274 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274850908.906, "dur": 3.910, + "args": { + "External id": 4055268,"Record function id": 0, "Ev Idx": 2275 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274850910.051, "dur": 2.305, + "args": { + "External id": 4055269,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 2276 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274850910.562, "dur": 1.423, + "args": { + "External id": 4055270,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 2277 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274850911.057, "dur": 0.854, + "args": { + "External id": 4055271,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 2278 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274850915.915, "dur": 3.668, + "args": { + "External id": 4055272,"Record function id": 0, "Ev Idx": 2279 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274850916.947, "dur": 2.229, + "args": { + "External id": 4055273,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 2280 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274850917.589, "dur": 1.176, + "args": { + "External id": 4055274,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 2281 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274850918.128, "dur": 0.562, + "args": { + "External id": 4055275,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 2282 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274850922.812, "dur": 5.672, + "args": { + "External id": 4055276,"Record function id": 0, "Ev Idx": 2283 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274850923.915, "dur": 4.150, + "args": { + "External id": 4055277,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 2284 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274850924.489, "dur": 3.193, + "args": { + "External id": 4055278,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 2285 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274850924.864, "dur": 2.748, + "args": { + "External id": 4055279,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 2286 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274850931.489, "dur": 5.608, + "args": { + "External id": 4055280,"Record function id": 0, "Ev Idx": 2287 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274850932.895, "dur": 3.800, + "args": { + "External id": 4055281,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 2288 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274850933.554, "dur": 2.735, + "args": { + "External id": 4055282,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 2289 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274850935.384, "dur": 0.838, + "args": { + "External id": 4055283,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 2290 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274850940.154, "dur": 3.572, + "args": { + "External id": 4055284,"Record function id": 0, "Ev Idx": 2291 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274850941.396, "dur": 1.929, + "args": { + "External id": 4055285,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 2292 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274850941.827, "dur": 1.101, + "args": { + "External id": 4055286,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 2293 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274850942.223, "dur": 0.640, + "args": { + "External id": 4055287,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 2294 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RegisterPostBackwardFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1655274850947.228, "dur": 36667.590, + "args": { + "External id": 4055288,"Record function id": 0, "Sequence number": 40618399, "Fwd thread id": 1, "Ev Idx": 2295 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1655274850948.481, "dur": 36657.952, + "args": { + "External id": 4055289,"Sequence number": 40618399, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 2296 + } + }, + { + "ph": "f", "id": 181, "pid": 1336756, "tid": 1381189, "ts": 1655274850948.481, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.23)", "pid": 1336756, "tid": 1381189, + "ts": 1655274850978.912, "dur": 76.120, + "args": { + "External id": 4055290,"Record function id": 0, "Ev Idx": 2297 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.23)", "pid": 1336756, "tid": 1381189, + "ts": 1655274851064.655, "dur": 61.160, + "args": { + "External id": 4055291,"Record function id": 0, "Ev Idx": 2298 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.23)", "pid": 1336756, "tid": 1381189, + "ts": 1655274851132.114, "dur": 36466.090, + "args": { + "External id": 4055292,"Record function id": 0, "Ev Idx": 2299 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655274851221.059, "dur": 6.794, + "args": { + "External id": 4055293,"Record function id": 0, "Concrete Inputs": ["[51384320]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2300 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274851241.445, "dur": 5.076, + "args": { + "External id": 4055294,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[51384320], []], "Ev Idx": 2301 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::chunk_cat", "pid": 1336756, "tid": 1381189, + "ts": 1655274851262.642, "dur": 35511.069, + "args": { + "External id": 4055295,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [2048, 1], [2048, 1], [2048, 1], [2048, 1], [1], [2048, 1], [2048, 1], [5632, 1]], [], [], [6423040, 1]], "Input Dims": [[[2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048], [5632, 2048], [5632, 2048], [2048, 5632]], [], [], [8, 6423040]], "Ev Idx": 2302 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_chunk_cat", "pid": 1336756, "tid": 1381189, + "ts": 1655274851275.857, "dur": 35489.467, + "args": { + "External id": 4055296,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [2048, 1], [2048, 1], [2048, 1], [2048, 1], [1], [2048, 1], [2048, 1], [5632, 1]], [], [], [6423040, 1]], "Input Dims": [[[2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048], [5632, 2048], [5632, 2048], [2048, 5632]], [], [], [8, 6423040]], "Ev Idx": 2303 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655274851326.412, "dur": 13.665, + "args": { + "External id": 4055297,"Record function id": 0, "Concrete Inputs": ["[12602]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2304 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1381189, + "ts": 1655274851346.283, "dur": 35382.217, + "args": { + "External id": 4055298,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[12602], [], [], [], [], [], [], []], "Ev Idx": 2305 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336756, "tid": 1381189, + "ts": 1655274851349.912, "dur": 35377.982, + "args": { + "External id": 4055299,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[12602], [], [], [], [], [], []], "Ev Idx": 2306 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274851353.885, "dur": 4.914, + "args": { + "External id": 4055300,"Record function id": 0, "Concrete Inputs": ["[12602]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2307 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1381189, + "ts": 1655274851360.459, "dur": 35363.980, + "args": { + "External id": 4055301,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[12602], [12602], []], "Ev Idx": 2308 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 1336756, "tid": 1381189, + "ts": 1655274886860.133, "dur": 8.313, + "args": { + "External id": 4055302,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "", "", "", "False"], "Input type": ["float", "ScalarList", "", "", "", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[51384320], [], [], [], [], []], "Ev Idx": 2309 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655274886862.977, "dur": 5.085, + "args": { + "External id": 4055303,"Record function id": 0, "Concrete Inputs": ["[6423040]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2310 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_reduce_scatter_base_", "pid": 1336756, "tid": 1381189, + "ts": 1655274886897.806, "dur": 372.841, + "args": { + "External id": 4055304,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "-1"], "Input type": ["float", "float", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], [], []], "Input Dims": [[6423040], [51384320], [], [], [], []], "Ev Idx": 2311 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336756, "tid": 1381189, + "ts": 1655274886930.186, "dur": 335.384, + "args": { + "External id": 4055305,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 3, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "3", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 6423040, "Process Group Name": "0", "Input type": ["float", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[51384320], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 2312, "In msg nelems": 51384320 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_reduce_scatter_base", "pid": 1336756, "tid": 1381189, + "ts": 1655274886941.641, "dur": 317.715, + "args": { + "External id": 4055306,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[51384320]], "Ev Idx": 2313 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336756, "tid": 1381189, + "ts": 1655274887296.579, "dur": 2.686, + "args": { + "External id": 4055307,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "3", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 2314, "In msg nelems": 0, "Rank": 3, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274887358.909, "dur": 8.510, + "args": { + "External id": 4055308,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2315 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274887414.129, "dur": 15.786, + "args": { + "External id": 4055309,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "256"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2316 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274887451.539, "dur": 1.249, + "args": { + "External id": 4055310,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "524544"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2317 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274887465.385, "dur": 0.924, + "args": { + "External id": 4055311,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "1048832"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2318 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274887479.688, "dur": 2.853, + "args": { + "External id": 4055312,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "1573120"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2319 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274887493.917, "dur": 0.833, + "args": { + "External id": 4055313,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2320 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274887506.258, "dur": 1.030, + "args": { + "External id": 4055314,"Record function id": 0, "Concrete Inputs": ["", "[704, 2048]", "[2048, 1]", "2097664"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2321 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274887520.006, "dur": 1.878, + "args": { + "External id": 4055315,"Record function id": 0, "Concrete Inputs": ["", "[704, 2048]", "[2048, 1]", "3539456"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2322 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274887534.590, "dur": 2.380, + "args": { + "External id": 4055316,"Record function id": 0, "Concrete Inputs": ["", "[256, 5632]", "[5632, 1]", "4981248"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2323 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: CompiledFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1655274887630.789, "dur": 2672.742, + "args": { + "External id": 4055317,"Record function id": 0, "Ev Idx": 2324 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.22)", "pid": 1336756, "tid": 1381189, + "ts": 1655274887649.452, "dur": 1008.408, + "args": { + "External id": 4055318,"Record function id": 0, "Ev Idx": 2325 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.22)", "pid": 1336756, "tid": 1381189, + "ts": 1655274887663.463, "dur": 304.684, + "args": { + "External id": 4055319,"Record function id": 0, "Ev Idx": 2326 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274887736.835, "dur": 3.729, + "args": { + "External id": 4055320,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[51384320], []], "Ev Idx": 2327 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274887743.694, "dur": 0.983, + "args": { + "External id": 4055321,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 2328 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274887746.411, "dur": 0.735, + "args": { + "External id": 4055322,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 2329 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274887748.912, "dur": 0.638, + "args": { + "External id": 4055323,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 2330 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274887752.992, "dur": 0.647, + "args": { + "External id": 4055324,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 2331 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274887755.174, "dur": 0.645, + "args": { + "External id": 4055325,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 2332 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274887757.305, "dur": 3.514, + "args": { + "External id": 4055326,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 2333 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274887762.502, "dur": 0.709, + "args": { + "External id": 4055327,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 2334 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274887766.069, "dur": 0.901, + "args": { + "External id": 4055328,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 2335 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274887768.409, "dur": 0.719, + "args": { + "External id": 4055329,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 2336 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 1336756, "tid": 1381189, + "ts": 1655274887787.448, "dur": 149.938, + "args": { + "External id": 4055330,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 2337 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 1336756, "tid": 1381189, + "ts": 1655274887803.585, "dur": 129.386, + "args": { + "External id": 4055331,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 2338 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655274887824.543, "dur": 12.310, + "args": { + "External id": 4055332,"Record function id": 0, "Concrete Inputs": ["[2133]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2339 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1381189, + "ts": 1655274887839.894, "dur": 66.430, + "args": { + "External id": 4055333,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], [], []], "Ev Idx": 2340 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336756, "tid": 1381189, + "ts": 1655274887844.105, "dur": 61.956, + "args": { + "External id": 4055334,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], []], "Ev Idx": 2341 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274887848.188, "dur": 5.647, + "args": { + "External id": 4055335,"Record function id": 0, "Concrete Inputs": ["[2133]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2342 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1381189, + "ts": 1655274887855.579, "dur": 49.837, + "args": { + "External id": 4055336,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[2133], [2133], []], "Ev Idx": 2343 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::backward_prefetch for model.layers.21", "pid": 1336756, "tid": 1381189, + "ts": 1655274888086.478, "dur": 563.700, + "args": { + "External id": 4055337,"Record function id": 0, "Ev Idx": 2344 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.21)", "pid": 1336756, "tid": 1381189, + "ts": 1655274888103.018, "dur": 534.895, + "args": { + "External id": 4055338,"Record function id": 0, "Ev Idx": 2345 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655274888158.345, "dur": 5.289, + "args": { + "External id": 4055339,"Record function id": 0, "Concrete Inputs": ["[6423040]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2346 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336756, "tid": 1381189, + "ts": 1655274888179.883, "dur": 29.587, + "args": { + "External id": 4055340,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 2347 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274888185.056, "dur": 2.393, + "args": { + "External id": 4055341,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2348 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274888189.336, "dur": 2.333, + "args": { + "External id": 4055342,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2349 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274888192.629, "dur": 0.506, + "args": { + "External id": 4055343,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2350 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274888195.105, "dur": 0.447, + "args": { + "External id": 4055344,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2351 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274888196.881, "dur": 0.378, + "args": { + "External id": 4055345,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2352 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274888198.612, "dur": 0.373, + "args": { + "External id": 4055346,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2353 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274888200.714, "dur": 0.273, + "args": { + "External id": 4055347,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2354 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274888202.255, "dur": 0.302, + "args": { + "External id": 4055348,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2355 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274888204.508, "dur": 0.485, + "args": { + "External id": 4055349,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2356 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336756, "tid": 1381189, + "ts": 1655274888222.651, "dur": 34.194, + "args": { + "External id": 4055350,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 2357 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 1336756, "tid": 1381189, + "ts": 1655274888287.392, "dur": 103.184, + "args": { + "External id": 4055351,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "6423040", "8", "3", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [], [], [], [], [], []], "Ev Idx": 2358 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655274888297.435, "dur": 5.294, + "args": { + "External id": 4055352,"Record function id": 0, "Concrete Inputs": ["[51384320]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2359 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 1336756, "tid": 1381189, + "ts": 1655274888307.525, "dur": 10.412, + "args": { + "External id": 4055353,"Record function id": 0, "Concrete Inputs": ["", "0", "19269120", "6423040"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 2360 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1381189, + "ts": 1655274888311.486, "dur": 6.024, + "args": { + "External id": 4055354,"Record function id": 0, "Concrete Inputs": ["", "0", "19269120", "25692160", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[51384320], [], [], [], []], "Ev Idx": 2361 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274888315.589, "dur": 0.682, + "args": { + "External id": 4055355,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "[1]", "19269120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 2362 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336756, "tid": 1381189, + "ts": 1655274888324.910, "dur": 27.062, + "args": { + "External id": 4055356,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 2363 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274888327.405, "dur": 0.506, + "args": { + "External id": 4055357,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "19269120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2364 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274888330.050, "dur": 0.650, + "args": { + "External id": 4055358,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "19269376"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2365 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274888332.462, "dur": 0.724, + "args": { + "External id": 4055359,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "19793664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2366 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274888334.856, "dur": 0.623, + "args": { + "External id": 4055360,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "20317952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2367 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274888337.273, "dur": 0.529, + "args": { + "External id": 4055361,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "20842240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2368 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274888339.514, "dur": 0.394, + "args": { + "External id": 4055362,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "21366528"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2369 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274888341.604, "dur": 2.424, + "args": { + "External id": 4055363,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "21366784"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2370 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274888345.920, "dur": 0.400, + "args": { + "External id": 4055364,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "22808576"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2371 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274888348.147, "dur": 0.468, + "args": { + "External id": 4055365,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "24250368"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2372 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336756, "tid": 1381189, + "ts": 1655274888363.555, "dur": 19.890, + "args": { + "External id": 4055366,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 2373 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 1336756, "tid": 1381189, + "ts": 1655274888455.366, "dur": 113.848, + "args": { + "External id": 4055367,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[51384320], [6423040], [], [], []], "Ev Idx": 2374 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336756, "tid": 1381189, + "ts": 1655274888478.886, "dur": 86.550, + "args": { + "External id": 4055368,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 3, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "3", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 51384320, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[6423040], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 2375, "In msg nelems": 6423040 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 1336756, "tid": 1381189, + "ts": 1655274888489.584, "dur": 71.345, + "args": { + "External id": 4055369,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[6423040]], "Ev Idx": 2376 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336756, "tid": 1381189, + "ts": 1655274888583.805, "dur": 2.111, + "args": { + "External id": 4055370,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "3", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 2377, "In msg nelems": 0, "Rank": 3, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1655274888665.244, "dur": 1617.951, + "args": { + "External id": 4055371,"Sequence number": 40618398, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 2378 + } + }, + { + "ph": "f", "id": 182, "pid": 1336756, "tid": 1381189, "ts": 1655274888665.244, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655274888770.152, "dur": 100.631, + "args": { + "External id": 4055372,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [5632, 1], [5632, 1]], "Input Dims": [[65536, 2048], [2048, 5632], [65536, 5632]], "Ev Idx": 2379 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_add_mul_rsub_silu_0", "pid": 1336756, "tid": 1381189, + "ts": 1655274888908.889, "dur": 36.121, + "args": { + "External id": 4055373,"kernel_hash": "c2zszzsomz26dv2qwvmiurvgyrl5qxtyn6ocoqkdpzzhfzwqp5q6", "grid": "grid(369098752,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "369098752"], "kernel_file": "/tmp/torchinductor_cvm/2z/c2zszzsomz26dv2qwvmiurvgyrl5qxtyn6ocoqkdpzzhfzwqp5q6.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[5632, 1], [5632, 1], [5632, 1], [23068672, 5632, 1], [23068672, 5632, 1], [23068672, 5632, 1], []], "Input Dims": [[65536, 5632], [65536, 5632], [65536, 5632], [16, 4096, 5632], [16, 4096, 5632], [16, 4096, 5632], []], "Ev Idx": 2380 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 1336756, "tid": 1381189, + "ts": 1655274888961.620, "dur": 94.283, + "args": { + "External id": 4055374,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[0, 1, 2048], [0, 5632, 1], [11534336, 5632, 1]], "Input Dims": [[1, 2048, 65536], [1, 65536, 5632], [1, 2048, 5632]], "Ev Idx": 2381 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655274889069.626, "dur": 36.141, + "args": { + "External id": 4055375,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 5632], [2048, 1], [2048, 1]], "Input Dims": [[5632, 65536], [65536, 2048], [5632, 2048]], "Ev Idx": 2382 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655274889112.264, "dur": 45.529, + "args": { + "External id": 4055376,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 5632], [5632, 2048], [65536, 2048]], "Ev Idx": 2383 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655274889167.513, "dur": 27.970, + "args": { + "External id": 4055377,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 5632], [2048, 1], [2048, 1]], "Input Dims": [[5632, 65536], [65536, 2048], [5632, 2048]], "Ev Idx": 2384 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655274889202.507, "dur": 42.485, + "args": { + "External id": 4055378,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 5632], [5632, 2048], [65536, 2048]], "Ev Idx": 2385 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_1", "pid": 1336756, "tid": 1381189, + "ts": 1655274889268.593, "dur": 22.266, + "args": { + "External id": 4055379,"kernel_hash": "cjd6g3jfgntyoifzno6l2urmnhif7alxtw6zz7miov66vywxwv7d", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/jd/cjd6g3jfgntyoifzno6l2urmnhif7alxtw6zz7miov66vywxwv7d.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[65536, 2048], [65536, 2048], []], "Ev Idx": 2386 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 1336756, "tid": 1381189, + "ts": 1655274889317.031, "dur": 27.132, + "args": { + "External id": 4055380,"kernel_hash": "cxhg545cyph4gbk5vymzyh72vho7oogk3ycan2lp4cxntklp5hew", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "65536", "2048", "1", "497", "132", "True", "2048", "True", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/xh/cxhg545cyph4gbk5vymzyh72vho7oogk3ycan2lp4cxntklp5hew.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [1], [2048, 1], [2048, 1], [2048, 1], [2048, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [2048], [65536, 2048], [65536, 2048], [132, 2048], [65536, 2048], [65536], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 2387 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 1336756, "tid": 1381189, + "ts": 1655274889364.660, "dur": 18.026, + "args": { + "External id": 4055381,"kernel_hash": "cu42i6zmxtvs2i7cs6x4ixaexke3lhgdiaye5oxwm7s3u6em6co4", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "66"], "kernel_file": "/tmp/torchinductor_cvm/u4/cu42i6zmxtvs2i7cs6x4ixaexke3lhgdiaye5oxwm7s3u6em6co4.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [4096, 1, 2048], [], []], "Input Dims": [[132, 2048], [1, 2048, 2], [], []], "Ev Idx": 2388 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 1336756, "tid": 1381189, + "ts": 1655274889396.076, "dur": 15.709, + "args": { + "External id": 4055382,"kernel_hash": "ckihofrorhmzazt2wfn2dz2m5wfx3auisu2gvfo2jsepr4zyekmq", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "2"], "kernel_file": "/tmp/torchinductor_cvm/ki/ckihofrorhmzazt2wfn2dz2m5wfx3auisu2gvfo2jsepr4zyekmq.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1, 2048], [2048, 1], [], []], "Input Dims": [[1, 2048, 2], [1, 2048], [], []], "Ev Idx": 2389 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655274889441.855, "dur": 33.913, + "args": { + "External id": 4055383,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 2390 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655274889479.760, "dur": 35.086, + "args": { + "External id": 4055384,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 2391 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 1336756, "tid": 1381189, + "ts": 1655274889543.302, "dur": 172.990, + "args": { + "External id": 4055385,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.125", "True", "-1", "-1", "0.", "", "False", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar", "long int"], "Input Strides": [[8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [131072, 4096, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 32, 4096], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 2392 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655274889622.109, "dur": 5.762, + "args": { + "External id": 4055386,"Record function id": 0, "Concrete Inputs": ["[16, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2393 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655274889630.015, "dur": 3.905, + "args": { + "External id": 4055387,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2394 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336756, "tid": 1381189, + "ts": 1655274889746.523, "dur": 23.670, + "args": { + "External id": 4055388,"kernel_hash": "cb6oumcqb462ndf2ivcd2sc6qg6mfjahptjw4ih7cesqhfpziv3b", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/b6/cb6oumcqb462ndf2ivcd2sc6qg6mfjahptjw4ih7cesqhfpziv3b.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 2395 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336756, "tid": 1381189, + "ts": 1655274889780.839, "dur": 13.733, + "args": { + "External id": 4055389,"kernel_hash": "cb6oumcqb462ndf2ivcd2sc6qg6mfjahptjw4ih7cesqhfpziv3b", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/b6/cb6oumcqb462ndf2ivcd2sc6qg6mfjahptjw4ih7cesqhfpziv3b.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 2396 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655274889803.024, "dur": 32.736, + "args": { + "External id": 4055390,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 2397 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655274889842.642, "dur": 34.596, + "args": { + "External id": 4055391,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 2398 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655274889883.732, "dur": 21.115, + "args": { + "External id": 4055392,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 2399 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655274889912.635, "dur": 30.683, + "args": { + "External id": 4055393,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 2400 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655274889950.557, "dur": 20.947, + "args": { + "External id": 4055394,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 2401 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655274889978.948, "dur": 68.796, + "args": { + "External id": 4055395,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 2402 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_4", "pid": 1336756, "tid": 1381189, + "ts": 1655274890069.138, "dur": 36.954, + "args": { + "External id": 4055396,"kernel_hash": "c7pqhdjojzeazwsh5g3ibnyk4m2nfh3q73e3zc7hljz4yvhe7c4h", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/7p/c7pqhdjojzeazwsh5g3ibnyk4m2nfh3q73e3zc7hljz4yvhe7c4h.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1], []], "Input Dims": [[65536, 2048], [65536, 2048], [65536, 2048], []], "Ev Idx": 2403 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_2", "pid": 1336756, "tid": 1381189, + "ts": 1655274890128.923, "dur": 22.436, + "args": { + "External id": 4055397,"kernel_hash": "cvgvwkysjpcw75q5t3guce5bep2so25f7i5zxc6ipt5f56shof73", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "65536", "2048", "1", "497", "132", "True", "2048", "False", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/vg/cvgvwkysjpcw75q5t3guce5bep2so25f7i5zxc6ipt5f56shof73.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [1], [2048, 1], [2048, 1], [2048, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [2048], [65536, 2048], [65536, 2048], [132, 2048], [65536], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 2404 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 1336756, "tid": 1381189, + "ts": 1655274890166.005, "dur": 15.810, + "args": { + "External id": 4055398,"kernel_hash": "cu42i6zmxtvs2i7cs6x4ixaexke3lhgdiaye5oxwm7s3u6em6co4", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "66"], "kernel_file": "/tmp/torchinductor_cvm/u4/cu42i6zmxtvs2i7cs6x4ixaexke3lhgdiaye5oxwm7s3u6em6co4.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [4096, 1, 2048], [], []], "Input Dims": [[132, 2048], [1, 2048, 2], [], []], "Ev Idx": 2405 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 1336756, "tid": 1381189, + "ts": 1655274890199.951, "dur": 13.467, + "args": { + "External id": 4055399,"kernel_hash": "ckihofrorhmzazt2wfn2dz2m5wfx3auisu2gvfo2jsepr4zyekmq", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "2"], "kernel_file": "/tmp/torchinductor_cvm/ki/ckihofrorhmzazt2wfn2dz2m5wfx3auisu2gvfo2jsepr4zyekmq.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1, 2048], [2048, 1], [], []], "Input Dims": [[1, 2048, 2], [1, 2048], [], []], "Ev Idx": 2406 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_5", "pid": 1336756, "tid": 1381189, + "ts": 1655274890234.582, "dur": 19.992, + "args": { + "External id": 4055400,"kernel_hash": "cckrpn5uuxyvbancoio3sz2onrjto236n54xx4ycphq5p6r3jlfj", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/ck/cckrpn5uuxyvbancoio3sz2onrjto236n54xx4ycphq5p6r3jlfj.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [8388608, 2048, 1], []], "Input Dims": [[65536, 2048], [65536, 2048], [16, 4096, 2048], []], "Ev Idx": 2407 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274890326.681, "dur": 15.844, + "args": { + "External id": 4055401,"Record function id": 0, "Ev Idx": 2408 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274890330.033, "dur": 11.523, + "args": { + "External id": 4055402,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 2409 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274890334.549, "dur": 6.031, + "args": { + "External id": 4055403,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 2410 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274890336.179, "dur": 4.283, + "args": { + "External id": 4055404,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 2411 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274890346.416, "dur": 5.366, + "args": { + "External id": 4055405,"Record function id": 0, "Ev Idx": 2412 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274890347.995, "dur": 3.351, + "args": { + "External id": 4055406,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 2413 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274890348.839, "dur": 2.068, + "args": { + "External id": 4055407,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 2414 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274890349.749, "dur": 1.080, + "args": { + "External id": 4055408,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 2415 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274890354.913, "dur": 5.819, + "args": { + "External id": 4055409,"Record function id": 0, "Ev Idx": 2416 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274890356.410, "dur": 3.916, + "args": { + "External id": 4055410,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 2417 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274890358.246, "dur": 1.636, + "args": { + "External id": 4055411,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 2418 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274890358.866, "dur": 0.933, + "args": { + "External id": 4055412,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 2419 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274890363.844, "dur": 6.153, + "args": { + "External id": 4055413,"Record function id": 0, "Ev Idx": 2420 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274890365.315, "dur": 4.272, + "args": { + "External id": 4055414,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 2421 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274890365.819, "dur": 3.373, + "args": { + "External id": 4055415,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 2422 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274890366.165, "dur": 2.942, + "args": { + "External id": 4055416,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 2423 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274890373.059, "dur": 3.844, + "args": { + "External id": 4055417,"Record function id": 0, "Ev Idx": 2424 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274890374.464, "dur": 2.023, + "args": { + "External id": 4055418,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 2425 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274890375.135, "dur": 0.936, + "args": { + "External id": 4055419,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 2426 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274890375.410, "dur": 0.571, + "args": { + "External id": 4055420,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 2427 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274890379.933, "dur": 3.751, + "args": { + "External id": 4055421,"Record function id": 0, "Ev Idx": 2428 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274890380.999, "dur": 2.282, + "args": { + "External id": 4055422,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 2429 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274890381.510, "dur": 1.306, + "args": { + "External id": 4055423,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 2430 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274890381.954, "dur": 0.750, + "args": { + "External id": 4055424,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 2431 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274890386.847, "dur": 3.900, + "args": { + "External id": 4055425,"Record function id": 0, "Ev Idx": 2432 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274890388.255, "dur": 2.102, + "args": { + "External id": 4055426,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 2433 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274890388.793, "dur": 1.160, + "args": { + "External id": 4055427,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 2434 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274890389.087, "dur": 0.761, + "args": { + "External id": 4055428,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 2435 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274890393.776, "dur": 3.633, + "args": { + "External id": 4055429,"Record function id": 0, "Ev Idx": 2436 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274890395.167, "dur": 1.803, + "args": { + "External id": 4055430,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 2437 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274890395.619, "dur": 0.960, + "args": { + "External id": 4055431,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 2438 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274890395.873, "dur": 0.630, + "args": { + "External id": 4055432,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 2439 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274890400.393, "dur": 3.953, + "args": { + "External id": 4055433,"Record function id": 0, "Ev Idx": 2440 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274890401.639, "dur": 2.310, + "args": { + "External id": 4055434,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 2441 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274890402.235, "dur": 1.302, + "args": { + "External id": 4055435,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 2442 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274890402.696, "dur": 0.741, + "args": { + "External id": 4055436,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 2443 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RegisterPostBackwardFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1655274890407.716, "dur": 37388.328, + "args": { + "External id": 4055437,"Record function id": 0, "Sequence number": 40618397, "Fwd thread id": 1, "Ev Idx": 2444 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1655274890408.900, "dur": 37378.702, + "args": { + "External id": 4055438,"Sequence number": 40618397, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 2445 + } + }, + { + "ph": "f", "id": 183, "pid": 1336756, "tid": 1381189, "ts": 1655274890408.900, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.22)", "pid": 1336756, "tid": 1381189, + "ts": 1655274890456.329, "dur": 38.342, + "args": { + "External id": 4055439,"Record function id": 0, "Ev Idx": 2446 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.22)", "pid": 1336756, "tid": 1381189, + "ts": 1655274890502.758, "dur": 60.008, + "args": { + "External id": 4055440,"Record function id": 0, "Ev Idx": 2447 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.22)", "pid": 1336756, "tid": 1381189, + "ts": 1655274890568.797, "dur": 37210.090, + "args": { + "External id": 4055441,"Record function id": 0, "Ev Idx": 2448 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655274890655.388, "dur": 6.686, + "args": { + "External id": 4055442,"Record function id": 0, "Concrete Inputs": ["[51384320]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2449 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274890671.977, "dur": 4.953, + "args": { + "External id": 4055443,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[51384320], []], "Ev Idx": 2450 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::chunk_cat", "pid": 1336756, "tid": 1381189, + "ts": 1655274890691.444, "dur": 36261.614, + "args": { + "External id": 4055444,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [2048, 1], [2048, 1], [2048, 1], [2048, 1], [1], [2048, 1], [2048, 1], [5632, 1]], [], [], [6423040, 1]], "Input Dims": [[[2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048], [5632, 2048], [5632, 2048], [2048, 5632]], [], [], [8, 6423040]], "Ev Idx": 2451 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_chunk_cat", "pid": 1336756, "tid": 1381189, + "ts": 1655274890705.138, "dur": 36238.999, + "args": { + "External id": 4055445,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [2048, 1], [2048, 1], [2048, 1], [2048, 1], [1], [2048, 1], [2048, 1], [5632, 1]], [], [], [6423040, 1]], "Input Dims": [[[2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048], [5632, 2048], [5632, 2048], [2048, 5632]], [], [], [8, 6423040]], "Ev Idx": 2452 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655274890757.666, "dur": 15.193, + "args": { + "External id": 4055446,"Record function id": 0, "Concrete Inputs": ["[12602]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2453 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1381189, + "ts": 1655274890779.508, "dur": 36125.578, + "args": { + "External id": 4055447,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[12602], [], [], [], [], [], [], []], "Ev Idx": 2454 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336756, "tid": 1381189, + "ts": 1655274890782.280, "dur": 36122.149, + "args": { + "External id": 4055448,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[12602], [], [], [], [], [], []], "Ev Idx": 2455 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274890786.658, "dur": 4.561, + "args": { + "External id": 4055449,"Record function id": 0, "Concrete Inputs": ["[12602]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2456 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1381189, + "ts": 1655274890793.114, "dur": 36107.637, + "args": { + "External id": 4055450,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[12602], [12602], []], "Ev Idx": 2457 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 1336756, "tid": 1381189, + "ts": 1655274927074.630, "dur": 9.995, + "args": { + "External id": 4055451,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "", "", "", "False"], "Input type": ["float", "ScalarList", "", "", "", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[51384320], [], [], [], [], []], "Ev Idx": 2458 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655274927078.009, "dur": 6.025, + "args": { + "External id": 4055452,"Record function id": 0, "Concrete Inputs": ["[6423040]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2459 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_reduce_scatter_base_", "pid": 1336756, "tid": 1381189, + "ts": 1655274927115.969, "dur": 362.851, + "args": { + "External id": 4055453,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "-1"], "Input type": ["float", "float", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], [], []], "Input Dims": [[6423040], [51384320], [], [], [], []], "Ev Idx": 2460 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336756, "tid": 1381189, + "ts": 1655274927143.175, "dur": 329.961, + "args": { + "External id": 4055454,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 3, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "3", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 6423040, "Process Group Name": "0", "Input type": ["float", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[51384320], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 2461, "In msg nelems": 51384320 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_reduce_scatter_base", "pid": 1336756, "tid": 1381189, + "ts": 1655274927155.120, "dur": 311.883, + "args": { + "External id": 4055455,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[51384320]], "Ev Idx": 2462 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336756, "tid": 1381189, + "ts": 1655274927500.414, "dur": 2.394, + "args": { + "External id": 4055456,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "3", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 2463, "In msg nelems": 0, "Rank": 3, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274927562.785, "dur": 6.893, + "args": { + "External id": 4055457,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2464 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274927617.050, "dur": 1.470, + "args": { + "External id": 4055458,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "256"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2465 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274927635.139, "dur": 1.161, + "args": { + "External id": 4055459,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "524544"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2466 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274927650.913, "dur": 0.915, + "args": { + "External id": 4055460,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "1048832"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2467 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274927663.718, "dur": 0.937, + "args": { + "External id": 4055461,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "1573120"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2468 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274927676.277, "dur": 0.822, + "args": { + "External id": 4055462,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2469 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274927689.670, "dur": 1.058, + "args": { + "External id": 4055463,"Record function id": 0, "Concrete Inputs": ["", "[704, 2048]", "[2048, 1]", "2097664"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2470 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274927704.303, "dur": 1.733, + "args": { + "External id": 4055464,"Record function id": 0, "Concrete Inputs": ["", "[704, 2048]", "[2048, 1]", "3539456"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2471 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274927716.970, "dur": 1.015, + "args": { + "External id": 4055465,"Record function id": 0, "Concrete Inputs": ["", "[256, 5632]", "[5632, 1]", "4981248"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2472 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: CompiledFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1655274927811.263, "dur": 2733.916, + "args": { + "External id": 4055466,"Record function id": 0, "Ev Idx": 2473 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.21)", "pid": 1336756, "tid": 1381189, + "ts": 1655274927830.712, "dur": 1013.657, + "args": { + "External id": 4055467,"Record function id": 0, "Ev Idx": 2474 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.21)", "pid": 1336756, "tid": 1381189, + "ts": 1655274927844.840, "dur": 368.393, + "args": { + "External id": 4055468,"Record function id": 0, "Ev Idx": 2475 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274927919.840, "dur": 3.941, + "args": { + "External id": 4055469,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[51384320], []], "Ev Idx": 2476 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274927927.248, "dur": 1.058, + "args": { + "External id": 4055470,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 2477 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274927930.012, "dur": 1.027, + "args": { + "External id": 4055471,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 2478 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274927932.532, "dur": 2.791, + "args": { + "External id": 4055472,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 2479 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274927936.914, "dur": 0.951, + "args": { + "External id": 4055473,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 2480 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274927939.615, "dur": 1.140, + "args": { + "External id": 4055474,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 2481 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274927942.384, "dur": 1.717, + "args": { + "External id": 4055475,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 2482 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274927945.624, "dur": 0.975, + "args": { + "External id": 4055476,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 2483 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274927948.025, "dur": 1.137, + "args": { + "External id": 4055477,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 2484 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274927950.566, "dur": 0.791, + "args": { + "External id": 4055478,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 2485 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 1336756, "tid": 1381189, + "ts": 1655274927970.156, "dur": 204.452, + "args": { + "External id": 4055479,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 2486 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 1336756, "tid": 1381189, + "ts": 1655274928038.104, "dur": 132.027, + "args": { + "External id": 4055480,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 2487 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655274928056.306, "dur": 13.128, + "args": { + "External id": 4055481,"Record function id": 0, "Concrete Inputs": ["[2133]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2488 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1381189, + "ts": 1655274928072.942, "dur": 69.029, + "args": { + "External id": 4055482,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], [], []], "Ev Idx": 2489 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336756, "tid": 1381189, + "ts": 1655274928075.590, "dur": 66.021, + "args": { + "External id": 4055483,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], []], "Ev Idx": 2490 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274928079.805, "dur": 7.792, + "args": { + "External id": 4055484,"Record function id": 0, "Concrete Inputs": ["[2133]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2491 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1381189, + "ts": 1655274928089.477, "dur": 51.581, + "args": { + "External id": 4055485,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[2133], [2133], []], "Ev Idx": 2492 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::backward_prefetch for model.layers.20", "pid": 1336756, "tid": 1381189, + "ts": 1655274928290.232, "dur": 546.266, + "args": { + "External id": 4055486,"Record function id": 0, "Ev Idx": 2493 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.20)", "pid": 1336756, "tid": 1381189, + "ts": 1655274928307.001, "dur": 516.199, + "args": { + "External id": 4055487,"Record function id": 0, "Ev Idx": 2494 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655274928361.190, "dur": 4.380, + "args": { + "External id": 4055488,"Record function id": 0, "Concrete Inputs": ["[6423040]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2495 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336756, "tid": 1381189, + "ts": 1655274928381.358, "dur": 31.563, + "args": { + "External id": 4055489,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 2496 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274928386.353, "dur": 1.542, + "args": { + "External id": 4055490,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2497 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274928390.293, "dur": 0.599, + "args": { + "External id": 4055491,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2498 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274928392.635, "dur": 0.472, + "args": { + "External id": 4055492,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2499 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274928394.676, "dur": 0.571, + "args": { + "External id": 4055493,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2500 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274928397.042, "dur": 0.429, + "args": { + "External id": 4055494,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2501 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274928399.214, "dur": 0.474, + "args": { + "External id": 4055495,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2502 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274928401.878, "dur": 2.518, + "args": { + "External id": 4055496,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2503 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274928406.054, "dur": 0.585, + "args": { + "External id": 4055497,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2504 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274928408.235, "dur": 0.371, + "args": { + "External id": 4055498,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2505 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336756, "tid": 1381189, + "ts": 1655274928438.645, "dur": 31.589, + "args": { + "External id": 4055499,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 2506 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 1336756, "tid": 1381189, + "ts": 1655274928506.398, "dur": 100.979, + "args": { + "External id": 4055500,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "6423040", "8", "3", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [], [], [], [], [], []], "Ev Idx": 2507 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655274928517.415, "dur": 3.800, + "args": { + "External id": 4055501,"Record function id": 0, "Concrete Inputs": ["[51384320]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2508 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 1336756, "tid": 1381189, + "ts": 1655274928527.238, "dur": 10.708, + "args": { + "External id": 4055502,"Record function id": 0, "Concrete Inputs": ["", "0", "19269120", "6423040"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 2509 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1381189, + "ts": 1655274928531.336, "dur": 6.217, + "args": { + "External id": 4055503,"Record function id": 0, "Concrete Inputs": ["", "0", "19269120", "25692160", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[51384320], [], [], [], []], "Ev Idx": 2510 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274928535.439, "dur": 0.569, + "args": { + "External id": 4055504,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "[1]", "19269120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 2511 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336756, "tid": 1381189, + "ts": 1655274928545.235, "dur": 27.104, + "args": { + "External id": 4055505,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 2512 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274928547.703, "dur": 0.394, + "args": { + "External id": 4055506,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "19269120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2513 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274928550.057, "dur": 0.441, + "args": { + "External id": 4055507,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "19269376"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2514 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274928552.339, "dur": 0.427, + "args": { + "External id": 4055508,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "19793664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2515 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274928554.620, "dur": 2.265, + "args": { + "External id": 4055509,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "20317952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2516 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274928559.017, "dur": 0.396, + "args": { + "External id": 4055510,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "20842240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2517 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274928561.555, "dur": 0.427, + "args": { + "External id": 4055511,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "21366528"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2518 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274928563.679, "dur": 0.397, + "args": { + "External id": 4055512,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "21366784"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2519 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274928566.137, "dur": 0.415, + "args": { + "External id": 4055513,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "22808576"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2520 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274928568.251, "dur": 0.704, + "args": { + "External id": 4055514,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "24250368"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2521 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336756, "tid": 1381189, + "ts": 1655274928581.453, "dur": 18.900, + "args": { + "External id": 4055515,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 2522 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 1336756, "tid": 1381189, + "ts": 1655274928651.986, "dur": 107.265, + "args": { + "External id": 4055516,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[51384320], [6423040], [], [], []], "Ev Idx": 2523 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336756, "tid": 1381189, + "ts": 1655274928673.552, "dur": 82.473, + "args": { + "External id": 4055517,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 3, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "3", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 51384320, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[6423040], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 2524, "In msg nelems": 6423040 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 1336756, "tid": 1381189, + "ts": 1655274928683.193, "dur": 68.602, + "args": { + "External id": 4055518,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[6423040]], "Ev Idx": 2525 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336756, "tid": 1381189, + "ts": 1655274928773.022, "dur": 1.846, + "args": { + "External id": 4055519,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "3", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 2526, "In msg nelems": 0, "Rank": 3, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1655274928851.011, "dur": 1674.890, + "args": { + "External id": 4055520,"Sequence number": 40618396, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 2527 + } + }, + { + "ph": "f", "id": 184, "pid": 1336756, "tid": 1381189, "ts": 1655274928851.011, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655274928953.071, "dur": 144.000, + "args": { + "External id": 4055521,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [5632, 1], [5632, 1]], "Input Dims": [[65536, 2048], [2048, 5632], [65536, 5632]], "Ev Idx": 2528 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_add_mul_rsub_silu_0", "pid": 1336756, "tid": 1381189, + "ts": 1655274929141.680, "dur": 38.425, + "args": { + "External id": 4055522,"kernel_hash": "c2zszzsomz26dv2qwvmiurvgyrl5qxtyn6ocoqkdpzzhfzwqp5q6", "grid": "grid(369098752,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "369098752"], "kernel_file": "/tmp/torchinductor_cvm/2z/c2zszzsomz26dv2qwvmiurvgyrl5qxtyn6ocoqkdpzzhfzwqp5q6.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[5632, 1], [5632, 1], [5632, 1], [23068672, 5632, 1], [23068672, 5632, 1], [23068672, 5632, 1], []], "Input Dims": [[65536, 5632], [65536, 5632], [65536, 5632], [16, 4096, 5632], [16, 4096, 5632], [16, 4096, 5632], []], "Ev Idx": 2529 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 1336756, "tid": 1381189, + "ts": 1655274929197.886, "dur": 53.416, + "args": { + "External id": 4055523,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[0, 1, 2048], [0, 5632, 1], [11534336, 5632, 1]], "Input Dims": [[1, 2048, 65536], [1, 65536, 5632], [1, 2048, 5632]], "Ev Idx": 2530 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655274929261.346, "dur": 33.660, + "args": { + "External id": 4055524,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 5632], [2048, 1], [2048, 1]], "Input Dims": [[5632, 65536], [65536, 2048], [5632, 2048]], "Ev Idx": 2531 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655274929304.227, "dur": 46.516, + "args": { + "External id": 4055525,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 5632], [5632, 2048], [65536, 2048]], "Ev Idx": 2532 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655274929358.994, "dur": 29.455, + "args": { + "External id": 4055526,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 5632], [2048, 1], [2048, 1]], "Input Dims": [[5632, 65536], [65536, 2048], [5632, 2048]], "Ev Idx": 2533 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655274929395.880, "dur": 51.824, + "args": { + "External id": 4055527,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 5632], [5632, 2048], [65536, 2048]], "Ev Idx": 2534 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_1", "pid": 1336756, "tid": 1381189, + "ts": 1655274929473.119, "dur": 23.486, + "args": { + "External id": 4055528,"kernel_hash": "cjd6g3jfgntyoifzno6l2urmnhif7alxtw6zz7miov66vywxwv7d", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/jd/cjd6g3jfgntyoifzno6l2urmnhif7alxtw6zz7miov66vywxwv7d.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[65536, 2048], [65536, 2048], []], "Ev Idx": 2535 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 1336756, "tid": 1381189, + "ts": 1655274929517.766, "dur": 28.438, + "args": { + "External id": 4055529,"kernel_hash": "cxhg545cyph4gbk5vymzyh72vho7oogk3ycan2lp4cxntklp5hew", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "65536", "2048", "1", "497", "132", "True", "2048", "True", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/xh/cxhg545cyph4gbk5vymzyh72vho7oogk3ycan2lp4cxntklp5hew.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [1], [2048, 1], [2048, 1], [2048, 1], [2048, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [2048], [65536, 2048], [65536, 2048], [132, 2048], [65536, 2048], [65536], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 2536 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 1336756, "tid": 1381189, + "ts": 1655274929564.995, "dur": 19.080, + "args": { + "External id": 4055530,"kernel_hash": "cu42i6zmxtvs2i7cs6x4ixaexke3lhgdiaye5oxwm7s3u6em6co4", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "66"], "kernel_file": "/tmp/torchinductor_cvm/u4/cu42i6zmxtvs2i7cs6x4ixaexke3lhgdiaye5oxwm7s3u6em6co4.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [4096, 1, 2048], [], []], "Input Dims": [[132, 2048], [1, 2048, 2], [], []], "Ev Idx": 2537 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 1336756, "tid": 1381189, + "ts": 1655274929597.975, "dur": 14.514, + "args": { + "External id": 4055531,"kernel_hash": "ckihofrorhmzazt2wfn2dz2m5wfx3auisu2gvfo2jsepr4zyekmq", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "2"], "kernel_file": "/tmp/torchinductor_cvm/ki/ckihofrorhmzazt2wfn2dz2m5wfx3auisu2gvfo2jsepr4zyekmq.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1, 2048], [2048, 1], [], []], "Input Dims": [[1, 2048, 2], [1, 2048], [], []], "Ev Idx": 2538 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655274929623.323, "dur": 33.865, + "args": { + "External id": 4055532,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 2539 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655274929660.561, "dur": 34.154, + "args": { + "External id": 4055533,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 2540 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 1336756, "tid": 1381189, + "ts": 1655274929724.243, "dur": 169.586, + "args": { + "External id": 4055534,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.125", "True", "-1", "-1", "0.", "", "False", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar", "long int"], "Input Strides": [[8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [131072, 4096, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 32, 4096], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 2541 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655274929801.226, "dur": 6.278, + "args": { + "External id": 4055535,"Record function id": 0, "Concrete Inputs": ["[16, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2542 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655274929809.960, "dur": 2.715, + "args": { + "External id": 4055536,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2543 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336756, "tid": 1381189, + "ts": 1655274929944.829, "dur": 24.477, + "args": { + "External id": 4055537,"kernel_hash": "cb6oumcqb462ndf2ivcd2sc6qg6mfjahptjw4ih7cesqhfpziv3b", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/b6/cb6oumcqb462ndf2ivcd2sc6qg6mfjahptjw4ih7cesqhfpziv3b.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 2544 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336756, "tid": 1381189, + "ts": 1655274929982.707, "dur": 56.466, + "args": { + "External id": 4055538,"kernel_hash": "cb6oumcqb462ndf2ivcd2sc6qg6mfjahptjw4ih7cesqhfpziv3b", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/b6/cb6oumcqb462ndf2ivcd2sc6qg6mfjahptjw4ih7cesqhfpziv3b.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 2545 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655274930052.248, "dur": 42.924, + "args": { + "External id": 4055539,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 2546 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655274930102.123, "dur": 36.499, + "args": { + "External id": 4055540,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 2547 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655274930148.115, "dur": 21.029, + "args": { + "External id": 4055541,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 2548 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655274930174.851, "dur": 30.670, + "args": { + "External id": 4055542,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 2549 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655274930212.305, "dur": 20.921, + "args": { + "External id": 4055543,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 2550 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655274930240.858, "dur": 42.253, + "args": { + "External id": 4055544,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 2551 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_4", "pid": 1336756, "tid": 1381189, + "ts": 1655274930308.103, "dur": 25.131, + "args": { + "External id": 4055545,"kernel_hash": "c7pqhdjojzeazwsh5g3ibnyk4m2nfh3q73e3zc7hljz4yvhe7c4h", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/7p/c7pqhdjojzeazwsh5g3ibnyk4m2nfh3q73e3zc7hljz4yvhe7c4h.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1], []], "Input Dims": [[65536, 2048], [65536, 2048], [65536, 2048], []], "Ev Idx": 2552 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_2", "pid": 1336756, "tid": 1381189, + "ts": 1655274930356.554, "dur": 22.916, + "args": { + "External id": 4055546,"kernel_hash": "cvgvwkysjpcw75q5t3guce5bep2so25f7i5zxc6ipt5f56shof73", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "65536", "2048", "1", "497", "132", "True", "2048", "False", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/vg/cvgvwkysjpcw75q5t3guce5bep2so25f7i5zxc6ipt5f56shof73.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [1], [2048, 1], [2048, 1], [2048, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [2048], [65536, 2048], [65536, 2048], [132, 2048], [65536], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 2553 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 1336756, "tid": 1381189, + "ts": 1655274930394.847, "dur": 16.207, + "args": { + "External id": 4055547,"kernel_hash": "cu42i6zmxtvs2i7cs6x4ixaexke3lhgdiaye5oxwm7s3u6em6co4", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "66"], "kernel_file": "/tmp/torchinductor_cvm/u4/cu42i6zmxtvs2i7cs6x4ixaexke3lhgdiaye5oxwm7s3u6em6co4.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [4096, 1, 2048], [], []], "Input Dims": [[132, 2048], [1, 2048, 2], [], []], "Ev Idx": 2554 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 1336756, "tid": 1381189, + "ts": 1655274930449.493, "dur": 16.391, + "args": { + "External id": 4055548,"kernel_hash": "ckihofrorhmzazt2wfn2dz2m5wfx3auisu2gvfo2jsepr4zyekmq", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "2"], "kernel_file": "/tmp/torchinductor_cvm/ki/ckihofrorhmzazt2wfn2dz2m5wfx3auisu2gvfo2jsepr4zyekmq.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1, 2048], [2048, 1], [], []], "Input Dims": [[1, 2048, 2], [1, 2048], [], []], "Ev Idx": 2555 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_5", "pid": 1336756, "tid": 1381189, + "ts": 1655274930478.653, "dur": 19.044, + "args": { + "External id": 4055549,"kernel_hash": "cckrpn5uuxyvbancoio3sz2onrjto236n54xx4ycphq5p6r3jlfj", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/ck/cckrpn5uuxyvbancoio3sz2onrjto236n54xx4ycphq5p6r3jlfj.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [8388608, 2048, 1], []], "Input Dims": [[65536, 2048], [65536, 2048], [16, 4096, 2048], []], "Ev Idx": 2556 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274930568.187, "dur": 40.818, + "args": { + "External id": 4055550,"Record function id": 0, "Ev Idx": 2557 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274930571.841, "dur": 36.230, + "args": { + "External id": 4055551,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 2558 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274930576.187, "dur": 30.838, + "args": { + "External id": 4055552,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 2559 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274930602.550, "dur": 4.315, + "args": { + "External id": 4055553,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 2560 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274930613.217, "dur": 5.245, + "args": { + "External id": 4055554,"Record function id": 0, "Ev Idx": 2561 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274930614.673, "dur": 3.319, + "args": { + "External id": 4055555,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 2562 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274930615.321, "dur": 2.204, + "args": { + "External id": 4055556,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 2563 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274930616.351, "dur": 1.034, + "args": { + "External id": 4055557,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 2564 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274930621.635, "dur": 5.830, + "args": { + "External id": 4055558,"Record function id": 0, "Ev Idx": 2565 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274930622.724, "dur": 4.313, + "args": { + "External id": 4055559,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 2566 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274930623.229, "dur": 3.375, + "args": { + "External id": 4055560,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 2567 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274930623.545, "dur": 2.989, + "args": { + "External id": 4055561,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 2568 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274930630.530, "dur": 3.858, + "args": { + "External id": 4055562,"Record function id": 0, "Ev Idx": 2569 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274930631.944, "dur": 2.039, + "args": { + "External id": 4055563,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 2570 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274930632.431, "dur": 1.132, + "args": { + "External id": 4055564,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 2571 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274930632.770, "dur": 0.733, + "args": { + "External id": 4055565,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 2572 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274930637.413, "dur": 3.291, + "args": { + "External id": 4055566,"Record function id": 0, "Ev Idx": 2573 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274930638.490, "dur": 1.815, + "args": { + "External id": 4055567,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 2574 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274930638.973, "dur": 0.938, + "args": { + "External id": 4055568,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 2575 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274930639.254, "dur": 0.592, + "args": { + "External id": 4055569,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 2576 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274930644.268, "dur": 3.621, + "args": { + "External id": 4055570,"Record function id": 0, "Ev Idx": 2577 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274930645.459, "dur": 2.048, + "args": { + "External id": 4055571,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 2578 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274930645.942, "dur": 1.163, + "args": { + "External id": 4055572,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 2579 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274930646.390, "dur": 0.627, + "args": { + "External id": 4055573,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 2580 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274930651.336, "dur": 3.694, + "args": { + "External id": 4055574,"Record function id": 0, "Ev Idx": 2581 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274930652.533, "dur": 2.111, + "args": { + "External id": 4055575,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 2582 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274930653.016, "dur": 1.223, + "args": { + "External id": 4055576,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 2583 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274930653.516, "dur": 0.652, + "args": { + "External id": 4055577,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 2584 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274930658.455, "dur": 5.787, + "args": { + "External id": 4055578,"Record function id": 0, "Ev Idx": 2585 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274930659.737, "dur": 4.061, + "args": { + "External id": 4055579,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 2586 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274930660.185, "dur": 3.213, + "args": { + "External id": 4055580,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 2587 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274930662.531, "dur": 0.771, + "args": { + "External id": 4055581,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 2588 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274930667.581, "dur": 3.748, + "args": { + "External id": 4055582,"Record function id": 0, "Ev Idx": 2589 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274930668.820, "dur": 2.086, + "args": { + "External id": 4055583,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 2590 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274930669.268, "dur": 1.250, + "args": { + "External id": 4055584,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 2591 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274930669.846, "dur": 0.587, + "args": { + "External id": 4055585,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 2592 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RegisterPostBackwardFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1655274930675.085, "dur": 36450.717, + "args": { + "External id": 4055586,"Record function id": 0, "Sequence number": 40618395, "Fwd thread id": 1, "Ev Idx": 2593 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1655274930676.353, "dur": 36440.317, + "args": { + "External id": 4055587,"Sequence number": 40618395, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 2594 + } + }, + { + "ph": "f", "id": 185, "pid": 1336756, "tid": 1381189, "ts": 1655274930676.353, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.21)", "pid": 1336756, "tid": 1381189, + "ts": 1655274930706.978, "dur": 38.261, + "args": { + "External id": 4055588,"Record function id": 0, "Ev Idx": 2595 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.21)", "pid": 1336756, "tid": 1381189, + "ts": 1655274930753.257, "dur": 61.677, + "args": { + "External id": 4055589,"Record function id": 0, "Ev Idx": 2596 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.21)", "pid": 1336756, "tid": 1381189, + "ts": 1655274930820.887, "dur": 36286.891, + "args": { + "External id": 4055590,"Record function id": 0, "Ev Idx": 2597 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655274930908.819, "dur": 6.078, + "args": { + "External id": 4055591,"Record function id": 0, "Concrete Inputs": ["[51384320]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2598 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274930925.025, "dur": 6.694, + "args": { + "External id": 4055592,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[51384320], []], "Ev Idx": 2599 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::chunk_cat", "pid": 1336756, "tid": 1381189, + "ts": 1655274930951.656, "dur": 35280.815, + "args": { + "External id": 4055593,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [2048, 1], [2048, 1], [2048, 1], [2048, 1], [1], [2048, 1], [2048, 1], [5632, 1]], [], [], [6423040, 1]], "Input Dims": [[[2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048], [5632, 2048], [5632, 2048], [2048, 5632]], [], [], [8, 6423040]], "Ev Idx": 2600 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_chunk_cat", "pid": 1336756, "tid": 1381189, + "ts": 1655274930965.189, "dur": 35258.032, + "args": { + "External id": 4055594,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [2048, 1], [2048, 1], [2048, 1], [2048, 1], [1], [2048, 1], [2048, 1], [5632, 1]], [], [], [6423040, 1]], "Input Dims": [[[2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048], [5632, 2048], [5632, 2048], [2048, 5632]], [], [], [8, 6423040]], "Ev Idx": 2601 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655274931052.654, "dur": 14.681, + "args": { + "External id": 4055595,"Record function id": 0, "Concrete Inputs": ["[12602]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2602 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1381189, + "ts": 1655274931074.098, "dur": 35103.531, + "args": { + "External id": 4055596,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[12602], [], [], [], [], [], [], []], "Ev Idx": 2603 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336756, "tid": 1381189, + "ts": 1655274931076.940, "dur": 35100.055, + "args": { + "External id": 4055597,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[12602], [], [], [], [], [], []], "Ev Idx": 2604 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274931081.542, "dur": 6.398, + "args": { + "External id": 4055598,"Record function id": 0, "Concrete Inputs": ["[12602]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2605 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1381189, + "ts": 1655274931090.045, "dur": 35083.221, + "args": { + "External id": 4055599,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[12602], [12602], []], "Ev Idx": 2606 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 1336756, "tid": 1381189, + "ts": 1655274966324.147, "dur": 9.153, + "args": { + "External id": 4055600,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "", "", "", "False"], "Input type": ["float", "ScalarList", "", "", "", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[51384320], [], [], [], [], []], "Ev Idx": 2607 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655274966327.412, "dur": 5.531, + "args": { + "External id": 4055601,"Record function id": 0, "Concrete Inputs": ["[6423040]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2608 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_reduce_scatter_base_", "pid": 1336756, "tid": 1381189, + "ts": 1655274966365.127, "dur": 396.685, + "args": { + "External id": 4055602,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "-1"], "Input type": ["float", "float", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], [], []], "Input Dims": [[6423040], [51384320], [], [], [], []], "Ev Idx": 2609 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336756, "tid": 1381189, + "ts": 1655274966392.760, "dur": 363.389, + "args": { + "External id": 4055603,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 3, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "3", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 6423040, "Process Group Name": "0", "Input type": ["float", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[51384320], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 2610, "In msg nelems": 51384320 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_reduce_scatter_base", "pid": 1336756, "tid": 1381189, + "ts": 1655274966404.547, "dur": 345.186, + "args": { + "External id": 4055604,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[51384320]], "Ev Idx": 2611 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336756, "tid": 1381189, + "ts": 1655274966784.191, "dur": 2.653, + "args": { + "External id": 4055605,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "3", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 2612, "In msg nelems": 0, "Rank": 3, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274966848.412, "dur": 6.820, + "args": { + "External id": 4055606,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2613 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274966902.723, "dur": 1.334, + "args": { + "External id": 4055607,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "256"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2614 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274966921.796, "dur": 3.001, + "args": { + "External id": 4055608,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "524544"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2615 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274966937.529, "dur": 1.007, + "args": { + "External id": 4055609,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "1048832"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2616 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274966951.892, "dur": 0.917, + "args": { + "External id": 4055610,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "1573120"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2617 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274966963.701, "dur": 0.900, + "args": { + "External id": 4055611,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2618 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274966976.916, "dur": 2.496, + "args": { + "External id": 4055612,"Record function id": 0, "Concrete Inputs": ["", "[704, 2048]", "[2048, 1]", "2097664"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2619 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274967030.367, "dur": 2.498, + "args": { + "External id": 4055613,"Record function id": 0, "Concrete Inputs": ["", "[704, 2048]", "[2048, 1]", "3539456"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2620 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274967045.009, "dur": 0.762, + "args": { + "External id": 4055614,"Record function id": 0, "Concrete Inputs": ["", "[256, 5632]", "[5632, 1]", "4981248"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2621 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: CompiledFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1655274967141.797, "dur": 2667.234, + "args": { + "External id": 4055615,"Record function id": 0, "Ev Idx": 2622 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.20)", "pid": 1336756, "tid": 1381189, + "ts": 1655274967161.562, "dur": 1021.920, + "args": { + "External id": 4055616,"Record function id": 0, "Ev Idx": 2623 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.20)", "pid": 1336756, "tid": 1381189, + "ts": 1655274967176.058, "dur": 344.842, + "args": { + "External id": 4055617,"Record function id": 0, "Ev Idx": 2624 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274967251.117, "dur": 3.979, + "args": { + "External id": 4055618,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[51384320], []], "Ev Idx": 2625 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274967258.204, "dur": 1.009, + "args": { + "External id": 4055619,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 2626 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274967261.072, "dur": 3.139, + "args": { + "External id": 4055620,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 2627 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274967266.323, "dur": 0.761, + "args": { + "External id": 4055621,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 2628 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274967268.717, "dur": 0.880, + "args": { + "External id": 4055622,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 2629 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274967271.701, "dur": 0.774, + "args": { + "External id": 4055623,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 2630 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274967274.055, "dur": 1.894, + "args": { + "External id": 4055624,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 2631 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274967277.375, "dur": 0.868, + "args": { + "External id": 4055625,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 2632 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274967279.654, "dur": 0.773, + "args": { + "External id": 4055626,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 2633 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274967282.241, "dur": 0.564, + "args": { + "External id": 4055627,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 2634 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 1336756, "tid": 1381189, + "ts": 1655274967303.826, "dur": 180.082, + "args": { + "External id": 4055628,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 2635 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 1336756, "tid": 1381189, + "ts": 1655274967320.229, "dur": 158.857, + "args": { + "External id": 4055629,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 2636 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655274967345.337, "dur": 15.329, + "args": { + "External id": 4055630,"Record function id": 0, "Concrete Inputs": ["[2133]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2637 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1381189, + "ts": 1655274967364.178, "dur": 86.026, + "args": { + "External id": 4055631,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], [], []], "Ev Idx": 2638 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336756, "tid": 1381189, + "ts": 1655274967366.882, "dur": 82.908, + "args": { + "External id": 4055632,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], []], "Ev Idx": 2639 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274967371.304, "dur": 5.554, + "args": { + "External id": 4055633,"Record function id": 0, "Concrete Inputs": ["[2133]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2640 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1381189, + "ts": 1655274967378.954, "dur": 69.715, + "args": { + "External id": 4055634,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[2133], [2133], []], "Ev Idx": 2641 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::backward_prefetch for model.layers.19", "pid": 1336756, "tid": 1381189, + "ts": 1655274967601.127, "dur": 574.422, + "args": { + "External id": 4055635,"Record function id": 0, "Ev Idx": 2642 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.19)", "pid": 1336756, "tid": 1381189, + "ts": 1655274967618.459, "dur": 544.012, + "args": { + "External id": 4055636,"Record function id": 0, "Ev Idx": 2643 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655274967674.229, "dur": 5.066, + "args": { + "External id": 4055637,"Record function id": 0, "Concrete Inputs": ["[6423040]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2644 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336756, "tid": 1381189, + "ts": 1655274967695.099, "dur": 31.293, + "args": { + "External id": 4055638,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 2645 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274967700.133, "dur": 1.455, + "args": { + "External id": 4055639,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2646 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274967703.865, "dur": 0.461, + "args": { + "External id": 4055640,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2647 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274967706.885, "dur": 0.515, + "args": { + "External id": 4055641,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2648 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274967709.500, "dur": 0.649, + "args": { + "External id": 4055642,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2649 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274967711.677, "dur": 0.334, + "args": { + "External id": 4055643,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2650 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274967713.551, "dur": 2.162, + "args": { + "External id": 4055644,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2651 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274967717.478, "dur": 0.366, + "args": { + "External id": 4055645,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2652 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274967719.384, "dur": 0.449, + "args": { + "External id": 4055646,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2653 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274967721.591, "dur": 0.442, + "args": { + "External id": 4055647,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2654 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336756, "tid": 1381189, + "ts": 1655274967735.442, "dur": 28.731, + "args": { + "External id": 4055648,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 2655 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 1336756, "tid": 1381189, + "ts": 1655274967795.260, "dur": 98.233, + "args": { + "External id": 4055649,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "6423040", "8", "3", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [], [], [], [], [], []], "Ev Idx": 2656 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655274967805.546, "dur": 3.049, + "args": { + "External id": 4055650,"Record function id": 0, "Concrete Inputs": ["[51384320]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2657 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 1336756, "tid": 1381189, + "ts": 1655274967813.785, "dur": 10.209, + "args": { + "External id": 4055651,"Record function id": 0, "Concrete Inputs": ["", "0", "19269120", "6423040"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 2658 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1381189, + "ts": 1655274967818.017, "dur": 5.571, + "args": { + "External id": 4055652,"Record function id": 0, "Concrete Inputs": ["", "0", "19269120", "25692160", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[51384320], [], [], [], []], "Ev Idx": 2659 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274967821.739, "dur": 0.422, + "args": { + "External id": 4055653,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "[1]", "19269120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 2660 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336756, "tid": 1381189, + "ts": 1655274967831.070, "dur": 25.971, + "args": { + "External id": 4055654,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 2661 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274967833.789, "dur": 0.574, + "args": { + "External id": 4055655,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "19269120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2662 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274967835.912, "dur": 0.374, + "args": { + "External id": 4055656,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "19269376"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2663 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274967838.168, "dur": 2.118, + "args": { + "External id": 4055657,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "19793664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2664 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274967842.116, "dur": 0.413, + "args": { + "External id": 4055658,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "20317952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2665 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274967844.181, "dur": 0.349, + "args": { + "External id": 4055659,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "20842240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2666 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274967846.214, "dur": 0.633, + "args": { + "External id": 4055660,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "21366528"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2667 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274967848.723, "dur": 0.502, + "args": { + "External id": 4055661,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "21366784"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2668 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274967850.865, "dur": 0.467, + "args": { + "External id": 4055662,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "22808576"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2669 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274967853.117, "dur": 0.439, + "args": { + "External id": 4055663,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "24250368"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2670 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336756, "tid": 1381189, + "ts": 1655274967867.697, "dur": 18.675, + "args": { + "External id": 4055664,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 2671 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 1336756, "tid": 1381189, + "ts": 1655274967937.687, "dur": 153.654, + "args": { + "External id": 4055665,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[51384320], [6423040], [], [], []], "Ev Idx": 2672 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336756, "tid": 1381189, + "ts": 1655274967960.101, "dur": 126.966, + "args": { + "External id": 4055666,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 3, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "3", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 51384320, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[6423040], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 2673, "In msg nelems": 6423040 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 1336756, "tid": 1381189, + "ts": 1655274967970.060, "dur": 111.910, + "args": { + "External id": 4055667,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[6423040]], "Ev Idx": 2674 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336756, "tid": 1381189, + "ts": 1655274968106.669, "dur": 2.348, + "args": { + "External id": 4055668,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "3", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 2675, "In msg nelems": 0, "Rank": 3, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1655274968190.392, "dur": 1599.262, + "args": { + "External id": 4055669,"Sequence number": 40618394, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 2676 + } + }, + { + "ph": "f", "id": 186, "pid": 1336756, "tid": 1381189, "ts": 1655274968190.392, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655274968297.849, "dur": 102.517, + "args": { + "External id": 4055670,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [5632, 1], [5632, 1]], "Input Dims": [[65536, 2048], [2048, 5632], [65536, 5632]], "Ev Idx": 2677 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_add_mul_rsub_silu_0", "pid": 1336756, "tid": 1381189, + "ts": 1655274968456.604, "dur": 38.628, + "args": { + "External id": 4055671,"kernel_hash": "c2zszzsomz26dv2qwvmiurvgyrl5qxtyn6ocoqkdpzzhfzwqp5q6", "grid": "grid(369098752,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "369098752"], "kernel_file": "/tmp/torchinductor_cvm/2z/c2zszzsomz26dv2qwvmiurvgyrl5qxtyn6ocoqkdpzzhfzwqp5q6.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[5632, 1], [5632, 1], [5632, 1], [23068672, 5632, 1], [23068672, 5632, 1], [23068672, 5632, 1], []], "Input Dims": [[65536, 5632], [65536, 5632], [65536, 5632], [16, 4096, 5632], [16, 4096, 5632], [16, 4096, 5632], []], "Ev Idx": 2678 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 1336756, "tid": 1381189, + "ts": 1655274968514.651, "dur": 54.317, + "args": { + "External id": 4055672,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[0, 1, 2048], [0, 5632, 1], [11534336, 5632, 1]], "Input Dims": [[1, 2048, 65536], [1, 65536, 5632], [1, 2048, 5632]], "Ev Idx": 2679 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655274968580.535, "dur": 33.969, + "args": { + "External id": 4055673,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 5632], [2048, 1], [2048, 1]], "Input Dims": [[5632, 65536], [65536, 2048], [5632, 2048]], "Ev Idx": 2680 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655274968621.720, "dur": 46.916, + "args": { + "External id": 4055674,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 5632], [5632, 2048], [65536, 2048]], "Ev Idx": 2681 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655274968676.443, "dur": 28.624, + "args": { + "External id": 4055675,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 5632], [2048, 1], [2048, 1]], "Input Dims": [[5632, 65536], [65536, 2048], [5632, 2048]], "Ev Idx": 2682 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655274968712.855, "dur": 43.086, + "args": { + "External id": 4055676,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 5632], [5632, 2048], [65536, 2048]], "Ev Idx": 2683 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_1", "pid": 1336756, "tid": 1381189, + "ts": 1655274968781.386, "dur": 21.033, + "args": { + "External id": 4055677,"kernel_hash": "cjd6g3jfgntyoifzno6l2urmnhif7alxtw6zz7miov66vywxwv7d", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/jd/cjd6g3jfgntyoifzno6l2urmnhif7alxtw6zz7miov66vywxwv7d.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[65536, 2048], [65536, 2048], []], "Ev Idx": 2684 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 1336756, "tid": 1381189, + "ts": 1655274968821.695, "dur": 26.862, + "args": { + "External id": 4055678,"kernel_hash": "cxhg545cyph4gbk5vymzyh72vho7oogk3ycan2lp4cxntklp5hew", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "65536", "2048", "1", "497", "132", "True", "2048", "True", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/xh/cxhg545cyph4gbk5vymzyh72vho7oogk3ycan2lp4cxntklp5hew.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [1], [2048, 1], [2048, 1], [2048, 1], [2048, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [2048], [65536, 2048], [65536, 2048], [132, 2048], [65536, 2048], [65536], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 2685 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 1336756, "tid": 1381189, + "ts": 1655274968867.678, "dur": 19.244, + "args": { + "External id": 4055679,"kernel_hash": "cu42i6zmxtvs2i7cs6x4ixaexke3lhgdiaye5oxwm7s3u6em6co4", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "66"], "kernel_file": "/tmp/torchinductor_cvm/u4/cu42i6zmxtvs2i7cs6x4ixaexke3lhgdiaye5oxwm7s3u6em6co4.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [4096, 1, 2048], [], []], "Input Dims": [[132, 2048], [1, 2048, 2], [], []], "Ev Idx": 2686 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 1336756, "tid": 1381189, + "ts": 1655274968899.690, "dur": 14.604, + "args": { + "External id": 4055680,"kernel_hash": "ckihofrorhmzazt2wfn2dz2m5wfx3auisu2gvfo2jsepr4zyekmq", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "2"], "kernel_file": "/tmp/torchinductor_cvm/ki/ckihofrorhmzazt2wfn2dz2m5wfx3auisu2gvfo2jsepr4zyekmq.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1, 2048], [2048, 1], [], []], "Input Dims": [[1, 2048, 2], [1, 2048], [], []], "Ev Idx": 2687 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655274968924.136, "dur": 30.028, + "args": { + "External id": 4055681,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 2688 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655274968957.415, "dur": 69.535, + "args": { + "External id": 4055682,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 2689 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 1336756, "tid": 1381189, + "ts": 1655274969060.589, "dur": 175.926, + "args": { + "External id": 4055683,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.125", "True", "-1", "-1", "0.", "", "False", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar", "long int"], "Input Strides": [[8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [131072, 4096, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 32, 4096], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 2690 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655274969141.492, "dur": 6.346, + "args": { + "External id": 4055684,"Record function id": 0, "Concrete Inputs": ["[16, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2691 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655274969150.038, "dur": 2.462, + "args": { + "External id": 4055685,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2692 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336756, "tid": 1381189, + "ts": 1655274969267.769, "dur": 23.708, + "args": { + "External id": 4055686,"kernel_hash": "cb6oumcqb462ndf2ivcd2sc6qg6mfjahptjw4ih7cesqhfpziv3b", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/b6/cb6oumcqb462ndf2ivcd2sc6qg6mfjahptjw4ih7cesqhfpziv3b.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 2693 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336756, "tid": 1381189, + "ts": 1655274969303.521, "dur": 14.571, + "args": { + "External id": 4055687,"kernel_hash": "cb6oumcqb462ndf2ivcd2sc6qg6mfjahptjw4ih7cesqhfpziv3b", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/b6/cb6oumcqb462ndf2ivcd2sc6qg6mfjahptjw4ih7cesqhfpziv3b.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 2694 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655274969326.595, "dur": 38.808, + "args": { + "External id": 4055688,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 2695 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655274969372.933, "dur": 34.704, + "args": { + "External id": 4055689,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 2696 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655274969434.289, "dur": 27.647, + "args": { + "External id": 4055690,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 2697 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655274969468.779, "dur": 30.492, + "args": { + "External id": 4055691,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 2698 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655274969506.930, "dur": 20.651, + "args": { + "External id": 4055692,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 2699 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655274969534.961, "dur": 30.694, + "args": { + "External id": 4055693,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 2700 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_4", "pid": 1336756, "tid": 1381189, + "ts": 1655274969595.916, "dur": 30.185, + "args": { + "External id": 4055694,"kernel_hash": "c7pqhdjojzeazwsh5g3ibnyk4m2nfh3q73e3zc7hljz4yvhe7c4h", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/7p/c7pqhdjojzeazwsh5g3ibnyk4m2nfh3q73e3zc7hljz4yvhe7c4h.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1], []], "Input Dims": [[65536, 2048], [65536, 2048], [65536, 2048], []], "Ev Idx": 2701 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_2", "pid": 1336756, "tid": 1381189, + "ts": 1655274969646.031, "dur": 22.053, + "args": { + "External id": 4055695,"kernel_hash": "cvgvwkysjpcw75q5t3guce5bep2so25f7i5zxc6ipt5f56shof73", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "65536", "2048", "1", "497", "132", "True", "2048", "False", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/vg/cvgvwkysjpcw75q5t3guce5bep2so25f7i5zxc6ipt5f56shof73.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [1], [2048, 1], [2048, 1], [2048, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [2048], [65536, 2048], [65536, 2048], [132, 2048], [65536], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 2702 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 1336756, "tid": 1381189, + "ts": 1655274969682.454, "dur": 19.675, + "args": { + "External id": 4055696,"kernel_hash": "cu42i6zmxtvs2i7cs6x4ixaexke3lhgdiaye5oxwm7s3u6em6co4", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "66"], "kernel_file": "/tmp/torchinductor_cvm/u4/cu42i6zmxtvs2i7cs6x4ixaexke3lhgdiaye5oxwm7s3u6em6co4.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [4096, 1, 2048], [], []], "Input Dims": [[132, 2048], [1, 2048, 2], [], []], "Ev Idx": 2703 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 1336756, "tid": 1381189, + "ts": 1655274969717.718, "dur": 13.943, + "args": { + "External id": 4055697,"kernel_hash": "ckihofrorhmzazt2wfn2dz2m5wfx3auisu2gvfo2jsepr4zyekmq", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "2"], "kernel_file": "/tmp/torchinductor_cvm/ki/ckihofrorhmzazt2wfn2dz2m5wfx3auisu2gvfo2jsepr4zyekmq.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1, 2048], [2048, 1], [], []], "Input Dims": [[1, 2048, 2], [1, 2048], [], []], "Ev Idx": 2704 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_5", "pid": 1336756, "tid": 1381189, + "ts": 1655274969743.507, "dur": 18.536, + "args": { + "External id": 4055698,"kernel_hash": "cckrpn5uuxyvbancoio3sz2onrjto236n54xx4ycphq5p6r3jlfj", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/ck/cckrpn5uuxyvbancoio3sz2onrjto236n54xx4ycphq5p6r3jlfj.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [8388608, 2048, 1], []], "Input Dims": [[65536, 2048], [65536, 2048], [16, 4096, 2048], []], "Ev Idx": 2705 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274969831.219, "dur": 15.355, + "args": { + "External id": 4055699,"Record function id": 0, "Ev Idx": 2706 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274969834.699, "dur": 10.950, + "args": { + "External id": 4055700,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 2707 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274969838.824, "dur": 5.979, + "args": { + "External id": 4055701,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 2708 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274969840.734, "dur": 3.940, + "args": { + "External id": 4055702,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 2709 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274969850.392, "dur": 7.117, + "args": { + "External id": 4055703,"Record function id": 0, "Ev Idx": 2710 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274969851.890, "dur": 5.202, + "args": { + "External id": 4055704,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 2711 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274969852.643, "dur": 3.971, + "args": { + "External id": 4055705,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 2712 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274969853.453, "dur": 3.063, + "args": { + "External id": 4055706,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 2713 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274969860.957, "dur": 4.390, + "args": { + "External id": 4055707,"Record function id": 0, "Ev Idx": 2714 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274969861.972, "dur": 2.949, + "args": { + "External id": 4055708,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 2715 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274969862.692, "dur": 1.782, + "args": { + "External id": 4055709,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 2716 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274969863.327, "dur": 1.087, + "args": { + "External id": 4055710,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 2717 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274969868.667, "dur": 3.983, + "args": { + "External id": 4055711,"Record function id": 0, "Ev Idx": 2718 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274969869.679, "dur": 2.546, + "args": { + "External id": 4055712,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 2719 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274969870.447, "dur": 1.365, + "args": { + "External id": 4055713,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 2720 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274969871.013, "dur": 0.730, + "args": { + "External id": 4055714,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 2721 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274969875.940, "dur": 3.365, + "args": { + "External id": 4055715,"Record function id": 0, "Ev Idx": 2722 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274969876.941, "dur": 1.952, + "args": { + "External id": 4055716,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 2723 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274969877.405, "dur": 1.035, + "args": { + "External id": 4055717,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 2724 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274969877.689, "dur": 0.684, + "args": { + "External id": 4055718,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 2725 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274969882.602, "dur": 3.975, + "args": { + "External id": 4055719,"Record function id": 0, "Ev Idx": 2726 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274969883.902, "dur": 2.245, + "args": { + "External id": 4055720,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 2727 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274969884.406, "dur": 1.311, + "args": { + "External id": 4055721,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 2728 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274969884.998, "dur": 0.612, + "args": { + "External id": 4055722,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 2729 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274969889.818, "dur": 3.782, + "args": { + "External id": 4055723,"Record function id": 0, "Ev Idx": 2730 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274969890.886, "dur": 2.311, + "args": { + "External id": 4055724,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 2731 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274969891.463, "dur": 1.310, + "args": { + "External id": 4055725,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 2732 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274969891.847, "dur": 0.817, + "args": { + "External id": 4055726,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 2733 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274969896.760, "dur": 3.918, + "args": { + "External id": 4055727,"Record function id": 0, "Ev Idx": 2734 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274969897.833, "dur": 2.416, + "args": { + "External id": 4055728,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 2735 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274969898.389, "dur": 1.431, + "args": { + "External id": 4055729,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 2736 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274969898.646, "dur": 1.106, + "args": { + "External id": 4055730,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 2737 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274969904.060, "dur": 5.478, + "args": { + "External id": 4055731,"Record function id": 0, "Ev Idx": 2738 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655274969905.192, "dur": 3.930, + "args": { + "External id": 4055732,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 2739 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274969905.650, "dur": 3.067, + "args": { + "External id": 4055733,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 2740 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655274969906.100, "dur": 2.532, + "args": { + "External id": 4055734,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 2741 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RegisterPostBackwardFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1655274969913.569, "dur": 36405.513, + "args": { + "External id": 4055735,"Record function id": 0, "Sequence number": 40618393, "Fwd thread id": 1, "Ev Idx": 2742 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1655274969914.986, "dur": 36395.895, + "args": { + "External id": 4055736,"Sequence number": 40618393, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 2743 + } + }, + { + "ph": "f", "id": 187, "pid": 1336756, "tid": 1381189, "ts": 1655274969914.986, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.20)", "pid": 1336756, "tid": 1381189, + "ts": 1655274969943.429, "dur": 35.721, + "args": { + "External id": 4055737,"Record function id": 0, "Ev Idx": 2744 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.20)", "pid": 1336756, "tid": 1381189, + "ts": 1655274970024.786, "dur": 65.322, + "args": { + "External id": 4055738,"Record function id": 0, "Ev Idx": 2745 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.20)", "pid": 1336756, "tid": 1381189, + "ts": 1655274970097.255, "dur": 36205.456, + "args": { + "External id": 4055739,"Record function id": 0, "Ev Idx": 2746 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655274970189.617, "dur": 6.881, + "args": { + "External id": 4055740,"Record function id": 0, "Concrete Inputs": ["[51384320]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2747 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655274970206.627, "dur": 5.077, + "args": { + "External id": 4055741,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[51384320], []], "Ev Idx": 2748 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::chunk_cat", "pid": 1336756, "tid": 1381189, + "ts": 1655274970226.661, "dur": 35263.278, + "args": { + "External id": 4055742,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [2048, 1], [2048, 1], [2048, 1], [2048, 1], [1], [2048, 1], [2048, 1], [5632, 1]], [], [], [6423040, 1]], "Input Dims": [[[2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048], [5632, 2048], [5632, 2048], [2048, 5632]], [], [], [8, 6423040]], "Ev Idx": 2749 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_chunk_cat", "pid": 1336756, "tid": 1381189, + "ts": 1655274970240.394, "dur": 35240.590, + "args": { + "External id": 4055743,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [2048, 1], [2048, 1], [2048, 1], [2048, 1], [1], [2048, 1], [2048, 1], [5632, 1]], [], [], [6423040, 1]], "Input Dims": [[[2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048], [5632, 2048], [5632, 2048], [2048, 5632]], [], [], [8, 6423040]], "Ev Idx": 2750 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655274970324.010, "dur": 13.501, + "args": { + "External id": 4055744,"Record function id": 0, "Concrete Inputs": ["[12602]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2751 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1381189, + "ts": 1655274970344.315, "dur": 35095.090, + "args": { + "External id": 4055745,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[12602], [], [], [], [], [], [], []], "Ev Idx": 2752 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336756, "tid": 1381189, + "ts": 1655274970346.980, "dur": 35091.714, + "args": { + "External id": 4055746,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[12602], [], [], [], [], [], []], "Ev Idx": 2753 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655274970351.484, "dur": 5.538, + "args": { + "External id": 4055747,"Record function id": 0, "Concrete Inputs": ["[12602]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2754 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1381189, + "ts": 1655274970358.936, "dur": 35076.360, + "args": { + "External id": 4055748,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[12602], [12602], []], "Ev Idx": 2755 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 1336756, "tid": 1381189, + "ts": 1655275005579.423, "dur": 9.227, + "args": { + "External id": 4055749,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "", "", "", "False"], "Input type": ["float", "ScalarList", "", "", "", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[51384320], [], [], [], [], []], "Ev Idx": 2756 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655275005582.782, "dur": 5.559, + "args": { + "External id": 4055750,"Record function id": 0, "Concrete Inputs": ["[6423040]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2757 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_reduce_scatter_base_", "pid": 1336756, "tid": 1381189, + "ts": 1655275005623.322, "dur": 346.463, + "args": { + "External id": 4055751,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "-1"], "Input type": ["float", "float", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], [], []], "Input Dims": [[6423040], [51384320], [], [], [], []], "Ev Idx": 2758 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336756, "tid": 1381189, + "ts": 1655275005653.242, "dur": 311.663, + "args": { + "External id": 4055752,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 3, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "3", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 6423040, "Process Group Name": "0", "Input type": ["float", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[51384320], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 2759, "In msg nelems": 51384320 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_reduce_scatter_base", "pid": 1336756, "tid": 1381189, + "ts": 1655275005664.839, "dur": 294.743, + "args": { + "External id": 4055753,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[51384320]], "Ev Idx": 2760 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336756, "tid": 1381189, + "ts": 1655275006022.337, "dur": 3.583, + "args": { + "External id": 4055754,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "3", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 2761, "In msg nelems": 0, "Rank": 3, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275006088.834, "dur": 7.165, + "args": { + "External id": 4055755,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2762 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275006144.274, "dur": 3.238, + "args": { + "External id": 4055756,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "256"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2763 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275006164.316, "dur": 0.837, + "args": { + "External id": 4055757,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "524544"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2764 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275006177.699, "dur": 0.811, + "args": { + "External id": 4055758,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "1048832"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2765 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275006190.237, "dur": 0.916, + "args": { + "External id": 4055759,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "1573120"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2766 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275006202.324, "dur": 2.713, + "args": { + "External id": 4055760,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2767 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275006216.241, "dur": 0.908, + "args": { + "External id": 4055761,"Record function id": 0, "Concrete Inputs": ["", "[704, 2048]", "[2048, 1]", "2097664"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2768 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275006228.968, "dur": 1.732, + "args": { + "External id": 4055762,"Record function id": 0, "Concrete Inputs": ["", "[704, 2048]", "[2048, 1]", "3539456"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2769 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275006241.917, "dur": 0.988, + "args": { + "External id": 4055763,"Record function id": 0, "Concrete Inputs": ["", "[256, 5632]", "[5632, 1]", "4981248"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2770 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: CompiledFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1655275006334.742, "dur": 2646.739, + "args": { + "External id": 4055764,"Record function id": 0, "Ev Idx": 2771 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.19)", "pid": 1336756, "tid": 1381189, + "ts": 1655275006353.866, "dur": 1000.829, + "args": { + "External id": 4055765,"Record function id": 0, "Ev Idx": 2772 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.19)", "pid": 1336756, "tid": 1381189, + "ts": 1655275006368.865, "dur": 335.651, + "args": { + "External id": 4055766,"Record function id": 0, "Ev Idx": 2773 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275006462.554, "dur": 6.315, + "args": { + "External id": 4055767,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[51384320], []], "Ev Idx": 2774 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275006472.444, "dur": 0.931, + "args": { + "External id": 4055768,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 2775 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275006475.176, "dur": 0.752, + "args": { + "External id": 4055769,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 2776 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275006477.720, "dur": 1.068, + "args": { + "External id": 4055770,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 2777 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275006480.376, "dur": 0.728, + "args": { + "External id": 4055771,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 2778 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275006488.245, "dur": 0.822, + "args": { + "External id": 4055772,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 2779 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275006490.859, "dur": 1.862, + "args": { + "External id": 4055773,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 2780 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275006494.329, "dur": 0.798, + "args": { + "External id": 4055774,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 2781 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275006496.576, "dur": 2.472, + "args": { + "External id": 4055775,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 2782 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275006500.587, "dur": 0.963, + "args": { + "External id": 4055776,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 2783 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 1336756, "tid": 1381189, + "ts": 1655275006521.435, "dur": 148.923, + "args": { + "External id": 4055777,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 2784 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 1336756, "tid": 1381189, + "ts": 1655275006537.892, "dur": 128.126, + "args": { + "External id": 4055778,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 2785 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655275006555.120, "dur": 12.611, + "args": { + "External id": 4055779,"Record function id": 0, "Concrete Inputs": ["[2133]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2786 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1381189, + "ts": 1655275006571.045, "dur": 66.987, + "args": { + "External id": 4055780,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], [], []], "Ev Idx": 2787 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336756, "tid": 1381189, + "ts": 1655275006573.690, "dur": 64.062, + "args": { + "External id": 4055781,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], []], "Ev Idx": 2788 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275006578.369, "dur": 5.249, + "args": { + "External id": 4055782,"Record function id": 0, "Concrete Inputs": ["[2133]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2789 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1381189, + "ts": 1655275006585.536, "dur": 51.577, + "args": { + "External id": 4055783,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[2133], [2133], []], "Ev Idx": 2790 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::backward_prefetch for model.layers.18", "pid": 1336756, "tid": 1381189, + "ts": 1655275006780.669, "dur": 566.494, + "args": { + "External id": 4055784,"Record function id": 0, "Ev Idx": 2791 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.18)", "pid": 1336756, "tid": 1381189, + "ts": 1655275006797.324, "dur": 537.392, + "args": { + "External id": 4055785,"Record function id": 0, "Ev Idx": 2792 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655275006849.976, "dur": 4.227, + "args": { + "External id": 4055786,"Record function id": 0, "Concrete Inputs": ["[6423040]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2793 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336756, "tid": 1381189, + "ts": 1655275006869.348, "dur": 28.888, + "args": { + "External id": 4055787,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 2794 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275006874.506, "dur": 1.146, + "args": { + "External id": 4055788,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2795 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275006877.627, "dur": 0.546, + "args": { + "External id": 4055789,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2796 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275006880.112, "dur": 0.491, + "args": { + "External id": 4055790,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2797 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275006882.167, "dur": 2.039, + "args": { + "External id": 4055791,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2798 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275006886.005, "dur": 0.428, + "args": { + "External id": 4055792,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2799 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275006888.040, "dur": 0.355, + "args": { + "External id": 4055793,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2800 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275006890.221, "dur": 0.319, + "args": { + "External id": 4055794,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2801 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275006892.313, "dur": 0.408, + "args": { + "External id": 4055795,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2802 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275006894.335, "dur": 0.398, + "args": { + "External id": 4055796,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2803 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336756, "tid": 1381189, + "ts": 1655275006907.349, "dur": 29.784, + "args": { + "External id": 4055797,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 2804 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 1336756, "tid": 1381189, + "ts": 1655275006968.169, "dur": 145.993, + "args": { + "External id": 4055798,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "6423040", "8", "3", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [], [], [], [], [], []], "Ev Idx": 2805 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655275006977.095, "dur": 39.698, + "args": { + "External id": 4055799,"Record function id": 0, "Concrete Inputs": ["[51384320]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2806 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 1336756, "tid": 1381189, + "ts": 1655275007024.663, "dur": 11.643, + "args": { + "External id": 4055800,"Record function id": 0, "Concrete Inputs": ["", "0", "19269120", "6423040"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 2807 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1381189, + "ts": 1655275007029.203, "dur": 6.698, + "args": { + "External id": 4055801,"Record function id": 0, "Concrete Inputs": ["", "0", "19269120", "25692160", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[51384320], [], [], [], []], "Ev Idx": 2808 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275007033.568, "dur": 0.780, + "args": { + "External id": 4055802,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "[1]", "19269120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 2809 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336756, "tid": 1381189, + "ts": 1655275007044.651, "dur": 27.653, + "args": { + "External id": 4055803,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 2810 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275007047.404, "dur": 2.561, + "args": { + "External id": 4055804,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "19269120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2811 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275007051.671, "dur": 0.519, + "args": { + "External id": 4055805,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "19269376"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2812 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275007054.078, "dur": 0.625, + "args": { + "External id": 4055806,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "19793664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2813 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275007056.167, "dur": 0.393, + "args": { + "External id": 4055807,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "20317952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2814 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275007058.200, "dur": 0.581, + "args": { + "External id": 4055808,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "20842240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2815 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275007060.358, "dur": 0.344, + "args": { + "External id": 4055809,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "21366528"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2816 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275007062.514, "dur": 0.527, + "args": { + "External id": 4055810,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "21366784"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2817 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275007064.697, "dur": 0.409, + "args": { + "External id": 4055811,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "22808576"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2818 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275007066.958, "dur": 2.144, + "args": { + "External id": 4055812,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "24250368"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2819 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336756, "tid": 1381189, + "ts": 1655275007082.721, "dur": 23.757, + "args": { + "External id": 4055813,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 2820 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 1336756, "tid": 1381189, + "ts": 1655275007161.649, "dur": 108.608, + "args": { + "External id": 4055814,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[51384320], [6423040], [], [], []], "Ev Idx": 2821 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336756, "tid": 1381189, + "ts": 1655275007184.838, "dur": 81.685, + "args": { + "External id": 4055815,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 3, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "3", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 51384320, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[6423040], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 2822, "In msg nelems": 6423040 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 1336756, "tid": 1381189, + "ts": 1655275007194.720, "dur": 67.684, + "args": { + "External id": 4055816,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[6423040]], "Ev Idx": 2823 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336756, "tid": 1381189, + "ts": 1655275007283.600, "dur": 1.702, + "args": { + "External id": 4055817,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "3", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 2824, "In msg nelems": 0, "Rank": 3, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1655275007361.942, "dur": 1600.509, + "args": { + "External id": 4055818,"Sequence number": 40618392, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 2825 + } + }, + { + "ph": "f", "id": 188, "pid": 1336756, "tid": 1381189, "ts": 1655275007361.942, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275007491.302, "dur": 105.778, + "args": { + "External id": 4055819,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [5632, 1], [5632, 1]], "Input Dims": [[65536, 2048], [2048, 5632], [65536, 5632]], "Ev Idx": 2826 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_add_mul_rsub_silu_0", "pid": 1336756, "tid": 1381189, + "ts": 1655275007636.252, "dur": 38.866, + "args": { + "External id": 4055820,"kernel_hash": "c2zszzsomz26dv2qwvmiurvgyrl5qxtyn6ocoqkdpzzhfzwqp5q6", "grid": "grid(369098752,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "369098752"], "kernel_file": "/tmp/torchinductor_cvm/2z/c2zszzsomz26dv2qwvmiurvgyrl5qxtyn6ocoqkdpzzhfzwqp5q6.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[5632, 1], [5632, 1], [5632, 1], [23068672, 5632, 1], [23068672, 5632, 1], [23068672, 5632, 1], []], "Input Dims": [[65536, 5632], [65536, 5632], [65536, 5632], [16, 4096, 5632], [16, 4096, 5632], [16, 4096, 5632], []], "Ev Idx": 2827 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 1336756, "tid": 1381189, + "ts": 1655275007694.024, "dur": 49.577, + "args": { + "External id": 4055821,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[0, 1, 2048], [0, 5632, 1], [11534336, 5632, 1]], "Input Dims": [[1, 2048, 65536], [1, 65536, 5632], [1, 2048, 5632]], "Ev Idx": 2828 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275007754.134, "dur": 34.197, + "args": { + "External id": 4055822,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 5632], [2048, 1], [2048, 1]], "Input Dims": [[5632, 65536], [65536, 2048], [5632, 2048]], "Ev Idx": 2829 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275007796.404, "dur": 47.566, + "args": { + "External id": 4055823,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 5632], [5632, 2048], [65536, 2048]], "Ev Idx": 2830 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275007852.140, "dur": 29.391, + "args": { + "External id": 4055824,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 5632], [2048, 1], [2048, 1]], "Input Dims": [[5632, 65536], [65536, 2048], [5632, 2048]], "Ev Idx": 2831 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275007891.451, "dur": 44.729, + "args": { + "External id": 4055825,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 5632], [5632, 2048], [65536, 2048]], "Ev Idx": 2832 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_1", "pid": 1336756, "tid": 1381189, + "ts": 1655275007959.673, "dur": 20.976, + "args": { + "External id": 4055826,"kernel_hash": "cjd6g3jfgntyoifzno6l2urmnhif7alxtw6zz7miov66vywxwv7d", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/jd/cjd6g3jfgntyoifzno6l2urmnhif7alxtw6zz7miov66vywxwv7d.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[65536, 2048], [65536, 2048], []], "Ev Idx": 2833 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 1336756, "tid": 1381189, + "ts": 1655275008041.585, "dur": 29.665, + "args": { + "External id": 4055827,"kernel_hash": "cxhg545cyph4gbk5vymzyh72vho7oogk3ycan2lp4cxntklp5hew", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "65536", "2048", "1", "497", "132", "True", "2048", "True", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/xh/cxhg545cyph4gbk5vymzyh72vho7oogk3ycan2lp4cxntklp5hew.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [1], [2048, 1], [2048, 1], [2048, 1], [2048, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [2048], [65536, 2048], [65536, 2048], [132, 2048], [65536, 2048], [65536], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 2834 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 1336756, "tid": 1381189, + "ts": 1655275008092.893, "dur": 18.905, + "args": { + "External id": 4055828,"kernel_hash": "cu42i6zmxtvs2i7cs6x4ixaexke3lhgdiaye5oxwm7s3u6em6co4", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "66"], "kernel_file": "/tmp/torchinductor_cvm/u4/cu42i6zmxtvs2i7cs6x4ixaexke3lhgdiaye5oxwm7s3u6em6co4.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [4096, 1, 2048], [], []], "Input Dims": [[132, 2048], [1, 2048, 2], [], []], "Ev Idx": 2835 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 1336756, "tid": 1381189, + "ts": 1655275008125.205, "dur": 14.256, + "args": { + "External id": 4055829,"kernel_hash": "ckihofrorhmzazt2wfn2dz2m5wfx3auisu2gvfo2jsepr4zyekmq", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "2"], "kernel_file": "/tmp/torchinductor_cvm/ki/ckihofrorhmzazt2wfn2dz2m5wfx3auisu2gvfo2jsepr4zyekmq.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1, 2048], [2048, 1], [], []], "Input Dims": [[1, 2048, 2], [1, 2048], [], []], "Ev Idx": 2836 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275008151.413, "dur": 34.447, + "args": { + "External id": 4055830,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 2837 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275008189.431, "dur": 34.620, + "args": { + "External id": 4055831,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 2838 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 1336756, "tid": 1381189, + "ts": 1655275008251.962, "dur": 185.194, + "args": { + "External id": 4055832,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.125", "True", "-1", "-1", "0.", "", "False", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar", "long int"], "Input Strides": [[8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [131072, 4096, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 32, 4096], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 2839 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655275008329.150, "dur": 6.289, + "args": { + "External id": 4055833,"Record function id": 0, "Concrete Inputs": ["[16, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2840 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655275008337.552, "dur": 2.218, + "args": { + "External id": 4055834,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2841 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336756, "tid": 1381189, + "ts": 1655275008471.011, "dur": 26.891, + "args": { + "External id": 4055835,"kernel_hash": "cb6oumcqb462ndf2ivcd2sc6qg6mfjahptjw4ih7cesqhfpziv3b", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/b6/cb6oumcqb462ndf2ivcd2sc6qg6mfjahptjw4ih7cesqhfpziv3b.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 2842 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336756, "tid": 1381189, + "ts": 1655275008509.520, "dur": 14.676, + "args": { + "External id": 4055836,"kernel_hash": "cb6oumcqb462ndf2ivcd2sc6qg6mfjahptjw4ih7cesqhfpziv3b", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/b6/cb6oumcqb462ndf2ivcd2sc6qg6mfjahptjw4ih7cesqhfpziv3b.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 2843 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275008534.292, "dur": 38.652, + "args": { + "External id": 4055837,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 2844 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275008581.773, "dur": 35.315, + "args": { + "External id": 4055838,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 2845 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275008624.709, "dur": 21.705, + "args": { + "External id": 4055839,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 2846 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275008652.252, "dur": 30.090, + "args": { + "External id": 4055840,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 2847 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275008688.865, "dur": 21.463, + "args": { + "External id": 4055841,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 2848 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275008719.287, "dur": 41.360, + "args": { + "External id": 4055842,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 2849 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_4", "pid": 1336756, "tid": 1381189, + "ts": 1655275008782.861, "dur": 24.334, + "args": { + "External id": 4055843,"kernel_hash": "c7pqhdjojzeazwsh5g3ibnyk4m2nfh3q73e3zc7hljz4yvhe7c4h", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/7p/c7pqhdjojzeazwsh5g3ibnyk4m2nfh3q73e3zc7hljz4yvhe7c4h.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1], []], "Input Dims": [[65536, 2048], [65536, 2048], [65536, 2048], []], "Ev Idx": 2850 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_2", "pid": 1336756, "tid": 1381189, + "ts": 1655275008823.359, "dur": 21.518, + "args": { + "External id": 4055844,"kernel_hash": "cvgvwkysjpcw75q5t3guce5bep2so25f7i5zxc6ipt5f56shof73", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "65536", "2048", "1", "497", "132", "True", "2048", "False", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/vg/cvgvwkysjpcw75q5t3guce5bep2so25f7i5zxc6ipt5f56shof73.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [1], [2048, 1], [2048, 1], [2048, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [2048], [65536, 2048], [65536, 2048], [132, 2048], [65536], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 2851 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 1336756, "tid": 1381189, + "ts": 1655275008859.244, "dur": 18.539, + "args": { + "External id": 4055845,"kernel_hash": "cu42i6zmxtvs2i7cs6x4ixaexke3lhgdiaye5oxwm7s3u6em6co4", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "66"], "kernel_file": "/tmp/torchinductor_cvm/u4/cu42i6zmxtvs2i7cs6x4ixaexke3lhgdiaye5oxwm7s3u6em6co4.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [4096, 1, 2048], [], []], "Input Dims": [[132, 2048], [1, 2048, 2], [], []], "Ev Idx": 2852 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 1336756, "tid": 1381189, + "ts": 1655275008891.581, "dur": 12.832, + "args": { + "External id": 4055846,"kernel_hash": "ckihofrorhmzazt2wfn2dz2m5wfx3auisu2gvfo2jsepr4zyekmq", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "2"], "kernel_file": "/tmp/torchinductor_cvm/ki/ckihofrorhmzazt2wfn2dz2m5wfx3auisu2gvfo2jsepr4zyekmq.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1, 2048], [2048, 1], [], []], "Input Dims": [[1, 2048, 2], [1, 2048], [], []], "Ev Idx": 2853 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_5", "pid": 1336756, "tid": 1381189, + "ts": 1655275008916.395, "dur": 17.917, + "args": { + "External id": 4055847,"kernel_hash": "cckrpn5uuxyvbancoio3sz2onrjto236n54xx4ycphq5p6r3jlfj", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/ck/cckrpn5uuxyvbancoio3sz2onrjto236n54xx4ycphq5p6r3jlfj.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [8388608, 2048, 1], []], "Input Dims": [[65536, 2048], [65536, 2048], [16, 4096, 2048], []], "Ev Idx": 2854 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275009038.261, "dur": 19.481, + "args": { + "External id": 4055848,"Record function id": 0, "Ev Idx": 2855 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275009042.352, "dur": 14.226, + "args": { + "External id": 4055849,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 2856 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275009046.893, "dur": 8.205, + "args": { + "External id": 4055850,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 2857 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275009048.856, "dur": 6.036, + "args": { + "External id": 4055851,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 2858 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275009062.086, "dur": 4.865, + "args": { + "External id": 4055852,"Record function id": 0, "Ev Idx": 2859 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275009063.479, "dur": 3.050, + "args": { + "External id": 4055853,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 2860 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275009064.194, "dur": 1.886, + "args": { + "External id": 4055854,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 2861 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275009064.871, "dur": 1.096, + "args": { + "External id": 4055855,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 2862 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275009070.612, "dur": 4.551, + "args": { + "External id": 4055856,"Record function id": 0, "Ev Idx": 2863 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275009072.157, "dur": 2.613, + "args": { + "External id": 4055857,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 2864 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275009072.730, "dur": 1.602, + "args": { + "External id": 4055858,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 2865 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275009073.322, "dur": 0.921, + "args": { + "External id": 4055859,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 2866 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275009078.467, "dur": 4.239, + "args": { + "External id": 4055860,"Record function id": 0, "Ev Idx": 2867 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275009079.820, "dur": 2.478, + "args": { + "External id": 4055861,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 2868 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275009080.484, "dur": 1.401, + "args": { + "External id": 4055862,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 2869 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275009081.109, "dur": 0.689, + "args": { + "External id": 4055863,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 2870 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275009086.251, "dur": 3.494, + "args": { + "External id": 4055864,"Record function id": 0, "Ev Idx": 2871 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275009087.524, "dur": 1.800, + "args": { + "External id": 4055865,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 2872 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275009087.961, "dur": 0.938, + "args": { + "External id": 4055866,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 2873 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275009088.231, "dur": 0.602, + "args": { + "External id": 4055867,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 2874 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275009093.367, "dur": 3.546, + "args": { + "External id": 4055868,"Record function id": 0, "Ev Idx": 2875 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275009094.502, "dur": 2.008, + "args": { + "External id": 4055869,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 2876 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275009094.948, "dur": 1.163, + "args": { + "External id": 4055870,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 2877 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275009095.398, "dur": 0.626, + "args": { + "External id": 4055871,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 2878 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275009100.428, "dur": 3.297, + "args": { + "External id": 4055872,"Record function id": 0, "Ev Idx": 2879 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275009101.505, "dur": 1.812, + "args": { + "External id": 4055873,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 2880 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275009101.938, "dur": 0.960, + "args": { + "External id": 4055874,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 2881 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275009102.211, "dur": 0.583, + "args": { + "External id": 4055875,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 2882 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275009107.234, "dur": 8.573, + "args": { + "External id": 4055876,"Record function id": 0, "Ev Idx": 2883 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275009108.376, "dur": 7.024, + "args": { + "External id": 4055877,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 2884 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275009109.020, "dur": 5.974, + "args": { + "External id": 4055878,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 2885 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275009109.294, "dur": 5.637, + "args": { + "External id": 4055879,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 2886 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275009119.656, "dur": 4.232, + "args": { + "External id": 4055880,"Record function id": 0, "Ev Idx": 2887 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275009120.883, "dur": 2.619, + "args": { + "External id": 4055881,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 2888 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275009121.313, "dur": 1.772, + "args": { + "External id": 4055882,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 2889 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275009122.111, "dur": 0.865, + "args": { + "External id": 4055883,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 2890 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RegisterPostBackwardFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1655275009127.608, "dur": 36355.163, + "args": { + "External id": 4055884,"Record function id": 0, "Sequence number": 40618391, "Fwd thread id": 1, "Ev Idx": 2891 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1655275009128.929, "dur": 36344.983, + "args": { + "External id": 4055885,"Sequence number": 40618391, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 2892 + } + }, + { + "ph": "f", "id": 189, "pid": 1336756, "tid": 1381189, "ts": 1655275009128.929, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.19)", "pid": 1336756, "tid": 1381189, + "ts": 1655275009159.520, "dur": 42.317, + "args": { + "External id": 4055886,"Record function id": 0, "Ev Idx": 2893 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.19)", "pid": 1336756, "tid": 1381189, + "ts": 1655275009209.333, "dur": 60.937, + "args": { + "External id": 4055887,"Record function id": 0, "Ev Idx": 2894 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.19)", "pid": 1336756, "tid": 1381189, + "ts": 1655275009276.133, "dur": 36188.967, + "args": { + "External id": 4055888,"Record function id": 0, "Ev Idx": 2895 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655275009364.464, "dur": 6.563, + "args": { + "External id": 4055889,"Record function id": 0, "Concrete Inputs": ["[51384320]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2896 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275009380.187, "dur": 4.661, + "args": { + "External id": 4055890,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[51384320], []], "Ev Idx": 2897 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::chunk_cat", "pid": 1336756, "tid": 1381189, + "ts": 1655275009399.295, "dur": 35255.837, + "args": { + "External id": 4055891,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [2048, 1], [2048, 1], [2048, 1], [2048, 1], [1], [2048, 1], [2048, 1], [5632, 1]], [], [], [6423040, 1]], "Input Dims": [[[2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048], [5632, 2048], [5632, 2048], [2048, 5632]], [], [], [8, 6423040]], "Ev Idx": 2898 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_chunk_cat", "pid": 1336756, "tid": 1381189, + "ts": 1655275009413.198, "dur": 35232.771, + "args": { + "External id": 4055892,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [2048, 1], [2048, 1], [2048, 1], [2048, 1], [1], [2048, 1], [2048, 1], [5632, 1]], [], [], [6423040, 1]], "Input Dims": [[[2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048], [5632, 2048], [5632, 2048], [2048, 5632]], [], [], [8, 6423040]], "Ev Idx": 2899 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655275009515.299, "dur": 15.066, + "args": { + "External id": 4055893,"Record function id": 0, "Concrete Inputs": ["[12602]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2900 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1381189, + "ts": 1655275009537.134, "dur": 35069.902, + "args": { + "External id": 4055894,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[12602], [], [], [], [], [], [], []], "Ev Idx": 2901 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336756, "tid": 1381189, + "ts": 1655275009539.911, "dur": 35066.501, + "args": { + "External id": 4055895,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[12602], [], [], [], [], [], []], "Ev Idx": 2902 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275009544.015, "dur": 5.452, + "args": { + "External id": 4055896,"Record function id": 0, "Concrete Inputs": ["[12602]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2903 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1381189, + "ts": 1655275009551.249, "dur": 35051.334, + "args": { + "External id": 4055897,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[12602], [12602], []], "Ev Idx": 2904 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 1336756, "tid": 1381189, + "ts": 1655275044744.789, "dur": 9.324, + "args": { + "External id": 4055898,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "", "", "", "False"], "Input type": ["float", "ScalarList", "", "", "", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[51384320], [], [], [], [], []], "Ev Idx": 2905 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655275044748.285, "dur": 5.453, + "args": { + "External id": 4055899,"Record function id": 0, "Concrete Inputs": ["[6423040]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2906 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_reduce_scatter_base_", "pid": 1336756, "tid": 1381189, + "ts": 1655275044785.079, "dur": 363.072, + "args": { + "External id": 4055900,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "-1"], "Input type": ["float", "float", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], [], []], "Input Dims": [[6423040], [51384320], [], [], [], []], "Ev Idx": 2907 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336756, "tid": 1381189, + "ts": 1655275044812.667, "dur": 330.095, + "args": { + "External id": 4055901,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 3, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "3", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 6423040, "Process Group Name": "0", "Input type": ["float", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[51384320], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 2908, "In msg nelems": 51384320 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_reduce_scatter_base", "pid": 1336756, "tid": 1381189, + "ts": 1655275044823.966, "dur": 313.200, + "args": { + "External id": 4055902,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[51384320]], "Ev Idx": 2909 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336756, "tid": 1381189, + "ts": 1655275045169.458, "dur": 2.327, + "args": { + "External id": 4055903,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "3", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 2910, "In msg nelems": 0, "Rank": 3, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275045233.565, "dur": 6.722, + "args": { + "External id": 4055904,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2911 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275045288.163, "dur": 1.118, + "args": { + "External id": 4055905,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "256"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2912 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275045305.514, "dur": 1.245, + "args": { + "External id": 4055906,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "524544"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2913 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275045319.521, "dur": 0.932, + "args": { + "External id": 4055907,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "1048832"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2914 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275045331.945, "dur": 0.924, + "args": { + "External id": 4055908,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "1573120"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2915 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275045346.164, "dur": 1.087, + "args": { + "External id": 4055909,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2916 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275045359.345, "dur": 0.926, + "args": { + "External id": 4055910,"Record function id": 0, "Concrete Inputs": ["", "[704, 2048]", "[2048, 1]", "2097664"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2917 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275045372.036, "dur": 1.911, + "args": { + "External id": 4055911,"Record function id": 0, "Concrete Inputs": ["", "[704, 2048]", "[2048, 1]", "3539456"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2918 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275045385.089, "dur": 0.736, + "args": { + "External id": 4055912,"Record function id": 0, "Concrete Inputs": ["", "[256, 5632]", "[5632, 1]", "4981248"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2919 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: CompiledFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1655275045499.917, "dur": 2713.533, + "args": { + "External id": 4055913,"Record function id": 0, "Ev Idx": 2920 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.18)", "pid": 1336756, "tid": 1381189, + "ts": 1655275045519.499, "dur": 1036.628, + "args": { + "External id": 4055914,"Record function id": 0, "Ev Idx": 2921 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.18)", "pid": 1336756, "tid": 1381189, + "ts": 1655275045536.388, "dur": 317.800, + "args": { + "External id": 4055915,"Record function id": 0, "Ev Idx": 2922 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275045615.471, "dur": 4.454, + "args": { + "External id": 4055916,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[51384320], []], "Ev Idx": 2923 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275045623.105, "dur": 1.305, + "args": { + "External id": 4055917,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 2924 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275045626.327, "dur": 0.969, + "args": { + "External id": 4055918,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 2925 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275045629.128, "dur": 1.145, + "args": { + "External id": 4055919,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 2926 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275045632.062, "dur": 0.874, + "args": { + "External id": 4055920,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 2927 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275045634.580, "dur": 0.936, + "args": { + "External id": 4055921,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 2928 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275045637.074, "dur": 1.785, + "args": { + "External id": 4055922,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 2929 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275045640.299, "dur": 2.680, + "args": { + "External id": 4055923,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 2930 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275045644.614, "dur": 0.989, + "args": { + "External id": 4055924,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 2931 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275045647.175, "dur": 0.811, + "args": { + "External id": 4055925,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 2932 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 1336756, "tid": 1381189, + "ts": 1655275045666.612, "dur": 155.890, + "args": { + "External id": 4055926,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 2933 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 1336756, "tid": 1381189, + "ts": 1655275045682.769, "dur": 135.595, + "args": { + "External id": 4055927,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 2934 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655275045707.794, "dur": 12.274, + "args": { + "External id": 4055928,"Record function id": 0, "Concrete Inputs": ["[2133]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2935 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1381189, + "ts": 1655275045723.412, "dur": 66.525, + "args": { + "External id": 4055929,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], [], []], "Ev Idx": 2936 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336756, "tid": 1381189, + "ts": 1655275045725.961, "dur": 63.672, + "args": { + "External id": 4055930,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], []], "Ev Idx": 2937 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275045729.984, "dur": 5.261, + "args": { + "External id": 4055931,"Record function id": 0, "Concrete Inputs": ["[2133]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2938 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1381189, + "ts": 1655275045737.153, "dur": 51.862, + "args": { + "External id": 4055932,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[2133], [2133], []], "Ev Idx": 2939 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::backward_prefetch for model.layers.17", "pid": 1336756, "tid": 1381189, + "ts": 1655275045927.723, "dur": 620.631, + "args": { + "External id": 4055933,"Record function id": 0, "Ev Idx": 2940 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.17)", "pid": 1336756, "tid": 1381189, + "ts": 1655275045944.088, "dur": 591.345, + "args": { + "External id": 4055934,"Record function id": 0, "Ev Idx": 2941 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655275046035.271, "dur": 7.185, + "args": { + "External id": 4055935,"Record function id": 0, "Concrete Inputs": ["[6423040]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2942 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336756, "tid": 1381189, + "ts": 1655275046058.786, "dur": 37.145, + "args": { + "External id": 4055936,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 2943 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275046064.285, "dur": 1.788, + "args": { + "External id": 4055937,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2944 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275046068.813, "dur": 0.633, + "args": { + "External id": 4055938,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2945 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275046071.405, "dur": 2.686, + "args": { + "External id": 4055939,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2946 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275046075.954, "dur": 0.458, + "args": { + "External id": 4055940,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2947 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275046077.926, "dur": 0.436, + "args": { + "External id": 4055941,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2948 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275046080.097, "dur": 0.415, + "args": { + "External id": 4055942,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2949 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275046086.653, "dur": 0.692, + "args": { + "External id": 4055943,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2950 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275046089.052, "dur": 0.438, + "args": { + "External id": 4055944,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2951 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275046091.049, "dur": 0.554, + "args": { + "External id": 4055945,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2952 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336756, "tid": 1381189, + "ts": 1655275046105.962, "dur": 34.247, + "args": { + "External id": 4055946,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 2953 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 1336756, "tid": 1381189, + "ts": 1655275046176.215, "dur": 103.850, + "args": { + "External id": 4055947,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "6423040", "8", "3", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [], [], [], [], [], []], "Ev Idx": 2954 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655275046186.624, "dur": 3.349, + "args": { + "External id": 4055948,"Record function id": 0, "Concrete Inputs": ["[51384320]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2955 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 1336756, "tid": 1381189, + "ts": 1655275046195.293, "dur": 12.061, + "args": { + "External id": 4055949,"Record function id": 0, "Concrete Inputs": ["", "0", "19269120", "6423040"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 2956 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1381189, + "ts": 1655275046199.646, "dur": 7.279, + "args": { + "External id": 4055950,"Record function id": 0, "Concrete Inputs": ["", "0", "19269120", "25692160", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[51384320], [], [], [], []], "Ev Idx": 2957 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275046203.492, "dur": 2.261, + "args": { + "External id": 4055951,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "[1]", "19269120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 2958 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336756, "tid": 1381189, + "ts": 1655275046214.920, "dur": 25.723, + "args": { + "External id": 4055952,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 2959 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275046217.341, "dur": 0.533, + "args": { + "External id": 4055953,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "19269120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2960 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275046219.569, "dur": 0.426, + "args": { + "External id": 4055954,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "19269376"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2961 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275046221.700, "dur": 0.421, + "args": { + "External id": 4055955,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "19793664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2962 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275046223.864, "dur": 0.370, + "args": { + "External id": 4055956,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "20317952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2963 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275046226.105, "dur": 0.536, + "args": { + "External id": 4055957,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "20842240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2964 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275046228.564, "dur": 0.459, + "args": { + "External id": 4055958,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "21366528"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2965 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275046230.534, "dur": 0.458, + "args": { + "External id": 4055959,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "21366784"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2966 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275046232.721, "dur": 2.366, + "args": { + "External id": 4055960,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "22808576"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2967 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275046236.606, "dur": 0.381, + "args": { + "External id": 4055961,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "24250368"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 2968 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336756, "tid": 1381189, + "ts": 1655275046253.901, "dur": 18.885, + "args": { + "External id": 4055962,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 2969 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 1336756, "tid": 1381189, + "ts": 1655275046329.726, "dur": 132.736, + "args": { + "External id": 4055963,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[51384320], [6423040], [], [], []], "Ev Idx": 2970 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336756, "tid": 1381189, + "ts": 1655275046355.573, "dur": 102.773, + "args": { + "External id": 4055964,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 3, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "3", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 51384320, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[6423040], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 2971, "In msg nelems": 6423040 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 1336756, "tid": 1381189, + "ts": 1655275046365.257, "dur": 87.743, + "args": { + "External id": 4055965,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[6423040]], "Ev Idx": 2972 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336756, "tid": 1381189, + "ts": 1655275046481.544, "dur": 2.209, + "args": { + "External id": 4055966,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "3", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 2973, "In msg nelems": 0, "Rank": 3, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1655275046563.620, "dur": 1632.281, + "args": { + "External id": 4055967,"Sequence number": 40618390, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 2974 + } + }, + { + "ph": "f", "id": 190, "pid": 1336756, "tid": 1381189, "ts": 1655275046563.620, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275046669.631, "dur": 104.274, + "args": { + "External id": 4055968,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [5632, 1], [5632, 1]], "Input Dims": [[65536, 2048], [2048, 5632], [65536, 5632]], "Ev Idx": 2975 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_add_mul_rsub_silu_0", "pid": 1336756, "tid": 1381189, + "ts": 1655275046811.136, "dur": 37.583, + "args": { + "External id": 4055969,"kernel_hash": "c2zszzsomz26dv2qwvmiurvgyrl5qxtyn6ocoqkdpzzhfzwqp5q6", "grid": "grid(369098752,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "369098752"], "kernel_file": "/tmp/torchinductor_cvm/2z/c2zszzsomz26dv2qwvmiurvgyrl5qxtyn6ocoqkdpzzhfzwqp5q6.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[5632, 1], [5632, 1], [5632, 1], [23068672, 5632, 1], [23068672, 5632, 1], [23068672, 5632, 1], []], "Input Dims": [[65536, 5632], [65536, 5632], [65536, 5632], [16, 4096, 5632], [16, 4096, 5632], [16, 4096, 5632], []], "Ev Idx": 2976 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 1336756, "tid": 1381189, + "ts": 1655275046868.939, "dur": 49.755, + "args": { + "External id": 4055970,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[0, 1, 2048], [0, 5632, 1], [11534336, 5632, 1]], "Input Dims": [[1, 2048, 65536], [1, 65536, 5632], [1, 2048, 5632]], "Ev Idx": 2977 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275046928.556, "dur": 33.455, + "args": { + "External id": 4055971,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 5632], [2048, 1], [2048, 1]], "Input Dims": [[5632, 65536], [65536, 2048], [5632, 2048]], "Ev Idx": 2978 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275046969.831, "dur": 90.356, + "args": { + "External id": 4055972,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 5632], [5632, 2048], [65536, 2048]], "Ev Idx": 2979 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275047072.784, "dur": 32.306, + "args": { + "External id": 4055973,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 5632], [2048, 1], [2048, 1]], "Input Dims": [[5632, 65536], [65536, 2048], [5632, 2048]], "Ev Idx": 2980 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275047115.044, "dur": 43.779, + "args": { + "External id": 4055974,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 5632], [5632, 2048], [65536, 2048]], "Ev Idx": 2981 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_1", "pid": 1336756, "tid": 1381189, + "ts": 1655275047184.556, "dur": 22.236, + "args": { + "External id": 4055975,"kernel_hash": "cjd6g3jfgntyoifzno6l2urmnhif7alxtw6zz7miov66vywxwv7d", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/jd/cjd6g3jfgntyoifzno6l2urmnhif7alxtw6zz7miov66vywxwv7d.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[65536, 2048], [65536, 2048], []], "Ev Idx": 2982 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 1336756, "tid": 1381189, + "ts": 1655275047224.049, "dur": 26.480, + "args": { + "External id": 4055976,"kernel_hash": "cxhg545cyph4gbk5vymzyh72vho7oogk3ycan2lp4cxntklp5hew", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "65536", "2048", "1", "497", "132", "True", "2048", "True", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/xh/cxhg545cyph4gbk5vymzyh72vho7oogk3ycan2lp4cxntklp5hew.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [1], [2048, 1], [2048, 1], [2048, 1], [2048, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [2048], [65536, 2048], [65536, 2048], [132, 2048], [65536, 2048], [65536], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 2983 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 1336756, "tid": 1381189, + "ts": 1655275047269.246, "dur": 19.227, + "args": { + "External id": 4055977,"kernel_hash": "cu42i6zmxtvs2i7cs6x4ixaexke3lhgdiaye5oxwm7s3u6em6co4", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "66"], "kernel_file": "/tmp/torchinductor_cvm/u4/cu42i6zmxtvs2i7cs6x4ixaexke3lhgdiaye5oxwm7s3u6em6co4.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [4096, 1, 2048], [], []], "Input Dims": [[132, 2048], [1, 2048, 2], [], []], "Ev Idx": 2984 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 1336756, "tid": 1381189, + "ts": 1655275047300.990, "dur": 14.486, + "args": { + "External id": 4055978,"kernel_hash": "ckihofrorhmzazt2wfn2dz2m5wfx3auisu2gvfo2jsepr4zyekmq", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "2"], "kernel_file": "/tmp/torchinductor_cvm/ki/ckihofrorhmzazt2wfn2dz2m5wfx3auisu2gvfo2jsepr4zyekmq.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1, 2048], [2048, 1], [], []], "Input Dims": [[1, 2048, 2], [1, 2048], [], []], "Ev Idx": 2985 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275047328.258, "dur": 29.037, + "args": { + "External id": 4055979,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 2986 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275047360.645, "dur": 33.412, + "args": { + "External id": 4055980,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 2987 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 1336756, "tid": 1381189, + "ts": 1655275047436.828, "dur": 177.067, + "args": { + "External id": 4055981,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.125", "True", "-1", "-1", "0.", "", "False", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar", "long int"], "Input Strides": [[8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [131072, 4096, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 32, 4096], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 2988 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655275047516.302, "dur": 6.774, + "args": { + "External id": 4055982,"Record function id": 0, "Concrete Inputs": ["[16, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2989 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655275047525.563, "dur": 2.932, + "args": { + "External id": 4055983,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 2990 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336756, "tid": 1381189, + "ts": 1655275047644.144, "dur": 23.862, + "args": { + "External id": 4055984,"kernel_hash": "cb6oumcqb462ndf2ivcd2sc6qg6mfjahptjw4ih7cesqhfpziv3b", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/b6/cb6oumcqb462ndf2ivcd2sc6qg6mfjahptjw4ih7cesqhfpziv3b.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 2991 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336756, "tid": 1381189, + "ts": 1655275047679.524, "dur": 14.248, + "args": { + "External id": 4055985,"kernel_hash": "cb6oumcqb462ndf2ivcd2sc6qg6mfjahptjw4ih7cesqhfpziv3b", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/b6/cb6oumcqb462ndf2ivcd2sc6qg6mfjahptjw4ih7cesqhfpziv3b.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 2992 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275047704.763, "dur": 39.592, + "args": { + "External id": 4055986,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 2993 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275047751.236, "dur": 36.757, + "args": { + "External id": 4055987,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 2994 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275047795.706, "dur": 20.913, + "args": { + "External id": 4055988,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 2995 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275047822.404, "dur": 31.216, + "args": { + "External id": 4055989,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 2996 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275047861.979, "dur": 21.018, + "args": { + "External id": 4055990,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 2997 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275047890.228, "dur": 30.093, + "args": { + "External id": 4055991,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 2998 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_4", "pid": 1336756, "tid": 1381189, + "ts": 1655275047937.361, "dur": 36.646, + "args": { + "External id": 4055992,"kernel_hash": "c7pqhdjojzeazwsh5g3ibnyk4m2nfh3q73e3zc7hljz4yvhe7c4h", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/7p/c7pqhdjojzeazwsh5g3ibnyk4m2nfh3q73e3zc7hljz4yvhe7c4h.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1], []], "Input Dims": [[65536, 2048], [65536, 2048], [65536, 2048], []], "Ev Idx": 2999 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_2", "pid": 1336756, "tid": 1381189, + "ts": 1655275048034.914, "dur": 29.245, + "args": { + "External id": 4055993,"kernel_hash": "cvgvwkysjpcw75q5t3guce5bep2so25f7i5zxc6ipt5f56shof73", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "65536", "2048", "1", "497", "132", "True", "2048", "False", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/vg/cvgvwkysjpcw75q5t3guce5bep2so25f7i5zxc6ipt5f56shof73.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [1], [2048, 1], [2048, 1], [2048, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [2048], [65536, 2048], [65536, 2048], [132, 2048], [65536], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 3000 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 1336756, "tid": 1381189, + "ts": 1655275048080.154, "dur": 17.918, + "args": { + "External id": 4055994,"kernel_hash": "cu42i6zmxtvs2i7cs6x4ixaexke3lhgdiaye5oxwm7s3u6em6co4", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "66"], "kernel_file": "/tmp/torchinductor_cvm/u4/cu42i6zmxtvs2i7cs6x4ixaexke3lhgdiaye5oxwm7s3u6em6co4.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [4096, 1, 2048], [], []], "Input Dims": [[132, 2048], [1, 2048, 2], [], []], "Ev Idx": 3001 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 1336756, "tid": 1381189, + "ts": 1655275048115.145, "dur": 13.888, + "args": { + "External id": 4055995,"kernel_hash": "ckihofrorhmzazt2wfn2dz2m5wfx3auisu2gvfo2jsepr4zyekmq", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "2"], "kernel_file": "/tmp/torchinductor_cvm/ki/ckihofrorhmzazt2wfn2dz2m5wfx3auisu2gvfo2jsepr4zyekmq.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1, 2048], [2048, 1], [], []], "Input Dims": [[1, 2048, 2], [1, 2048], [], []], "Ev Idx": 3002 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_5", "pid": 1336756, "tid": 1381189, + "ts": 1655275048145.242, "dur": 16.007, + "args": { + "External id": 4055996,"kernel_hash": "cckrpn5uuxyvbancoio3sz2onrjto236n54xx4ycphq5p6r3jlfj", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/ck/cckrpn5uuxyvbancoio3sz2onrjto236n54xx4ycphq5p6r3jlfj.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [8388608, 2048, 1], []], "Input Dims": [[65536, 2048], [65536, 2048], [16, 4096, 2048], []], "Ev Idx": 3003 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275048236.099, "dur": 15.112, + "args": { + "External id": 4055997,"Record function id": 0, "Ev Idx": 3004 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275048239.189, "dur": 11.138, + "args": { + "External id": 4055998,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 3005 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275048243.493, "dur": 5.988, + "args": { + "External id": 4055999,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 3006 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275048245.329, "dur": 4.013, + "args": { + "External id": 4056000,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 3007 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275048255.367, "dur": 4.879, + "args": { + "External id": 4056001,"Record function id": 0, "Ev Idx": 3008 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275048256.698, "dur": 3.133, + "args": { + "External id": 4056002,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 3009 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275048257.379, "dur": 1.971, + "args": { + "External id": 4056003,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 3010 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275048258.176, "dur": 1.060, + "args": { + "External id": 4056004,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 3011 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275048263.649, "dur": 4.643, + "args": { + "External id": 4056005,"Record function id": 0, "Ev Idx": 3012 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275048264.922, "dur": 2.976, + "args": { + "External id": 4056006,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 3013 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275048265.585, "dur": 1.872, + "args": { + "External id": 4056007,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 3014 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275048266.096, "dur": 1.259, + "args": { + "External id": 4056008,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 3015 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275048271.421, "dur": 4.051, + "args": { + "External id": 4056009,"Record function id": 0, "Ev Idx": 3016 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275048272.901, "dur": 2.186, + "args": { + "External id": 4056010,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 3017 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275048273.471, "dur": 1.186, + "args": { + "External id": 4056011,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 3018 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275048273.936, "dur": 0.627, + "args": { + "External id": 4056012,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 3019 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275048278.677, "dur": 3.503, + "args": { + "External id": 4056013,"Record function id": 0, "Ev Idx": 3020 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275048279.734, "dur": 2.007, + "args": { + "External id": 4056014,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 3021 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275048280.211, "dur": 1.047, + "args": { + "External id": 4056015,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 3022 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275048280.632, "dur": 0.562, + "args": { + "External id": 4056016,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 3023 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275048285.370, "dur": 4.162, + "args": { + "External id": 4056017,"Record function id": 0, "Ev Idx": 3024 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275048286.388, "dur": 2.736, + "args": { + "External id": 4056018,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 3025 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275048287.267, "dur": 1.374, + "args": { + "External id": 4056019,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 3026 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275048287.807, "dur": 0.707, + "args": { + "External id": 4056020,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 3027 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275048292.771, "dur": 5.835, + "args": { + "External id": 4056021,"Record function id": 0, "Ev Idx": 3028 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275048293.875, "dur": 4.327, + "args": { + "External id": 4056022,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 3029 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275048294.331, "dur": 3.435, + "args": { + "External id": 4056023,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 3030 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275048294.634, "dur": 3.044, + "args": { + "External id": 4056024,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 3031 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275048301.880, "dur": 3.514, + "args": { + "External id": 4056025,"Record function id": 0, "Ev Idx": 3032 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275048303.069, "dur": 1.919, + "args": { + "External id": 4056026,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 3033 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275048303.499, "dur": 1.067, + "args": { + "External id": 4056027,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 3034 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275048303.777, "dur": 0.718, + "args": { + "External id": 4056028,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 3035 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275048308.513, "dur": 3.546, + "args": { + "External id": 4056029,"Record function id": 0, "Ev Idx": 3036 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275048309.745, "dur": 1.929, + "args": { + "External id": 4056030,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 3037 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275048310.206, "dur": 1.039, + "args": { + "External id": 4056031,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 3038 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275048310.626, "dur": 0.525, + "args": { + "External id": 4056032,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 3039 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RegisterPostBackwardFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1655275048318.809, "dur": 36832.268, + "args": { + "External id": 4056033,"Record function id": 0, "Sequence number": 40618389, "Fwd thread id": 1, "Ev Idx": 3040 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1655275048320.191, "dur": 36821.975, + "args": { + "External id": 4056034,"Sequence number": 40618389, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 3041 + } + }, + { + "ph": "f", "id": 191, "pid": 1336756, "tid": 1381189, "ts": 1655275048320.191, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.18)", "pid": 1336756, "tid": 1381189, + "ts": 1655275048348.330, "dur": 41.703, + "args": { + "External id": 4056035,"Record function id": 0, "Ev Idx": 3042 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.18)", "pid": 1336756, "tid": 1381189, + "ts": 1655275048397.597, "dur": 79.315, + "args": { + "External id": 4056036,"Record function id": 0, "Ev Idx": 3043 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.18)", "pid": 1336756, "tid": 1381189, + "ts": 1655275048484.349, "dur": 36649.083, + "args": { + "External id": 4056037,"Record function id": 0, "Ev Idx": 3044 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655275048572.487, "dur": 6.867, + "args": { + "External id": 4056038,"Record function id": 0, "Concrete Inputs": ["[51384320]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3045 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275048589.988, "dur": 5.091, + "args": { + "External id": 4056039,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[51384320], []], "Ev Idx": 3046 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::chunk_cat", "pid": 1336756, "tid": 1381189, + "ts": 1655275048610.445, "dur": 35638.636, + "args": { + "External id": 4056040,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [2048, 1], [2048, 1], [2048, 1], [2048, 1], [1], [2048, 1], [2048, 1], [5632, 1]], [], [], [6423040, 1]], "Input Dims": [[[2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048], [5632, 2048], [5632, 2048], [2048, 5632]], [], [], [8, 6423040]], "Ev Idx": 3047 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_chunk_cat", "pid": 1336756, "tid": 1381189, + "ts": 1655275048653.925, "dur": 35585.574, + "args": { + "External id": 4056041,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [2048, 1], [2048, 1], [2048, 1], [2048, 1], [1], [2048, 1], [2048, 1], [5632, 1]], [], [], [6423040, 1]], "Input Dims": [[[2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048], [5632, 2048], [5632, 2048], [2048, 5632]], [], [], [8, 6423040]], "Ev Idx": 3048 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655275048694.121, "dur": 13.437, + "args": { + "External id": 4056042,"Record function id": 0, "Concrete Inputs": ["[12602]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3049 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1381189, + "ts": 1655275048714.160, "dur": 35485.967, + "args": { + "External id": 4056043,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[12602], [], [], [], [], [], [], []], "Ev Idx": 3050 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336756, "tid": 1381189, + "ts": 1655275048716.864, "dur": 35482.194, + "args": { + "External id": 4056044,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[12602], [], [], [], [], [], []], "Ev Idx": 3051 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275048721.180, "dur": 5.989, + "args": { + "External id": 4056045,"Record function id": 0, "Concrete Inputs": ["[12602]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3052 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1381189, + "ts": 1655275048729.125, "dur": 35466.048, + "args": { + "External id": 4056046,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[12602], [12602], []], "Ev Idx": 3053 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 1336756, "tid": 1381189, + "ts": 1655275084341.015, "dur": 9.180, + "args": { + "External id": 4056047,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "", "", "", "False"], "Input type": ["float", "ScalarList", "", "", "", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[51384320], [], [], [], [], []], "Ev Idx": 3054 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655275084344.580, "dur": 5.251, + "args": { + "External id": 4056048,"Record function id": 0, "Concrete Inputs": ["[6423040]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3055 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_reduce_scatter_base_", "pid": 1336756, "tid": 1381189, + "ts": 1655275084382.991, "dur": 402.251, + "args": { + "External id": 4056049,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "-1"], "Input type": ["float", "float", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], [], []], "Input Dims": [[6423040], [51384320], [], [], [], []], "Ev Idx": 3056 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336756, "tid": 1381189, + "ts": 1655275084410.967, "dur": 368.872, + "args": { + "External id": 4056050,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 3, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "3", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 6423040, "Process Group Name": "0", "Input type": ["float", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[51384320], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 3057, "In msg nelems": 51384320 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_reduce_scatter_base", "pid": 1336756, "tid": 1381189, + "ts": 1655275084435.902, "dur": 338.359, + "args": { + "External id": 4056051,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[51384320]], "Ev Idx": 3058 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336756, "tid": 1381189, + "ts": 1655275084807.079, "dur": 2.318, + "args": { + "External id": 4056052,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "3", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 3059, "In msg nelems": 0, "Rank": 3, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275084870.546, "dur": 8.524, + "args": { + "External id": 4056053,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3060 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275084926.261, "dur": 1.176, + "args": { + "External id": 4056054,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "256"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3061 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275084945.103, "dur": 0.985, + "args": { + "External id": 4056055,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "524544"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3062 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275084959.416, "dur": 1.092, + "args": { + "External id": 4056056,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "1048832"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3063 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275084972.089, "dur": 2.644, + "args": { + "External id": 4056057,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "1573120"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3064 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275085022.659, "dur": 1.742, + "args": { + "External id": 4056058,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3065 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275085039.021, "dur": 1.040, + "args": { + "External id": 4056059,"Record function id": 0, "Concrete Inputs": ["", "[704, 2048]", "[2048, 1]", "2097664"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3066 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275085053.963, "dur": 1.816, + "args": { + "External id": 4056060,"Record function id": 0, "Concrete Inputs": ["", "[704, 2048]", "[2048, 1]", "3539456"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3067 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275085067.207, "dur": 2.896, + "args": { + "External id": 4056061,"Record function id": 0, "Concrete Inputs": ["", "[256, 5632]", "[5632, 1]", "4981248"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3068 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: CompiledFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1655275085167.774, "dur": 2727.827, + "args": { + "External id": 4056062,"Record function id": 0, "Ev Idx": 3069 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.17)", "pid": 1336756, "tid": 1381189, + "ts": 1655275085186.386, "dur": 1063.223, + "args": { + "External id": 4056063,"Record function id": 0, "Ev Idx": 3070 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.17)", "pid": 1336756, "tid": 1381189, + "ts": 1655275085201.228, "dur": 363.926, + "args": { + "External id": 4056064,"Record function id": 0, "Ev Idx": 3071 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275085309.267, "dur": 4.789, + "args": { + "External id": 4056065,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[51384320], []], "Ev Idx": 3072 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275085317.736, "dur": 1.052, + "args": { + "External id": 4056066,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 3073 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275085320.588, "dur": 1.286, + "args": { + "External id": 4056067,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 3074 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275085323.322, "dur": 0.795, + "args": { + "External id": 4056068,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 3075 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275085325.891, "dur": 0.719, + "args": { + "External id": 4056069,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 3076 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275085329.972, "dur": 0.687, + "args": { + "External id": 4056070,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 3077 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275085332.398, "dur": 3.574, + "args": { + "External id": 4056071,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 3078 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275085337.331, "dur": 0.729, + "args": { + "External id": 4056072,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 3079 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275085339.504, "dur": 0.970, + "args": { + "External id": 4056073,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 3080 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275085341.894, "dur": 0.790, + "args": { + "External id": 4056074,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 3081 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 1336756, "tid": 1381189, + "ts": 1655275085361.693, "dur": 167.840, + "args": { + "External id": 4056075,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 3082 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 1336756, "tid": 1381189, + "ts": 1655275085377.719, "dur": 146.605, + "args": { + "External id": 4056076,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 3083 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655275085393.171, "dur": 12.843, + "args": { + "External id": 4056077,"Record function id": 0, "Concrete Inputs": ["[2133]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3084 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1381189, + "ts": 1655275085409.331, "dur": 85.647, + "args": { + "External id": 4056078,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], [], []], "Ev Idx": 3085 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336756, "tid": 1381189, + "ts": 1655275085411.911, "dur": 82.708, + "args": { + "External id": 4056079,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], []], "Ev Idx": 3086 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275085432.483, "dur": 6.426, + "args": { + "External id": 4056080,"Record function id": 0, "Concrete Inputs": ["[2133]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3087 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1381189, + "ts": 1655275085441.106, "dur": 52.957, + "args": { + "External id": 4056081,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[2133], [2133], []], "Ev Idx": 3088 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::backward_prefetch for model.layers.16", "pid": 1336756, "tid": 1381189, + "ts": 1655275085643.591, "dur": 597.974, + "args": { + "External id": 4056082,"Record function id": 0, "Ev Idx": 3089 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.16)", "pid": 1336756, "tid": 1381189, + "ts": 1655275085660.796, "dur": 567.937, + "args": { + "External id": 4056083,"Record function id": 0, "Ev Idx": 3090 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655275085716.438, "dur": 5.368, + "args": { + "External id": 4056084,"Record function id": 0, "Concrete Inputs": ["[6423040]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3091 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336756, "tid": 1381189, + "ts": 1655275085737.622, "dur": 30.856, + "args": { + "External id": 4056085,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 3092 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275085742.822, "dur": 1.484, + "args": { + "External id": 4056086,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3093 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275085746.603, "dur": 2.430, + "args": { + "External id": 4056087,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3094 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275085750.744, "dur": 0.554, + "args": { + "External id": 4056088,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3095 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275085752.899, "dur": 0.567, + "args": { + "External id": 4056089,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3096 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275085755.206, "dur": 0.388, + "args": { + "External id": 4056090,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3097 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275085757.220, "dur": 0.435, + "args": { + "External id": 4056091,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3098 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275085759.342, "dur": 0.400, + "args": { + "External id": 4056092,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3099 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275085761.937, "dur": 0.491, + "args": { + "External id": 4056093,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3100 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275085764.232, "dur": 0.353, + "args": { + "External id": 4056094,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3101 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336756, "tid": 1381189, + "ts": 1655275085778.761, "dur": 29.370, + "args": { + "External id": 4056095,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 3102 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 1336756, "tid": 1381189, + "ts": 1655275085840.473, "dur": 109.605, + "args": { + "External id": 4056096,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "6423040", "8", "3", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [], [], [], [], [], []], "Ev Idx": 3103 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655275085850.954, "dur": 4.890, + "args": { + "External id": 4056097,"Record function id": 0, "Concrete Inputs": ["[51384320]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3104 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 1336756, "tid": 1381189, + "ts": 1655275085860.889, "dur": 10.214, + "args": { + "External id": 4056098,"Record function id": 0, "Concrete Inputs": ["", "0", "19269120", "6423040"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 3105 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1381189, + "ts": 1655275085865.113, "dur": 5.580, + "args": { + "External id": 4056099,"Record function id": 0, "Concrete Inputs": ["", "0", "19269120", "25692160", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[51384320], [], [], [], []], "Ev Idx": 3106 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275085869.003, "dur": 0.418, + "args": { + "External id": 4056100,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "[1]", "19269120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 3107 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336756, "tid": 1381189, + "ts": 1655275085878.333, "dur": 25.980, + "args": { + "External id": 4056101,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 3108 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275085880.593, "dur": 0.446, + "args": { + "External id": 4056102,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "19269120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3109 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275085883.144, "dur": 0.597, + "args": { + "External id": 4056103,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "19269376"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3110 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275085885.419, "dur": 0.480, + "args": { + "External id": 4056104,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "19793664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3111 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275085887.609, "dur": 0.435, + "args": { + "External id": 4056105,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "20317952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3112 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275085889.971, "dur": 0.370, + "args": { + "External id": 4056106,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "20842240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3113 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275085892.177, "dur": 0.362, + "args": { + "External id": 4056107,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "21366528"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3114 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275085894.276, "dur": 2.283, + "args": { + "External id": 4056108,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "21366784"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3115 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275085898.397, "dur": 0.369, + "args": { + "External id": 4056109,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "22808576"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3116 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275085900.429, "dur": 0.485, + "args": { + "External id": 4056110,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "24250368"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3117 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336756, "tid": 1381189, + "ts": 1655275085921.285, "dur": 21.835, + "args": { + "External id": 4056111,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 3118 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 1336756, "tid": 1381189, + "ts": 1655275086036.327, "dur": 118.592, + "args": { + "External id": 4056112,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[51384320], [6423040], [], [], []], "Ev Idx": 3119 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336756, "tid": 1381189, + "ts": 1655275086063.208, "dur": 87.968, + "args": { + "External id": 4056113,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 3, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "3", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 51384320, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[6423040], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 3120, "In msg nelems": 6423040 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 1336756, "tid": 1381189, + "ts": 1655275086073.992, "dur": 73.108, + "args": { + "External id": 4056114,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[6423040]], "Ev Idx": 3121 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336756, "tid": 1381189, + "ts": 1655275086171.926, "dur": 1.708, + "args": { + "External id": 4056115,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "3", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 3122, "In msg nelems": 0, "Rank": 3, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1655275086257.639, "dur": 1619.848, + "args": { + "External id": 4056116,"Sequence number": 40618388, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 3123 + } + }, + { + "ph": "f", "id": 192, "pid": 1336756, "tid": 1381189, "ts": 1655275086257.639, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275086364.774, "dur": 122.579, + "args": { + "External id": 4056117,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [5632, 1], [5632, 1]], "Input Dims": [[65536, 2048], [2048, 5632], [65536, 5632]], "Ev Idx": 3124 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_add_mul_rsub_silu_0", "pid": 1336756, "tid": 1381189, + "ts": 1655275086527.613, "dur": 38.420, + "args": { + "External id": 4056118,"kernel_hash": "c2zszzsomz26dv2qwvmiurvgyrl5qxtyn6ocoqkdpzzhfzwqp5q6", "grid": "grid(369098752,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "369098752"], "kernel_file": "/tmp/torchinductor_cvm/2z/c2zszzsomz26dv2qwvmiurvgyrl5qxtyn6ocoqkdpzzhfzwqp5q6.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[5632, 1], [5632, 1], [5632, 1], [23068672, 5632, 1], [23068672, 5632, 1], [23068672, 5632, 1], []], "Input Dims": [[65536, 5632], [65536, 5632], [65536, 5632], [16, 4096, 5632], [16, 4096, 5632], [16, 4096, 5632], []], "Ev Idx": 3125 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 1336756, "tid": 1381189, + "ts": 1655275086586.310, "dur": 52.460, + "args": { + "External id": 4056119,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[0, 1, 2048], [0, 5632, 1], [11534336, 5632, 1]], "Input Dims": [[1, 2048, 65536], [1, 65536, 5632], [1, 2048, 5632]], "Ev Idx": 3126 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275086647.966, "dur": 34.297, + "args": { + "External id": 4056120,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 5632], [2048, 1], [2048, 1]], "Input Dims": [[5632, 65536], [65536, 2048], [5632, 2048]], "Ev Idx": 3127 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275086689.875, "dur": 46.524, + "args": { + "External id": 4056121,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 5632], [5632, 2048], [65536, 2048]], "Ev Idx": 3128 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275086746.234, "dur": 28.102, + "args": { + "External id": 4056122,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 5632], [2048, 1], [2048, 1]], "Input Dims": [[5632, 65536], [65536, 2048], [5632, 2048]], "Ev Idx": 3129 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275086781.808, "dur": 43.613, + "args": { + "External id": 4056123,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 5632], [5632, 2048], [65536, 2048]], "Ev Idx": 3130 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_1", "pid": 1336756, "tid": 1381189, + "ts": 1655275086847.426, "dur": 20.316, + "args": { + "External id": 4056124,"kernel_hash": "cjd6g3jfgntyoifzno6l2urmnhif7alxtw6zz7miov66vywxwv7d", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/jd/cjd6g3jfgntyoifzno6l2urmnhif7alxtw6zz7miov66vywxwv7d.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[65536, 2048], [65536, 2048], []], "Ev Idx": 3131 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 1336756, "tid": 1381189, + "ts": 1655275086885.618, "dur": 26.844, + "args": { + "External id": 4056125,"kernel_hash": "cxhg545cyph4gbk5vymzyh72vho7oogk3ycan2lp4cxntklp5hew", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "65536", "2048", "1", "497", "132", "True", "2048", "True", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/xh/cxhg545cyph4gbk5vymzyh72vho7oogk3ycan2lp4cxntklp5hew.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [1], [2048, 1], [2048, 1], [2048, 1], [2048, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [2048], [65536, 2048], [65536, 2048], [132, 2048], [65536, 2048], [65536], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 3132 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 1336756, "tid": 1381189, + "ts": 1655275086930.511, "dur": 19.370, + "args": { + "External id": 4056126,"kernel_hash": "cu42i6zmxtvs2i7cs6x4ixaexke3lhgdiaye5oxwm7s3u6em6co4", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "66"], "kernel_file": "/tmp/torchinductor_cvm/u4/cu42i6zmxtvs2i7cs6x4ixaexke3lhgdiaye5oxwm7s3u6em6co4.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [4096, 1, 2048], [], []], "Input Dims": [[132, 2048], [1, 2048, 2], [], []], "Ev Idx": 3133 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 1336756, "tid": 1381189, + "ts": 1655275086962.089, "dur": 14.445, + "args": { + "External id": 4056127,"kernel_hash": "ckihofrorhmzazt2wfn2dz2m5wfx3auisu2gvfo2jsepr4zyekmq", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "2"], "kernel_file": "/tmp/torchinductor_cvm/ki/ckihofrorhmzazt2wfn2dz2m5wfx3auisu2gvfo2jsepr4zyekmq.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1, 2048], [2048, 1], [], []], "Input Dims": [[1, 2048, 2], [1, 2048], [], []], "Ev Idx": 3134 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275087027.951, "dur": 35.050, + "args": { + "External id": 4056128,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 3135 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275087067.282, "dur": 33.994, + "args": { + "External id": 4056129,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 3136 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 1336756, "tid": 1381189, + "ts": 1655275087128.693, "dur": 173.795, + "args": { + "External id": 4056130,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.125", "True", "-1", "-1", "0.", "", "False", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar", "long int"], "Input Strides": [[8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [131072, 4096, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 32, 4096], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 3137 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655275087208.243, "dur": 5.291, + "args": { + "External id": 4056131,"Record function id": 0, "Concrete Inputs": ["[16, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3138 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655275087215.724, "dur": 3.712, + "args": { + "External id": 4056132,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3139 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336756, "tid": 1381189, + "ts": 1655275087333.896, "dur": 24.451, + "args": { + "External id": 4056133,"kernel_hash": "cb6oumcqb462ndf2ivcd2sc6qg6mfjahptjw4ih7cesqhfpziv3b", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/b6/cb6oumcqb462ndf2ivcd2sc6qg6mfjahptjw4ih7cesqhfpziv3b.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 3140 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336756, "tid": 1381189, + "ts": 1655275087385.975, "dur": 15.417, + "args": { + "External id": 4056134,"kernel_hash": "cb6oumcqb462ndf2ivcd2sc6qg6mfjahptjw4ih7cesqhfpziv3b", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/b6/cb6oumcqb462ndf2ivcd2sc6qg6mfjahptjw4ih7cesqhfpziv3b.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 3141 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275087410.905, "dur": 55.628, + "args": { + "External id": 4056135,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 3142 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275087476.208, "dur": 35.798, + "args": { + "External id": 4056136,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 3143 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275087519.683, "dur": 21.249, + "args": { + "External id": 4056137,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 3144 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275087548.363, "dur": 43.806, + "args": { + "External id": 4056138,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 3145 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275087604.743, "dur": 24.388, + "args": { + "External id": 4056139,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 3146 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275087637.139, "dur": 31.809, + "args": { + "External id": 4056140,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 3147 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_4", "pid": 1336756, "tid": 1381189, + "ts": 1655275087692.407, "dur": 24.543, + "args": { + "External id": 4056141,"kernel_hash": "c7pqhdjojzeazwsh5g3ibnyk4m2nfh3q73e3zc7hljz4yvhe7c4h", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/7p/c7pqhdjojzeazwsh5g3ibnyk4m2nfh3q73e3zc7hljz4yvhe7c4h.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1], []], "Input Dims": [[65536, 2048], [65536, 2048], [65536, 2048], []], "Ev Idx": 3148 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_2", "pid": 1336756, "tid": 1381189, + "ts": 1655275087734.425, "dur": 25.042, + "args": { + "External id": 4056142,"kernel_hash": "cvgvwkysjpcw75q5t3guce5bep2so25f7i5zxc6ipt5f56shof73", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "65536", "2048", "1", "497", "132", "True", "2048", "False", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/vg/cvgvwkysjpcw75q5t3guce5bep2so25f7i5zxc6ipt5f56shof73.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [1], [2048, 1], [2048, 1], [2048, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [2048], [65536, 2048], [65536, 2048], [132, 2048], [65536], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 3149 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 1336756, "tid": 1381189, + "ts": 1655275087773.747, "dur": 17.136, + "args": { + "External id": 4056143,"kernel_hash": "cu42i6zmxtvs2i7cs6x4ixaexke3lhgdiaye5oxwm7s3u6em6co4", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "66"], "kernel_file": "/tmp/torchinductor_cvm/u4/cu42i6zmxtvs2i7cs6x4ixaexke3lhgdiaye5oxwm7s3u6em6co4.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [4096, 1, 2048], [], []], "Input Dims": [[132, 2048], [1, 2048, 2], [], []], "Ev Idx": 3150 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 1336756, "tid": 1381189, + "ts": 1655275087805.550, "dur": 14.792, + "args": { + "External id": 4056144,"kernel_hash": "ckihofrorhmzazt2wfn2dz2m5wfx3auisu2gvfo2jsepr4zyekmq", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "2"], "kernel_file": "/tmp/torchinductor_cvm/ki/ckihofrorhmzazt2wfn2dz2m5wfx3auisu2gvfo2jsepr4zyekmq.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1, 2048], [2048, 1], [], []], "Input Dims": [[1, 2048, 2], [1, 2048], [], []], "Ev Idx": 3151 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_5", "pid": 1336756, "tid": 1381189, + "ts": 1655275087834.723, "dur": 15.308, + "args": { + "External id": 4056145,"kernel_hash": "cckrpn5uuxyvbancoio3sz2onrjto236n54xx4ycphq5p6r3jlfj", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/ck/cckrpn5uuxyvbancoio3sz2onrjto236n54xx4ycphq5p6r3jlfj.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [8388608, 2048, 1], []], "Input Dims": [[65536, 2048], [65536, 2048], [16, 4096, 2048], []], "Ev Idx": 3152 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275087918.214, "dur": 16.084, + "args": { + "External id": 4056146,"Record function id": 0, "Ev Idx": 3153 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275087921.924, "dur": 11.376, + "args": { + "External id": 4056147,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 3154 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275087926.350, "dur": 6.103, + "args": { + "External id": 4056148,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 3155 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275087928.258, "dur": 4.070, + "args": { + "External id": 4056149,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 3156 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275087938.279, "dur": 5.769, + "args": { + "External id": 4056150,"Record function id": 0, "Ev Idx": 3157 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275087939.803, "dur": 3.781, + "args": { + "External id": 4056151,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 3158 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275087940.678, "dur": 2.481, + "args": { + "External id": 4056152,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 3159 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275087941.587, "dur": 1.459, + "args": { + "External id": 4056153,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 3160 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275087947.364, "dur": 4.293, + "args": { + "External id": 4056154,"Record function id": 0, "Ev Idx": 3161 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275087948.817, "dur": 2.416, + "args": { + "External id": 4056155,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 3162 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275087949.319, "dur": 1.513, + "args": { + "External id": 4056156,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 3163 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275087949.623, "dur": 1.106, + "args": { + "External id": 4056157,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 3164 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275087954.877, "dur": 5.769, + "args": { + "External id": 4056158,"Record function id": 0, "Ev Idx": 3165 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275087956.102, "dur": 4.112, + "args": { + "External id": 4056159,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 3166 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275087956.746, "dur": 3.087, + "args": { + "External id": 4056160,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 3167 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275087957.323, "dur": 2.424, + "args": { + "External id": 4056161,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 3168 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275087966.579, "dur": 3.694, + "args": { + "External id": 4056162,"Record function id": 0, "Ev Idx": 3169 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275087967.696, "dur": 2.173, + "args": { + "External id": 4056163,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 3170 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275087968.233, "dur": 1.222, + "args": { + "External id": 4056164,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 3171 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275087968.693, "dur": 0.671, + "args": { + "External id": 4056165,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 3172 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275087973.562, "dur": 3.807, + "args": { + "External id": 4056166,"Record function id": 0, "Ev Idx": 3173 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275087974.830, "dur": 2.150, + "args": { + "External id": 4056167,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 3174 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275087975.462, "dur": 1.130, + "args": { + "External id": 4056168,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 3175 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275087975.937, "dur": 0.540, + "args": { + "External id": 4056169,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 3176 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275087980.550, "dur": 37.717, + "args": { + "External id": 4056170,"Record function id": 0, "Ev Idx": 3177 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275087981.879, "dur": 2.023, + "args": { + "External id": 4056171,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 3178 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275087982.335, "dur": 1.180, + "args": { + "External id": 4056172,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 3179 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275087982.772, "dur": 0.650, + "args": { + "External id": 4056173,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 3180 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275088028.459, "dur": 6.527, + "args": { + "External id": 4056174,"Record function id": 0, "Ev Idx": 3181 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275088030.339, "dur": 4.031, + "args": { + "External id": 4056175,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 3182 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275088031.369, "dur": 2.191, + "args": { + "External id": 4056176,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 3183 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275088032.188, "dur": 1.281, + "args": { + "External id": 4056177,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 3184 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275088038.108, "dur": 3.869, + "args": { + "External id": 4056178,"Record function id": 0, "Ev Idx": 3185 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275088039.161, "dur": 2.410, + "args": { + "External id": 4056179,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 3186 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275088039.627, "dur": 1.552, + "args": { + "External id": 4056180,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 3187 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275088040.171, "dur": 0.903, + "args": { + "External id": 4056181,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 3188 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RegisterPostBackwardFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1655275088045.871, "dur": 37421.727, + "args": { + "External id": 4056182,"Record function id": 0, "Sequence number": 40618387, "Fwd thread id": 1, "Ev Idx": 3189 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1655275088047.585, "dur": 37411.313, + "args": { + "External id": 4056183,"Sequence number": 40618387, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 3190 + } + }, + { + "ph": "f", "id": 193, "pid": 1336756, "tid": 1381189, "ts": 1655275088047.585, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.17)", "pid": 1336756, "tid": 1381189, + "ts": 1655275088080.327, "dur": 36.518, + "args": { + "External id": 4056184,"Record function id": 0, "Ev Idx": 3191 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.17)", "pid": 1336756, "tid": 1381189, + "ts": 1655275088124.829, "dur": 62.640, + "args": { + "External id": 4056185,"Record function id": 0, "Ev Idx": 3192 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.17)", "pid": 1336756, "tid": 1381189, + "ts": 1655275088193.242, "dur": 37257.118, + "args": { + "External id": 4056186,"Record function id": 0, "Ev Idx": 3193 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655275088279.842, "dur": 6.402, + "args": { + "External id": 4056187,"Record function id": 0, "Concrete Inputs": ["[51384320]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3194 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275088295.712, "dur": 4.847, + "args": { + "External id": 4056188,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[51384320], []], "Ev Idx": 3195 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::chunk_cat", "pid": 1336756, "tid": 1381189, + "ts": 1655275088316.330, "dur": 36310.009, + "args": { + "External id": 4056189,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [2048, 1], [2048, 1], [2048, 1], [2048, 1], [1], [2048, 1], [2048, 1], [5632, 1]], [], [], [6423040, 1]], "Input Dims": [[[2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048], [5632, 2048], [5632, 2048], [2048, 5632]], [], [], [8, 6423040]], "Ev Idx": 3196 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_chunk_cat", "pid": 1336756, "tid": 1381189, + "ts": 1655275088329.547, "dur": 36287.827, + "args": { + "External id": 4056190,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [2048, 1], [2048, 1], [2048, 1], [2048, 1], [1], [2048, 1], [2048, 1], [5632, 1]], [], [], [6423040, 1]], "Input Dims": [[[2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048], [5632, 2048], [5632, 2048], [2048, 5632]], [], [], [8, 6423040]], "Ev Idx": 3197 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655275088374.371, "dur": 15.192, + "args": { + "External id": 4056191,"Record function id": 0, "Concrete Inputs": ["[12602]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3198 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1381189, + "ts": 1655275088395.964, "dur": 36182.147, + "args": { + "External id": 4056192,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[12602], [], [], [], [], [], [], []], "Ev Idx": 3199 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336756, "tid": 1381189, + "ts": 1655275088398.450, "dur": 36178.930, + "args": { + "External id": 4056193,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[12602], [], [], [], [], [], []], "Ev Idx": 3200 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275088402.633, "dur": 4.883, + "args": { + "External id": 4056194,"Record function id": 0, "Concrete Inputs": ["[12602]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3201 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1381189, + "ts": 1655275088409.540, "dur": 36164.286, + "args": { + "External id": 4056195,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[12602], [12602], []], "Ev Idx": 3202 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 1336756, "tid": 1381189, + "ts": 1655275124714.435, "dur": 9.255, + "args": { + "External id": 4056196,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "", "", "", "False"], "Input type": ["float", "ScalarList", "", "", "", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[51384320], [], [], [], [], []], "Ev Idx": 3203 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655275124717.930, "dur": 5.451, + "args": { + "External id": 4056197,"Record function id": 0, "Concrete Inputs": ["[6423040]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3204 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_reduce_scatter_base_", "pid": 1336756, "tid": 1381189, + "ts": 1655275124755.951, "dur": 377.289, + "args": { + "External id": 4056198,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "-1"], "Input type": ["float", "float", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], [], []], "Input Dims": [[6423040], [51384320], [], [], [], []], "Ev Idx": 3205 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336756, "tid": 1381189, + "ts": 1655275124782.125, "dur": 345.323, + "args": { + "External id": 4056199,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 3, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "3", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 6423040, "Process Group Name": "0", "Input type": ["float", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[51384320], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 3206, "In msg nelems": 51384320 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_reduce_scatter_base", "pid": 1336756, "tid": 1381189, + "ts": 1655275124793.511, "dur": 328.071, + "args": { + "External id": 4056200,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[51384320]], "Ev Idx": 3207 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336756, "tid": 1381189, + "ts": 1655275125154.346, "dur": 2.298, + "args": { + "External id": 4056201,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "3", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 3208, "In msg nelems": 0, "Rank": 3, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275125215.466, "dur": 6.801, + "args": { + "External id": 4056202,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3209 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275125269.790, "dur": 1.484, + "args": { + "External id": 4056203,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "256"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3210 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275125288.227, "dur": 1.043, + "args": { + "External id": 4056204,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "524544"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3211 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275125304.249, "dur": 0.914, + "args": { + "External id": 4056205,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "1048832"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3212 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275125316.317, "dur": 0.928, + "args": { + "External id": 4056206,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "1573120"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3213 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275125328.732, "dur": 0.989, + "args": { + "External id": 4056207,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3214 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275125341.972, "dur": 1.265, + "args": { + "External id": 4056208,"Record function id": 0, "Concrete Inputs": ["", "[704, 2048]", "[2048, 1]", "2097664"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3215 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275125357.453, "dur": 2.160, + "args": { + "External id": 4056209,"Record function id": 0, "Concrete Inputs": ["", "[704, 2048]", "[2048, 1]", "3539456"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3216 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275125370.469, "dur": 0.973, + "args": { + "External id": 4056210,"Record function id": 0, "Concrete Inputs": ["", "[256, 5632]", "[5632, 1]", "4981248"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3217 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: CompiledFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1655275125484.306, "dur": 2701.322, + "args": { + "External id": 4056211,"Record function id": 0, "Ev Idx": 3218 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.16)", "pid": 1336756, "tid": 1381189, + "ts": 1655275125504.067, "dur": 1005.170, + "args": { + "External id": 4056212,"Record function id": 0, "Ev Idx": 3219 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.16)", "pid": 1336756, "tid": 1381189, + "ts": 1655275125519.476, "dur": 314.074, + "args": { + "External id": 4056213,"Record function id": 0, "Ev Idx": 3220 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275125595.759, "dur": 4.956, + "args": { + "External id": 4056214,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[51384320], []], "Ev Idx": 3221 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275125604.045, "dur": 1.092, + "args": { + "External id": 4056215,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 3222 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275125606.763, "dur": 1.122, + "args": { + "External id": 4056216,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 3223 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275125609.400, "dur": 2.741, + "args": { + "External id": 4056217,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 3224 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275125613.518, "dur": 0.692, + "args": { + "External id": 4056218,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 3225 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275125615.935, "dur": 0.719, + "args": { + "External id": 4056219,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 3226 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275125618.110, "dur": 1.631, + "args": { + "External id": 4056220,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 3227 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275125621.382, "dur": 0.883, + "args": { + "External id": 4056221,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 3228 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275125623.690, "dur": 0.680, + "args": { + "External id": 4056222,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 3229 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275125625.732, "dur": 1.170, + "args": { + "External id": 4056223,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 3230 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 1336756, "tid": 1381189, + "ts": 1655275125644.941, "dur": 155.983, + "args": { + "External id": 4056224,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 3231 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 1336756, "tid": 1381189, + "ts": 1655275125660.961, "dur": 135.172, + "args": { + "External id": 4056225,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 3232 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655275125684.205, "dur": 11.967, + "args": { + "External id": 4056226,"Record function id": 0, "Concrete Inputs": ["[2133]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3233 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1381189, + "ts": 1655275125699.520, "dur": 68.842, + "args": { + "External id": 4056227,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], [], []], "Ev Idx": 3234 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336756, "tid": 1381189, + "ts": 1655275125702.252, "dur": 65.813, + "args": { + "External id": 4056228,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], []], "Ev Idx": 3235 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275125706.490, "dur": 7.226, + "args": { + "External id": 4056229,"Record function id": 0, "Concrete Inputs": ["[2133]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3236 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1381189, + "ts": 1655275125715.740, "dur": 51.538, + "args": { + "External id": 4056230,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[2133], [2133], []], "Ev Idx": 3237 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::backward_prefetch for model.layers.15", "pid": 1336756, "tid": 1381189, + "ts": 1655275125909.093, "dur": 591.629, + "args": { + "External id": 4056231,"Record function id": 0, "Ev Idx": 3238 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.15)", "pid": 1336756, "tid": 1381189, + "ts": 1655275125924.760, "dur": 563.559, + "args": { + "External id": 4056232,"Record function id": 0, "Ev Idx": 3239 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655275125976.757, "dur": 43.368, + "args": { + "External id": 4056233,"Record function id": 0, "Concrete Inputs": ["[6423040]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3240 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336756, "tid": 1381189, + "ts": 1655275126038.294, "dur": 31.495, + "args": { + "External id": 4056234,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 3241 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275126043.382, "dur": 1.587, + "args": { + "External id": 4056235,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3242 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275126047.288, "dur": 0.644, + "args": { + "External id": 4056236,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3243 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275126049.750, "dur": 0.482, + "args": { + "External id": 4056237,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3244 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275126051.984, "dur": 0.454, + "args": { + "External id": 4056238,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3245 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275126054.167, "dur": 0.768, + "args": { + "External id": 4056239,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3246 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275126056.747, "dur": 0.351, + "args": { + "External id": 4056240,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3247 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275126058.933, "dur": 2.161, + "args": { + "External id": 4056241,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3248 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275126062.557, "dur": 0.547, + "args": { + "External id": 4056242,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3249 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275126064.959, "dur": 0.398, + "args": { + "External id": 4056243,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3250 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336756, "tid": 1381189, + "ts": 1655275126079.107, "dur": 33.466, + "args": { + "External id": 4056244,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 3251 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 1336756, "tid": 1381189, + "ts": 1655275126147.377, "dur": 102.575, + "args": { + "External id": 4056245,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "6423040", "8", "3", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [], [], [], [], [], []], "Ev Idx": 3252 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655275126157.686, "dur": 3.494, + "args": { + "External id": 4056246,"Record function id": 0, "Concrete Inputs": ["[51384320]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3253 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 1336756, "tid": 1381189, + "ts": 1655275126166.794, "dur": 10.626, + "args": { + "External id": 4056247,"Record function id": 0, "Concrete Inputs": ["", "0", "19269120", "6423040"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 3254 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1381189, + "ts": 1655275126171.256, "dur": 5.721, + "args": { + "External id": 4056248,"Record function id": 0, "Concrete Inputs": ["", "0", "19269120", "25692160", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[51384320], [], [], [], []], "Ev Idx": 3255 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275126174.995, "dur": 0.734, + "args": { + "External id": 4056249,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "[1]", "19269120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 3256 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336756, "tid": 1381189, + "ts": 1655275126184.578, "dur": 27.859, + "args": { + "External id": 4056250,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 3257 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275126187.463, "dur": 0.362, + "args": { + "External id": 4056251,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "19269120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3258 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275126190.177, "dur": 0.504, + "args": { + "External id": 4056252,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "19269376"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3259 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275126192.766, "dur": 0.551, + "args": { + "External id": 4056253,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "19793664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3260 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275126194.913, "dur": 2.478, + "args": { + "External id": 4056254,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "20317952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3261 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275126199.279, "dur": 0.389, + "args": { + "External id": 4056255,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "20842240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3262 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275126201.447, "dur": 0.716, + "args": { + "External id": 4056256,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "21366528"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3263 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275126204.278, "dur": 0.563, + "args": { + "External id": 4056257,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "21366784"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3264 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275126206.620, "dur": 0.646, + "args": { + "External id": 4056258,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "22808576"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3265 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275126208.965, "dur": 0.314, + "args": { + "External id": 4056259,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "24250368"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3266 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336756, "tid": 1381189, + "ts": 1655275126224.012, "dur": 18.708, + "args": { + "External id": 4056260,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 3267 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 1336756, "tid": 1381189, + "ts": 1655275126296.619, "dur": 106.329, + "args": { + "External id": 4056261,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[51384320], [6423040], [], [], []], "Ev Idx": 3268 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336756, "tid": 1381189, + "ts": 1655275126318.076, "dur": 81.139, + "args": { + "External id": 4056262,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 3, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "3", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 51384320, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[6423040], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 3269, "In msg nelems": 6423040 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 1336756, "tid": 1381189, + "ts": 1655275126327.957, "dur": 67.164, + "args": { + "External id": 4056263,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[6423040]], "Ev Idx": 3270 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336756, "tid": 1381189, + "ts": 1655275126432.844, "dur": 2.756, + "args": { + "External id": 4056264,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "3", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 3271, "In msg nelems": 0, "Rank": 3, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1655275126515.949, "dur": 1650.210, + "args": { + "External id": 4056265,"Sequence number": 40618386, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 3272 + } + }, + { + "ph": "f", "id": 194, "pid": 1336756, "tid": 1381189, "ts": 1655275126515.949, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275126623.830, "dur": 105.541, + "args": { + "External id": 4056266,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [5632, 1], [5632, 1]], "Input Dims": [[65536, 2048], [2048, 5632], [65536, 5632]], "Ev Idx": 3273 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_add_mul_rsub_silu_0", "pid": 1336756, "tid": 1381189, + "ts": 1655275126769.749, "dur": 37.258, + "args": { + "External id": 4056267,"kernel_hash": "c2zszzsomz26dv2qwvmiurvgyrl5qxtyn6ocoqkdpzzhfzwqp5q6", "grid": "grid(369098752,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "369098752"], "kernel_file": "/tmp/torchinductor_cvm/2z/c2zszzsomz26dv2qwvmiurvgyrl5qxtyn6ocoqkdpzzhfzwqp5q6.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[5632, 1], [5632, 1], [5632, 1], [23068672, 5632, 1], [23068672, 5632, 1], [23068672, 5632, 1], []], "Input Dims": [[65536, 5632], [65536, 5632], [65536, 5632], [16, 4096, 5632], [16, 4096, 5632], [16, 4096, 5632], []], "Ev Idx": 3274 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 1336756, "tid": 1381189, + "ts": 1655275126824.260, "dur": 49.791, + "args": { + "External id": 4056268,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[0, 1, 2048], [0, 5632, 1], [11534336, 5632, 1]], "Input Dims": [[1, 2048, 65536], [1, 65536, 5632], [1, 2048, 5632]], "Ev Idx": 3275 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275126884.297, "dur": 33.560, + "args": { + "External id": 4056269,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 5632], [2048, 1], [2048, 1]], "Input Dims": [[5632, 65536], [65536, 2048], [5632, 2048]], "Ev Idx": 3276 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275126927.537, "dur": 47.469, + "args": { + "External id": 4056270,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 5632], [5632, 2048], [65536, 2048]], "Ev Idx": 3277 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275127041.528, "dur": 37.630, + "args": { + "External id": 4056271,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 5632], [2048, 1], [2048, 1]], "Input Dims": [[5632, 65536], [65536, 2048], [5632, 2048]], "Ev Idx": 3278 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275127089.152, "dur": 44.032, + "args": { + "External id": 4056272,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 5632], [5632, 2048], [65536, 2048]], "Ev Idx": 3279 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_1", "pid": 1336756, "tid": 1381189, + "ts": 1655275127158.642, "dur": 23.967, + "args": { + "External id": 4056273,"kernel_hash": "cjd6g3jfgntyoifzno6l2urmnhif7alxtw6zz7miov66vywxwv7d", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/jd/cjd6g3jfgntyoifzno6l2urmnhif7alxtw6zz7miov66vywxwv7d.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[65536, 2048], [65536, 2048], []], "Ev Idx": 3280 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 1336756, "tid": 1381189, + "ts": 1655275127202.731, "dur": 27.010, + "args": { + "External id": 4056274,"kernel_hash": "cxhg545cyph4gbk5vymzyh72vho7oogk3ycan2lp4cxntklp5hew", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "65536", "2048", "1", "497", "132", "True", "2048", "True", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/xh/cxhg545cyph4gbk5vymzyh72vho7oogk3ycan2lp4cxntklp5hew.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [1], [2048, 1], [2048, 1], [2048, 1], [2048, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [2048], [65536, 2048], [65536, 2048], [132, 2048], [65536, 2048], [65536], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 3281 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 1336756, "tid": 1381189, + "ts": 1655275127250.077, "dur": 19.820, + "args": { + "External id": 4056275,"kernel_hash": "cu42i6zmxtvs2i7cs6x4ixaexke3lhgdiaye5oxwm7s3u6em6co4", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "66"], "kernel_file": "/tmp/torchinductor_cvm/u4/cu42i6zmxtvs2i7cs6x4ixaexke3lhgdiaye5oxwm7s3u6em6co4.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [4096, 1, 2048], [], []], "Input Dims": [[132, 2048], [1, 2048, 2], [], []], "Ev Idx": 3282 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 1336756, "tid": 1381189, + "ts": 1655275127285.185, "dur": 15.016, + "args": { + "External id": 4056276,"kernel_hash": "ckihofrorhmzazt2wfn2dz2m5wfx3auisu2gvfo2jsepr4zyekmq", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "2"], "kernel_file": "/tmp/torchinductor_cvm/ki/ckihofrorhmzazt2wfn2dz2m5wfx3auisu2gvfo2jsepr4zyekmq.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1, 2048], [2048, 1], [], []], "Input Dims": [[1, 2048, 2], [1, 2048], [], []], "Ev Idx": 3283 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275127310.707, "dur": 29.996, + "args": { + "External id": 4056277,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 3284 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275127343.919, "dur": 34.073, + "args": { + "External id": 4056278,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 3285 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 1336756, "tid": 1381189, + "ts": 1655275127405.903, "dur": 193.689, + "args": { + "External id": 4056279,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.125", "True", "-1", "-1", "0.", "", "False", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar", "long int"], "Input Strides": [[8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [131072, 4096, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 32, 4096], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 3286 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655275127502.502, "dur": 6.433, + "args": { + "External id": 4056280,"Record function id": 0, "Concrete Inputs": ["[16, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3287 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655275127511.483, "dur": 2.360, + "args": { + "External id": 4056281,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3288 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336756, "tid": 1381189, + "ts": 1655275127629.973, "dur": 24.096, + "args": { + "External id": 4056282,"kernel_hash": "cb6oumcqb462ndf2ivcd2sc6qg6mfjahptjw4ih7cesqhfpziv3b", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/b6/cb6oumcqb462ndf2ivcd2sc6qg6mfjahptjw4ih7cesqhfpziv3b.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 3289 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336756, "tid": 1381189, + "ts": 1655275127665.609, "dur": 13.811, + "args": { + "External id": 4056283,"kernel_hash": "cb6oumcqb462ndf2ivcd2sc6qg6mfjahptjw4ih7cesqhfpziv3b", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/b6/cb6oumcqb462ndf2ivcd2sc6qg6mfjahptjw4ih7cesqhfpziv3b.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 3290 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275127688.792, "dur": 39.706, + "args": { + "External id": 4056284,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 3291 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275127736.133, "dur": 36.308, + "args": { + "External id": 4056285,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 3292 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275127781.087, "dur": 20.719, + "args": { + "External id": 4056286,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 3293 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275127807.379, "dur": 31.018, + "args": { + "External id": 4056287,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 3294 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275127844.395, "dur": 19.399, + "args": { + "External id": 4056288,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 3295 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275127870.164, "dur": 29.045, + "args": { + "External id": 4056289,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 3296 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_4", "pid": 1336756, "tid": 1381189, + "ts": 1655275127915.455, "dur": 30.743, + "args": { + "External id": 4056290,"kernel_hash": "c7pqhdjojzeazwsh5g3ibnyk4m2nfh3q73e3zc7hljz4yvhe7c4h", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/7p/c7pqhdjojzeazwsh5g3ibnyk4m2nfh3q73e3zc7hljz4yvhe7c4h.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1], []], "Input Dims": [[65536, 2048], [65536, 2048], [65536, 2048], []], "Ev Idx": 3297 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_2", "pid": 1336756, "tid": 1381189, + "ts": 1655275127969.346, "dur": 62.543, + "args": { + "External id": 4056291,"kernel_hash": "cvgvwkysjpcw75q5t3guce5bep2so25f7i5zxc6ipt5f56shof73", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "65536", "2048", "1", "497", "132", "True", "2048", "False", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/vg/cvgvwkysjpcw75q5t3guce5bep2so25f7i5zxc6ipt5f56shof73.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [1], [2048, 1], [2048, 1], [2048, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [2048], [65536, 2048], [65536, 2048], [132, 2048], [65536], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 3298 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 1336756, "tid": 1381189, + "ts": 1655275128049.867, "dur": 17.904, + "args": { + "External id": 4056292,"kernel_hash": "cu42i6zmxtvs2i7cs6x4ixaexke3lhgdiaye5oxwm7s3u6em6co4", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "66"], "kernel_file": "/tmp/torchinductor_cvm/u4/cu42i6zmxtvs2i7cs6x4ixaexke3lhgdiaye5oxwm7s3u6em6co4.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [4096, 1, 2048], [], []], "Input Dims": [[132, 2048], [1, 2048, 2], [], []], "Ev Idx": 3299 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 1336756, "tid": 1381189, + "ts": 1655275128090.573, "dur": 14.497, + "args": { + "External id": 4056293,"kernel_hash": "ckihofrorhmzazt2wfn2dz2m5wfx3auisu2gvfo2jsepr4zyekmq", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "2"], "kernel_file": "/tmp/torchinductor_cvm/ki/ckihofrorhmzazt2wfn2dz2m5wfx3auisu2gvfo2jsepr4zyekmq.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1, 2048], [2048, 1], [], []], "Input Dims": [[1, 2048, 2], [1, 2048], [], []], "Ev Idx": 3300 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_5", "pid": 1336756, "tid": 1381189, + "ts": 1655275128118.347, "dur": 16.132, + "args": { + "External id": 4056294,"kernel_hash": "cckrpn5uuxyvbancoio3sz2onrjto236n54xx4ycphq5p6r3jlfj", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/ck/cckrpn5uuxyvbancoio3sz2onrjto236n54xx4ycphq5p6r3jlfj.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [8388608, 2048, 1], []], "Input Dims": [[65536, 2048], [65536, 2048], [16, 4096, 2048], []], "Ev Idx": 3301 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275128208.445, "dur": 19.349, + "args": { + "External id": 4056295,"Record function id": 0, "Ev Idx": 3302 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275128211.884, "dur": 14.910, + "args": { + "External id": 4056296,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 3303 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275128216.332, "dur": 9.494, + "args": { + "External id": 4056297,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 3304 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275128218.338, "dur": 7.379, + "args": { + "External id": 4056298,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 3305 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275128232.084, "dur": 4.843, + "args": { + "External id": 4056299,"Record function id": 0, "Ev Idx": 3306 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275128233.458, "dur": 2.982, + "args": { + "External id": 4056300,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 3307 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275128234.511, "dur": 1.467, + "args": { + "External id": 4056301,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 3308 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275128235.166, "dur": 0.726, + "args": { + "External id": 4056302,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 3309 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275128240.340, "dur": 6.701, + "args": { + "External id": 4056303,"Record function id": 0, "Ev Idx": 3310 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275128241.857, "dur": 4.777, + "args": { + "External id": 4056304,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 3311 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275128242.674, "dur": 3.530, + "args": { + "External id": 4056305,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 3312 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275128243.035, "dur": 3.083, + "args": { + "External id": 4056306,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 3313 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275128250.578, "dur": 4.783, + "args": { + "External id": 4056307,"Record function id": 0, "Ev Idx": 3314 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275128251.858, "dur": 3.105, + "args": { + "External id": 4056308,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 3315 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275128252.501, "dur": 2.047, + "args": { + "External id": 4056309,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 3316 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275128253.290, "dur": 1.167, + "args": { + "External id": 4056310,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 3317 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275128258.722, "dur": 4.040, + "args": { + "External id": 4056311,"Record function id": 0, "Ev Idx": 3318 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275128260.151, "dur": 2.203, + "args": { + "External id": 4056312,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 3319 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275128260.987, "dur": 0.946, + "args": { + "External id": 4056313,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 3320 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275128261.263, "dur": 0.600, + "args": { + "External id": 4056314,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 3321 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275128265.970, "dur": 4.119, + "args": { + "External id": 4056315,"Record function id": 0, "Ev Idx": 3322 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275128267.204, "dur": 2.484, + "args": { + "External id": 4056316,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 3323 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275128267.930, "dur": 1.322, + "args": { + "External id": 4056317,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 3324 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275128268.492, "dur": 0.629, + "args": { + "External id": 4056318,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 3325 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275128273.283, "dur": 3.697, + "args": { + "External id": 4056319,"Record function id": 0, "Ev Idx": 3326 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275128274.422, "dur": 2.135, + "args": { + "External id": 4056320,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 3327 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275128274.949, "dur": 1.211, + "args": { + "External id": 4056321,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 3328 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275128275.481, "dur": 0.569, + "args": { + "External id": 4056322,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 3329 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275128280.324, "dur": 7.024, + "args": { + "External id": 4056323,"Record function id": 0, "Ev Idx": 3330 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275128284.531, "dur": 2.436, + "args": { + "External id": 4056324,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 3331 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275128285.052, "dur": 1.485, + "args": { + "External id": 4056325,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 3332 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275128285.522, "dur": 0.942, + "args": { + "External id": 4056326,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 3333 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275128290.642, "dur": 4.328, + "args": { + "External id": 4056327,"Record function id": 0, "Ev Idx": 3334 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275128291.792, "dur": 2.764, + "args": { + "External id": 4056328,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 3335 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275128292.689, "dur": 1.443, + "args": { + "External id": 4056329,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 3336 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275128293.192, "dur": 0.855, + "args": { + "External id": 4056330,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 3337 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RegisterPostBackwardFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1655275128298.786, "dur": 38987.331, + "args": { + "External id": 4056331,"Record function id": 0, "Sequence number": 40618385, "Fwd thread id": 1, "Ev Idx": 3338 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1655275128300.109, "dur": 38976.983, + "args": { + "External id": 4056332,"Sequence number": 40618385, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 3339 + } + }, + { + "ph": "f", "id": 195, "pid": 1336756, "tid": 1381189, "ts": 1655275128300.109, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.16)", "pid": 1336756, "tid": 1381189, + "ts": 1655275128327.893, "dur": 39.076, + "args": { + "External id": 4056333,"Record function id": 0, "Ev Idx": 3340 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.16)", "pid": 1336756, "tid": 1381189, + "ts": 1655275128375.100, "dur": 83.920, + "args": { + "External id": 4056334,"Record function id": 0, "Ev Idx": 3341 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.16)", "pid": 1336756, "tid": 1381189, + "ts": 1655275128467.008, "dur": 38801.669, + "args": { + "External id": 4056335,"Record function id": 0, "Ev Idx": 3342 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655275128555.956, "dur": 7.078, + "args": { + "External id": 4056336,"Record function id": 0, "Concrete Inputs": ["[51384320]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3343 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275128573.179, "dur": 6.627, + "args": { + "External id": 4056337,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[51384320], []], "Ev Idx": 3344 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::chunk_cat", "pid": 1336756, "tid": 1381189, + "ts": 1655275128593.884, "dur": 37753.869, + "args": { + "External id": 4056338,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [2048, 1], [2048, 1], [2048, 1], [2048, 1], [1], [2048, 1], [2048, 1], [5632, 1]], [], [], [6423040, 1]], "Input Dims": [[[2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048], [5632, 2048], [5632, 2048], [2048, 5632]], [], [], [8, 6423040]], "Ev Idx": 3345 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_chunk_cat", "pid": 1336756, "tid": 1381189, + "ts": 1655275128607.722, "dur": 37730.851, + "args": { + "External id": 4056339,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [2048, 1], [2048, 1], [2048, 1], [2048, 1], [1], [2048, 1], [2048, 1], [5632, 1]], [], [], [6423040, 1]], "Input Dims": [[[2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048], [5632, 2048], [5632, 2048], [2048, 5632]], [], [], [8, 6423040]], "Ev Idx": 3346 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655275128655.138, "dur": 13.989, + "args": { + "External id": 4056340,"Record function id": 0, "Concrete Inputs": ["[12602]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3347 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1381189, + "ts": 1655275128675.459, "dur": 37624.406, + "args": { + "External id": 4056341,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[12602], [], [], [], [], [], [], []], "Ev Idx": 3348 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336756, "tid": 1381189, + "ts": 1655275128678.180, "dur": 37621.037, + "args": { + "External id": 4056342,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[12602], [], [], [], [], [], []], "Ev Idx": 3349 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275128682.980, "dur": 5.032, + "args": { + "External id": 4056343,"Record function id": 0, "Concrete Inputs": ["[12602]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3350 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1381189, + "ts": 1655275128689.985, "dur": 37605.164, + "args": { + "External id": 4056344,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[12602], [12602], []], "Ev Idx": 3351 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 1336756, "tid": 1381189, + "ts": 1655275166450.890, "dur": 9.997, + "args": { + "External id": 4056345,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "", "", "", "False"], "Input type": ["float", "ScalarList", "", "", "", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[51384320], [], [], [], [], []], "Ev Idx": 3352 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655275166454.051, "dur": 6.281, + "args": { + "External id": 4056346,"Record function id": 0, "Concrete Inputs": ["[6423040]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3353 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_reduce_scatter_base_", "pid": 1336756, "tid": 1381189, + "ts": 1655275166492.478, "dur": 418.096, + "args": { + "External id": 4056347,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "-1"], "Input type": ["float", "float", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], [], []], "Input Dims": [[6423040], [51384320], [], [], [], []], "Ev Idx": 3354 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336756, "tid": 1381189, + "ts": 1655275166523.858, "dur": 381.180, + "args": { + "External id": 4056348,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 3, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "3", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 6423040, "Process Group Name": "0", "Input type": ["float", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[51384320], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 3355, "In msg nelems": 51384320 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_reduce_scatter_base", "pid": 1336756, "tid": 1381189, + "ts": 1655275166535.730, "dur": 363.323, + "args": { + "External id": 4056349,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[51384320]], "Ev Idx": 3356 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336756, "tid": 1381189, + "ts": 1655275166943.671, "dur": 2.718, + "args": { + "External id": 4056350,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "3", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 3357, "In msg nelems": 0, "Rank": 3, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275167045.775, "dur": 7.410, + "args": { + "External id": 4056351,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3358 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275167101.216, "dur": 1.837, + "args": { + "External id": 4056352,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "256"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3359 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275167120.505, "dur": 3.244, + "args": { + "External id": 4056353,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "524544"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3360 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275167136.950, "dur": 1.157, + "args": { + "External id": 4056354,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "1048832"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3361 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275167149.410, "dur": 1.021, + "args": { + "External id": 4056355,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "1573120"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3362 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275167161.860, "dur": 1.023, + "args": { + "External id": 4056356,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3363 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275167174.143, "dur": 2.535, + "args": { + "External id": 4056357,"Record function id": 0, "Concrete Inputs": ["", "[704, 2048]", "[2048, 1]", "2097664"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3364 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275167190.216, "dur": 1.980, + "args": { + "External id": 4056358,"Record function id": 0, "Concrete Inputs": ["", "[704, 2048]", "[2048, 1]", "3539456"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3365 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275167204.135, "dur": 0.995, + "args": { + "External id": 4056359,"Record function id": 0, "Concrete Inputs": ["", "[256, 5632]", "[5632, 1]", "4981248"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3366 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: CompiledFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1655275167301.837, "dur": 2655.311, + "args": { + "External id": 4056360,"Record function id": 0, "Ev Idx": 3367 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.15)", "pid": 1336756, "tid": 1381189, + "ts": 1655275167321.473, "dur": 1011.405, + "args": { + "External id": 4056361,"Record function id": 0, "Ev Idx": 3368 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.15)", "pid": 1336756, "tid": 1381189, + "ts": 1655275167335.763, "dur": 338.883, + "args": { + "External id": 4056362,"Record function id": 0, "Ev Idx": 3369 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275167410.229, "dur": 4.063, + "args": { + "External id": 4056363,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[51384320], []], "Ev Idx": 3370 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275167434.544, "dur": 1.428, + "args": { + "External id": 4056364,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 3371 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275167438.349, "dur": 3.141, + "args": { + "External id": 4056365,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 3372 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275167443.214, "dur": 0.916, + "args": { + "External id": 4056366,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 3373 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275167445.772, "dur": 0.931, + "args": { + "External id": 4056367,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 3374 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275167448.512, "dur": 1.104, + "args": { + "External id": 4056368,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 3375 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275167451.298, "dur": 1.441, + "args": { + "External id": 4056369,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 3376 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275167454.203, "dur": 1.091, + "args": { + "External id": 4056370,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 3377 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275167457.052, "dur": 1.129, + "args": { + "External id": 4056371,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 3378 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275167459.730, "dur": 0.786, + "args": { + "External id": 4056372,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 3379 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 1336756, "tid": 1381189, + "ts": 1655275167480.609, "dur": 158.995, + "args": { + "External id": 4056373,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 3380 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 1336756, "tid": 1381189, + "ts": 1655275167497.531, "dur": 137.222, + "args": { + "External id": 4056374,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 3381 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655275167518.667, "dur": 15.880, + "args": { + "External id": 4056375,"Record function id": 0, "Concrete Inputs": ["[2133]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3382 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1381189, + "ts": 1655275167537.625, "dur": 68.610, + "args": { + "External id": 4056376,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], [], []], "Ev Idx": 3383 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336756, "tid": 1381189, + "ts": 1655275167540.328, "dur": 65.504, + "args": { + "External id": 4056377,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], []], "Ev Idx": 3384 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275167544.747, "dur": 5.904, + "args": { + "External id": 4056378,"Record function id": 0, "Concrete Inputs": ["[2133]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3385 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1381189, + "ts": 1655275167552.438, "dur": 52.537, + "args": { + "External id": 4056379,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[2133], [2133], []], "Ev Idx": 3386 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::backward_prefetch for model.layers.14", "pid": 1336756, "tid": 1381189, + "ts": 1655275167755.497, "dur": 569.066, + "args": { + "External id": 4056380,"Record function id": 0, "Ev Idx": 3387 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.14)", "pid": 1336756, "tid": 1381189, + "ts": 1655275167773.437, "dur": 538.260, + "args": { + "External id": 4056381,"Record function id": 0, "Ev Idx": 3388 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655275167826.568, "dur": 4.943, + "args": { + "External id": 4056382,"Record function id": 0, "Concrete Inputs": ["[6423040]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3389 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336756, "tid": 1381189, + "ts": 1655275167846.847, "dur": 30.648, + "args": { + "External id": 4056383,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 3390 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275167852.146, "dur": 1.591, + "args": { + "External id": 4056384,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3391 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275167855.967, "dur": 0.727, + "args": { + "External id": 4056385,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3392 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275167858.541, "dur": 0.471, + "args": { + "External id": 4056386,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3393 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275167860.813, "dur": 0.632, + "args": { + "External id": 4056387,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3394 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275167863.521, "dur": 0.437, + "args": { + "External id": 4056388,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3395 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275167865.449, "dur": 2.212, + "args": { + "External id": 4056389,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3396 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275167869.218, "dur": 0.409, + "args": { + "External id": 4056390,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3397 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275167871.262, "dur": 0.393, + "args": { + "External id": 4056391,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3398 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275167873.244, "dur": 0.438, + "args": { + "External id": 4056392,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3399 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336756, "tid": 1381189, + "ts": 1655275167886.597, "dur": 27.894, + "args": { + "External id": 4056393,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 3400 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 1336756, "tid": 1381189, + "ts": 1655275167944.222, "dur": 142.799, + "args": { + "External id": 4056394,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "6423040", "8", "3", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [], [], [], [], [], []], "Ev Idx": 3401 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655275167953.411, "dur": 2.733, + "args": { + "External id": 4056395,"Record function id": 0, "Concrete Inputs": ["[51384320]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3402 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 1336756, "tid": 1381189, + "ts": 1655275167960.991, "dur": 10.605, + "args": { + "External id": 4056396,"Record function id": 0, "Concrete Inputs": ["", "0", "19269120", "6423040"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 3403 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1381189, + "ts": 1655275167965.297, "dur": 5.873, + "args": { + "External id": 4056397,"Record function id": 0, "Concrete Inputs": ["", "0", "19269120", "25692160", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[51384320], [], [], [], []], "Ev Idx": 3404 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275167969.462, "dur": 0.456, + "args": { + "External id": 4056398,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "[1]", "19269120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 3405 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336756, "tid": 1381189, + "ts": 1655275167978.649, "dur": 66.083, + "args": { + "External id": 4056399,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 3406 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275168018.854, "dur": 0.991, + "args": { + "External id": 4056400,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "19269120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3407 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275168022.773, "dur": 0.534, + "args": { + "External id": 4056401,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "19269376"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3408 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275168024.873, "dur": 2.199, + "args": { + "External id": 4056402,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "19793664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3409 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275168028.699, "dur": 0.304, + "args": { + "External id": 4056403,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "20317952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3410 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275168030.879, "dur": 0.340, + "args": { + "External id": 4056404,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "20842240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3411 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275168033.326, "dur": 0.533, + "args": { + "External id": 4056405,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "21366528"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3412 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275168035.638, "dur": 0.370, + "args": { + "External id": 4056406,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "21366784"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3413 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275168037.925, "dur": 0.552, + "args": { + "External id": 4056407,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "22808576"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3414 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275168040.292, "dur": 0.750, + "args": { + "External id": 4056408,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "24250368"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3415 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336756, "tid": 1381189, + "ts": 1655275168056.057, "dur": 23.517, + "args": { + "External id": 4056409,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 3416 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 1336756, "tid": 1381189, + "ts": 1655275168135.541, "dur": 110.581, + "args": { + "External id": 4056410,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[51384320], [6423040], [], [], []], "Ev Idx": 3417 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336756, "tid": 1381189, + "ts": 1655275168158.930, "dur": 83.632, + "args": { + "External id": 4056411,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 3, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "3", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 51384320, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[6423040], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 3418, "In msg nelems": 6423040 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 1336756, "tid": 1381189, + "ts": 1655275168169.011, "dur": 69.236, + "args": { + "External id": 4056412,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[6423040]], "Ev Idx": 3419 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336756, "tid": 1381189, + "ts": 1655275168260.620, "dur": 1.944, + "args": { + "External id": 4056413,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "3", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 3420, "In msg nelems": 0, "Rank": 3, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1655275168340.126, "dur": 1594.555, + "args": { + "External id": 4056414,"Sequence number": 40618384, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 3421 + } + }, + { + "ph": "f", "id": 196, "pid": 1336756, "tid": 1381189, "ts": 1655275168340.126, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275168464.816, "dur": 105.106, + "args": { + "External id": 4056415,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [5632, 1], [5632, 1]], "Input Dims": [[65536, 2048], [2048, 5632], [65536, 5632]], "Ev Idx": 3422 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_add_mul_rsub_silu_0", "pid": 1336756, "tid": 1381189, + "ts": 1655275168607.069, "dur": 36.534, + "args": { + "External id": 4056416,"kernel_hash": "c2zszzsomz26dv2qwvmiurvgyrl5qxtyn6ocoqkdpzzhfzwqp5q6", "grid": "grid(369098752,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "369098752"], "kernel_file": "/tmp/torchinductor_cvm/2z/c2zszzsomz26dv2qwvmiurvgyrl5qxtyn6ocoqkdpzzhfzwqp5q6.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[5632, 1], [5632, 1], [5632, 1], [23068672, 5632, 1], [23068672, 5632, 1], [23068672, 5632, 1], []], "Input Dims": [[65536, 5632], [65536, 5632], [65536, 5632], [16, 4096, 5632], [16, 4096, 5632], [16, 4096, 5632], []], "Ev Idx": 3423 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 1336756, "tid": 1381189, + "ts": 1655275168660.988, "dur": 49.059, + "args": { + "External id": 4056417,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[0, 1, 2048], [0, 5632, 1], [11534336, 5632, 1]], "Input Dims": [[1, 2048, 65536], [1, 65536, 5632], [1, 2048, 5632]], "Ev Idx": 3424 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275168721.965, "dur": 33.273, + "args": { + "External id": 4056418,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 5632], [2048, 1], [2048, 1]], "Input Dims": [[5632, 65536], [65536, 2048], [5632, 2048]], "Ev Idx": 3425 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275168762.368, "dur": 46.180, + "args": { + "External id": 4056419,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 5632], [5632, 2048], [65536, 2048]], "Ev Idx": 3426 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275168816.238, "dur": 28.433, + "args": { + "External id": 4056420,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 5632], [2048, 1], [2048, 1]], "Input Dims": [[5632, 65536], [65536, 2048], [5632, 2048]], "Ev Idx": 3427 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275168851.977, "dur": 43.545, + "args": { + "External id": 4056421,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 5632], [5632, 2048], [65536, 2048]], "Ev Idx": 3428 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_1", "pid": 1336756, "tid": 1381189, + "ts": 1655275168919.482, "dur": 20.840, + "args": { + "External id": 4056422,"kernel_hash": "cjd6g3jfgntyoifzno6l2urmnhif7alxtw6zz7miov66vywxwv7d", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/jd/cjd6g3jfgntyoifzno6l2urmnhif7alxtw6zz7miov66vywxwv7d.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[65536, 2048], [65536, 2048], []], "Ev Idx": 3429 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 1336756, "tid": 1381189, + "ts": 1655275168957.580, "dur": 67.365, + "args": { + "External id": 4056423,"kernel_hash": "cxhg545cyph4gbk5vymzyh72vho7oogk3ycan2lp4cxntklp5hew", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "65536", "2048", "1", "497", "132", "True", "2048", "True", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/xh/cxhg545cyph4gbk5vymzyh72vho7oogk3ycan2lp4cxntklp5hew.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [1], [2048, 1], [2048, 1], [2048, 1], [2048, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [2048], [65536, 2048], [65536, 2048], [132, 2048], [65536, 2048], [65536], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 3430 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 1336756, "tid": 1381189, + "ts": 1655275169048.430, "dur": 19.846, + "args": { + "External id": 4056424,"kernel_hash": "cu42i6zmxtvs2i7cs6x4ixaexke3lhgdiaye5oxwm7s3u6em6co4", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "66"], "kernel_file": "/tmp/torchinductor_cvm/u4/cu42i6zmxtvs2i7cs6x4ixaexke3lhgdiaye5oxwm7s3u6em6co4.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [4096, 1, 2048], [], []], "Input Dims": [[132, 2048], [1, 2048, 2], [], []], "Ev Idx": 3431 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 1336756, "tid": 1381189, + "ts": 1655275169081.280, "dur": 15.044, + "args": { + "External id": 4056425,"kernel_hash": "ckihofrorhmzazt2wfn2dz2m5wfx3auisu2gvfo2jsepr4zyekmq", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "2"], "kernel_file": "/tmp/torchinductor_cvm/ki/ckihofrorhmzazt2wfn2dz2m5wfx3auisu2gvfo2jsepr4zyekmq.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1, 2048], [2048, 1], [], []], "Input Dims": [[1, 2048, 2], [1, 2048], [], []], "Ev Idx": 3432 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275169104.709, "dur": 32.676, + "args": { + "External id": 4056426,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 3433 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275169140.494, "dur": 33.351, + "args": { + "External id": 4056427,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 3434 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 1336756, "tid": 1381189, + "ts": 1655275169221.867, "dur": 168.813, + "args": { + "External id": 4056428,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.125", "True", "-1", "-1", "0.", "", "False", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar", "long int"], "Input Strides": [[8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [131072, 4096, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 32, 4096], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 3435 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655275169298.572, "dur": 5.798, + "args": { + "External id": 4056429,"Record function id": 0, "Concrete Inputs": ["[16, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3436 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655275169306.681, "dur": 1.851, + "args": { + "External id": 4056430,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3437 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336756, "tid": 1381189, + "ts": 1655275169436.613, "dur": 27.718, + "args": { + "External id": 4056431,"kernel_hash": "cb6oumcqb462ndf2ivcd2sc6qg6mfjahptjw4ih7cesqhfpziv3b", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/b6/cb6oumcqb462ndf2ivcd2sc6qg6mfjahptjw4ih7cesqhfpziv3b.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 3438 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336756, "tid": 1381189, + "ts": 1655275169476.927, "dur": 14.481, + "args": { + "External id": 4056432,"kernel_hash": "cb6oumcqb462ndf2ivcd2sc6qg6mfjahptjw4ih7cesqhfpziv3b", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/b6/cb6oumcqb462ndf2ivcd2sc6qg6mfjahptjw4ih7cesqhfpziv3b.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 3439 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275169501.462, "dur": 39.257, + "args": { + "External id": 4056433,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 3440 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275169547.705, "dur": 34.465, + "args": { + "External id": 4056434,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 3441 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275169590.544, "dur": 20.631, + "args": { + "External id": 4056435,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 3442 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275169616.573, "dur": 30.441, + "args": { + "External id": 4056436,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 3443 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275169653.250, "dur": 20.769, + "args": { + "External id": 4056437,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 3444 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275169681.850, "dur": 29.851, + "args": { + "External id": 4056438,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 3445 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_4", "pid": 1336756, "tid": 1381189, + "ts": 1655275169744.958, "dur": 26.481, + "args": { + "External id": 4056439,"kernel_hash": "c7pqhdjojzeazwsh5g3ibnyk4m2nfh3q73e3zc7hljz4yvhe7c4h", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/7p/c7pqhdjojzeazwsh5g3ibnyk4m2nfh3q73e3zc7hljz4yvhe7c4h.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1], []], "Input Dims": [[65536, 2048], [65536, 2048], [65536, 2048], []], "Ev Idx": 3446 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_2", "pid": 1336756, "tid": 1381189, + "ts": 1655275169789.238, "dur": 22.613, + "args": { + "External id": 4056440,"kernel_hash": "cvgvwkysjpcw75q5t3guce5bep2so25f7i5zxc6ipt5f56shof73", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "65536", "2048", "1", "497", "132", "True", "2048", "False", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/vg/cvgvwkysjpcw75q5t3guce5bep2so25f7i5zxc6ipt5f56shof73.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [1], [2048, 1], [2048, 1], [2048, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [2048], [65536, 2048], [65536, 2048], [132, 2048], [65536], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 3447 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 1336756, "tid": 1381189, + "ts": 1655275169829.074, "dur": 17.567, + "args": { + "External id": 4056441,"kernel_hash": "cu42i6zmxtvs2i7cs6x4ixaexke3lhgdiaye5oxwm7s3u6em6co4", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "66"], "kernel_file": "/tmp/torchinductor_cvm/u4/cu42i6zmxtvs2i7cs6x4ixaexke3lhgdiaye5oxwm7s3u6em6co4.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [4096, 1, 2048], [], []], "Input Dims": [[132, 2048], [1, 2048, 2], [], []], "Ev Idx": 3448 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 1336756, "tid": 1381189, + "ts": 1655275169861.758, "dur": 14.419, + "args": { + "External id": 4056442,"kernel_hash": "ckihofrorhmzazt2wfn2dz2m5wfx3auisu2gvfo2jsepr4zyekmq", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "2"], "kernel_file": "/tmp/torchinductor_cvm/ki/ckihofrorhmzazt2wfn2dz2m5wfx3auisu2gvfo2jsepr4zyekmq.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1, 2048], [2048, 1], [], []], "Input Dims": [[1, 2048, 2], [1, 2048], [], []], "Ev Idx": 3449 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_5", "pid": 1336756, "tid": 1381189, + "ts": 1655275169891.568, "dur": 14.625, + "args": { + "External id": 4056443,"kernel_hash": "cckrpn5uuxyvbancoio3sz2onrjto236n54xx4ycphq5p6r3jlfj", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/ck/cckrpn5uuxyvbancoio3sz2onrjto236n54xx4ycphq5p6r3jlfj.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [8388608, 2048, 1], []], "Input Dims": [[65536, 2048], [65536, 2048], [16, 4096, 2048], []], "Ev Idx": 3450 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275169979.427, "dur": 57.582, + "args": { + "External id": 4056444,"Record function id": 0, "Ev Idx": 3451 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275169983.107, "dur": 52.154, + "args": { + "External id": 4056445,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 3452 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275170027.434, "dur": 6.662, + "args": { + "External id": 4056446,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 3453 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275170029.449, "dur": 4.300, + "args": { + "External id": 4056447,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 3454 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275170043.641, "dur": 8.629, + "args": { + "External id": 4056448,"Record function id": 0, "Ev Idx": 3455 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275170045.665, "dur": 6.137, + "args": { + "External id": 4056449,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 3456 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275170046.719, "dur": 4.507, + "args": { + "External id": 4056450,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 3457 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275170047.579, "dur": 3.583, + "args": { + "External id": 4056451,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 3458 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275170055.728, "dur": 5.114, + "args": { + "External id": 4056452,"Record function id": 0, "Ev Idx": 3459 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275170057.079, "dur": 3.294, + "args": { + "External id": 4056453,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 3460 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275170057.634, "dur": 2.314, + "args": { + "External id": 4056454,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 3461 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275170058.146, "dur": 1.728, + "args": { + "External id": 4056455,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 3462 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275170063.979, "dur": 4.622, + "args": { + "External id": 4056456,"Record function id": 0, "Ev Idx": 3463 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275170065.519, "dur": 2.623, + "args": { + "External id": 4056457,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 3464 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275170066.227, "dur": 1.497, + "args": { + "External id": 4056458,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 3465 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275170066.923, "dur": 0.741, + "args": { + "External id": 4056459,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 3466 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275170071.712, "dur": 3.819, + "args": { + "External id": 4056460,"Record function id": 0, "Ev Idx": 3467 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275170073.062, "dur": 2.067, + "args": { + "External id": 4056461,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 3468 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275170073.640, "dur": 1.088, + "args": { + "External id": 4056462,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 3469 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275170074.011, "dur": 0.645, + "args": { + "External id": 4056463,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 3470 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275170078.671, "dur": 4.525, + "args": { + "External id": 4056464,"Record function id": 0, "Ev Idx": 3471 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275170080.229, "dur": 2.499, + "args": { + "External id": 4056465,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 3472 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275170080.797, "dur": 1.508, + "args": { + "External id": 4056466,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 3473 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275170081.576, "dur": 0.628, + "args": { + "External id": 4056467,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 3474 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275170086.313, "dur": 3.850, + "args": { + "External id": 4056468,"Record function id": 0, "Ev Idx": 3475 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275170087.698, "dur": 2.029, + "args": { + "External id": 4056469,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 3476 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275170088.171, "dur": 1.163, + "args": { + "External id": 4056470,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 3477 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275170088.475, "dur": 0.767, + "args": { + "External id": 4056471,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 3478 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275170093.201, "dur": 3.844, + "args": { + "External id": 4056472,"Record function id": 0, "Ev Idx": 3479 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275170094.757, "dur": 1.864, + "args": { + "External id": 4056473,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 3480 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275170095.191, "dur": 1.033, + "args": { + "External id": 4056474,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 3481 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275170095.436, "dur": 0.682, + "args": { + "External id": 4056475,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 3482 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275170100.060, "dur": 5.698, + "args": { + "External id": 4056476,"Record function id": 0, "Ev Idx": 3483 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275170101.154, "dur": 4.149, + "args": { + "External id": 4056477,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 3484 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275170101.594, "dur": 3.203, + "args": { + "External id": 4056478,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 3485 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275170102.167, "dur": 2.516, + "args": { + "External id": 4056479,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 3486 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RegisterPostBackwardFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1655275170109.726, "dur": 37330.803, + "args": { + "External id": 4056480,"Record function id": 0, "Sequence number": 40618383, "Fwd thread id": 1, "Ev Idx": 3487 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1655275170111.137, "dur": 37318.959, + "args": { + "External id": 4056481,"Sequence number": 40618383, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 3488 + } + }, + { + "ph": "f", "id": 197, "pid": 1336756, "tid": 1381189, "ts": 1655275170111.137, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.15)", "pid": 1336756, "tid": 1381189, + "ts": 1655275170140.894, "dur": 37.348, + "args": { + "External id": 4056482,"Record function id": 0, "Ev Idx": 3489 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.15)", "pid": 1336756, "tid": 1381189, + "ts": 1655275170186.232, "dur": 59.372, + "args": { + "External id": 4056483,"Record function id": 0, "Ev Idx": 3490 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.15)", "pid": 1336756, "tid": 1381189, + "ts": 1655275170251.017, "dur": 37155.804, + "args": { + "External id": 4056484,"Record function id": 0, "Ev Idx": 3491 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655275170336.161, "dur": 6.832, + "args": { + "External id": 4056485,"Record function id": 0, "Concrete Inputs": ["[51384320]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3492 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275170352.637, "dur": 4.599, + "args": { + "External id": 4056486,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[51384320], []], "Ev Idx": 3493 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::chunk_cat", "pid": 1336756, "tid": 1381189, + "ts": 1655275170371.595, "dur": 36221.650, + "args": { + "External id": 4056487,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [2048, 1], [2048, 1], [2048, 1], [2048, 1], [1], [2048, 1], [2048, 1], [5632, 1]], [], [], [6423040, 1]], "Input Dims": [[[2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048], [5632, 2048], [5632, 2048], [2048, 5632]], [], [], [8, 6423040]], "Ev Idx": 3494 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_chunk_cat", "pid": 1336756, "tid": 1381189, + "ts": 1655275170384.480, "dur": 36198.128, + "args": { + "External id": 4056488,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [2048, 1], [2048, 1], [2048, 1], [2048, 1], [1], [2048, 1], [2048, 1], [5632, 1]], [], [], [6423040, 1]], "Input Dims": [[[2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048], [5632, 2048], [5632, 2048], [2048, 5632]], [], [], [8, 6423040]], "Ev Idx": 3495 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655275170450.298, "dur": 14.455, + "args": { + "External id": 4056489,"Record function id": 0, "Concrete Inputs": ["[12602]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3496 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1381189, + "ts": 1655275170471.613, "dur": 36069.209, + "args": { + "External id": 4056490,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[12602], [], [], [], [], [], [], []], "Ev Idx": 3497 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336756, "tid": 1381189, + "ts": 1655275170474.449, "dur": 36065.376, + "args": { + "External id": 4056491,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[12602], [], [], [], [], [], []], "Ev Idx": 3498 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275170478.691, "dur": 6.179, + "args": { + "External id": 4056492,"Record function id": 0, "Concrete Inputs": ["[12602]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3499 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1381189, + "ts": 1655275170486.780, "dur": 36048.795, + "args": { + "External id": 4056493,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[12602], [12602], []], "Ev Idx": 3500 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 1336756, "tid": 1381189, + "ts": 1655275206689.459, "dur": 10.560, + "args": { + "External id": 4056494,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "", "", "", "False"], "Input type": ["float", "ScalarList", "", "", "", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[51384320], [], [], [], [], []], "Ev Idx": 3501 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655275206693.038, "dur": 6.558, + "args": { + "External id": 4056495,"Record function id": 0, "Concrete Inputs": ["[6423040]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3502 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_reduce_scatter_base_", "pid": 1336756, "tid": 1381189, + "ts": 1655275206731.341, "dur": 379.354, + "args": { + "External id": 4056496,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "-1"], "Input type": ["float", "float", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], [], []], "Input Dims": [[6423040], [51384320], [], [], [], []], "Ev Idx": 3503 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336756, "tid": 1381189, + "ts": 1655275206759.667, "dur": 345.197, + "args": { + "External id": 4056497,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 3, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "3", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 6423040, "Process Group Name": "0", "Input type": ["float", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[51384320], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 3504, "In msg nelems": 51384320 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_reduce_scatter_base", "pid": 1336756, "tid": 1381189, + "ts": 1655275206771.158, "dur": 327.559, + "args": { + "External id": 4056498,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[51384320]], "Ev Idx": 3505 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336756, "tid": 1381189, + "ts": 1655275207131.173, "dur": 2.083, + "args": { + "External id": 4056499,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "3", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 3506, "In msg nelems": 0, "Rank": 3, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275207191.614, "dur": 6.861, + "args": { + "External id": 4056500,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3507 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275207244.584, "dur": 3.452, + "args": { + "External id": 4056501,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "256"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3508 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275207265.319, "dur": 1.012, + "args": { + "External id": 4056502,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "524544"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3509 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275207279.052, "dur": 1.030, + "args": { + "External id": 4056503,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "1048832"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3510 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275207292.293, "dur": 0.981, + "args": { + "External id": 4056504,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "1573120"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3511 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275207304.585, "dur": 2.698, + "args": { + "External id": 4056505,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3512 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275207320.367, "dur": 1.023, + "args": { + "External id": 4056506,"Record function id": 0, "Concrete Inputs": ["", "[704, 2048]", "[2048, 1]", "2097664"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3513 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275207333.372, "dur": 2.125, + "args": { + "External id": 4056507,"Record function id": 0, "Concrete Inputs": ["", "[704, 2048]", "[2048, 1]", "3539456"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3514 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275207346.478, "dur": 0.855, + "args": { + "External id": 4056508,"Record function id": 0, "Concrete Inputs": ["", "[256, 5632]", "[5632, 1]", "4981248"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3515 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: CompiledFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1655275207457.521, "dur": 2712.304, + "args": { + "External id": 4056509,"Record function id": 0, "Ev Idx": 3516 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.14)", "pid": 1336756, "tid": 1381189, + "ts": 1655275207478.624, "dur": 1006.228, + "args": { + "External id": 4056510,"Record function id": 0, "Ev Idx": 3517 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.14)", "pid": 1336756, "tid": 1381189, + "ts": 1655275207492.652, "dur": 317.898, + "args": { + "External id": 4056511,"Record function id": 0, "Ev Idx": 3518 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275207569.513, "dur": 6.530, + "args": { + "External id": 4056512,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[51384320], []], "Ev Idx": 3519 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275207579.490, "dur": 1.108, + "args": { + "External id": 4056513,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 3520 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275207582.467, "dur": 0.801, + "args": { + "External id": 4056514,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 3521 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275207584.976, "dur": 0.803, + "args": { + "External id": 4056515,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 3522 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275207587.343, "dur": 1.149, + "args": { + "External id": 4056516,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 3523 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275207590.597, "dur": 1.001, + "args": { + "External id": 4056517,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 3524 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275207593.225, "dur": 1.850, + "args": { + "External id": 4056518,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 3525 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275207596.765, "dur": 0.938, + "args": { + "External id": 4056519,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 3526 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275207599.108, "dur": 3.143, + "args": { + "External id": 4056520,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 3527 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275207603.661, "dur": 0.992, + "args": { + "External id": 4056521,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 3528 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 1336756, "tid": 1381189, + "ts": 1655275207623.377, "dur": 155.052, + "args": { + "External id": 4056522,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 3529 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 1336756, "tid": 1381189, + "ts": 1655275207639.079, "dur": 134.952, + "args": { + "External id": 4056523,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 3530 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655275207663.672, "dur": 12.199, + "args": { + "External id": 4056524,"Record function id": 0, "Concrete Inputs": ["[2133]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3531 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1381189, + "ts": 1655275207679.127, "dur": 67.505, + "args": { + "External id": 4056525,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], [], []], "Ev Idx": 3532 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336756, "tid": 1381189, + "ts": 1655275207682.040, "dur": 64.234, + "args": { + "External id": 4056526,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], []], "Ev Idx": 3533 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275207686.282, "dur": 5.665, + "args": { + "External id": 4056527,"Record function id": 0, "Concrete Inputs": ["[2133]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3534 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1381189, + "ts": 1655275207693.873, "dur": 51.885, + "args": { + "External id": 4056528,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[2133], [2133], []], "Ev Idx": 3535 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::backward_prefetch for model.layers.13", "pid": 1336756, "tid": 1381189, + "ts": 1655275207886.072, "dur": 590.345, + "args": { + "External id": 4056529,"Record function id": 0, "Ev Idx": 3536 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.13)", "pid": 1336756, "tid": 1381189, + "ts": 1655275207902.537, "dur": 560.855, + "args": { + "External id": 4056530,"Record function id": 0, "Ev Idx": 3537 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655275207953.226, "dur": 4.660, + "args": { + "External id": 4056531,"Record function id": 0, "Concrete Inputs": ["[6423040]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3538 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336756, "tid": 1381189, + "ts": 1655275207972.992, "dur": 69.479, + "args": { + "External id": 4056532,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 3539 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275207977.696, "dur": 1.462, + "args": { + "External id": 4056533,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3540 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275208018.223, "dur": 1.169, + "args": { + "External id": 4056534,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3541 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275208022.534, "dur": 0.483, + "args": { + "External id": 4056535,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3542 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275208024.779, "dur": 2.403, + "args": { + "External id": 4056536,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3543 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275208029.012, "dur": 0.544, + "args": { + "External id": 4056537,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3544 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275208031.506, "dur": 0.599, + "args": { + "External id": 4056538,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3545 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275208033.635, "dur": 0.483, + "args": { + "External id": 4056539,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3546 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275208035.642, "dur": 0.528, + "args": { + "External id": 4056540,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3547 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275208037.704, "dur": 0.463, + "args": { + "External id": 4056541,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3548 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336756, "tid": 1381189, + "ts": 1655275208052.469, "dur": 32.196, + "args": { + "External id": 4056542,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 3549 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 1336756, "tid": 1381189, + "ts": 1655275208118.480, "dur": 108.822, + "args": { + "External id": 4056543,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "6423040", "8", "3", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [], [], [], [], [], []], "Ev Idx": 3550 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655275208129.133, "dur": 4.084, + "args": { + "External id": 4056544,"Record function id": 0, "Concrete Inputs": ["[51384320]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3551 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 1336756, "tid": 1381189, + "ts": 1655275208144.182, "dur": 10.527, + "args": { + "External id": 4056545,"Record function id": 0, "Concrete Inputs": ["", "0", "19269120", "6423040"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 3552 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1381189, + "ts": 1655275208148.610, "dur": 5.677, + "args": { + "External id": 4056546,"Record function id": 0, "Concrete Inputs": ["", "0", "19269120", "25692160", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[51384320], [], [], [], []], "Ev Idx": 3553 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275208152.279, "dur": 0.505, + "args": { + "External id": 4056547,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "[1]", "19269120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 3554 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336756, "tid": 1381189, + "ts": 1655275208164.366, "dur": 25.343, + "args": { + "External id": 4056548,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 3555 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275208166.528, "dur": 2.787, + "args": { + "External id": 4056549,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "19269120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3556 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275208170.910, "dur": 0.483, + "args": { + "External id": 4056550,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "19269376"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3557 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275208172.819, "dur": 0.362, + "args": { + "External id": 4056551,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "19793664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3558 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275208174.569, "dur": 0.434, + "args": { + "External id": 4056552,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "20317952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3559 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275208176.754, "dur": 0.395, + "args": { + "External id": 4056553,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "20842240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3560 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275208178.814, "dur": 0.253, + "args": { + "External id": 4056554,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "21366528"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3561 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275208180.709, "dur": 0.359, + "args": { + "External id": 4056555,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "21366784"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3562 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275208182.394, "dur": 0.480, + "args": { + "External id": 4056556,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "22808576"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3563 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275208184.607, "dur": 1.882, + "args": { + "External id": 4056557,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "24250368"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3564 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336756, "tid": 1381189, + "ts": 1655275208200.559, "dur": 19.286, + "args": { + "External id": 4056558,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 3565 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 1336756, "tid": 1381189, + "ts": 1655275208273.754, "dur": 105.457, + "args": { + "External id": 4056559,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[51384320], [6423040], [], [], []], "Ev Idx": 3566 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336756, "tid": 1381189, + "ts": 1655275208294.554, "dur": 81.090, + "args": { + "External id": 4056560,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 3, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "3", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 51384320, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[6423040], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 3567, "In msg nelems": 6423040 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 1336756, "tid": 1381189, + "ts": 1655275208304.415, "dur": 67.105, + "args": { + "External id": 4056561,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[6423040]], "Ev Idx": 3568 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336756, "tid": 1381189, + "ts": 1655275208392.993, "dur": 1.812, + "args": { + "External id": 4056562,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "3", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 3569, "In msg nelems": 0, "Rank": 3, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1655275208492.008, "dur": 1659.787, + "args": { + "External id": 4056563,"Sequence number": 40618382, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 3570 + } + }, + { + "ph": "f", "id": 198, "pid": 1336756, "tid": 1381189, "ts": 1655275208492.008, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275208598.876, "dur": 104.693, + "args": { + "External id": 4056564,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [5632, 1], [5632, 1]], "Input Dims": [[65536, 2048], [2048, 5632], [65536, 5632]], "Ev Idx": 3571 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_add_mul_rsub_silu_0", "pid": 1336756, "tid": 1381189, + "ts": 1655275208740.520, "dur": 37.468, + "args": { + "External id": 4056565,"kernel_hash": "c2zszzsomz26dv2qwvmiurvgyrl5qxtyn6ocoqkdpzzhfzwqp5q6", "grid": "grid(369098752,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "369098752"], "kernel_file": "/tmp/torchinductor_cvm/2z/c2zszzsomz26dv2qwvmiurvgyrl5qxtyn6ocoqkdpzzhfzwqp5q6.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[5632, 1], [5632, 1], [5632, 1], [23068672, 5632, 1], [23068672, 5632, 1], [23068672, 5632, 1], []], "Input Dims": [[65536, 5632], [65536, 5632], [65536, 5632], [16, 4096, 5632], [16, 4096, 5632], [16, 4096, 5632], []], "Ev Idx": 3572 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 1336756, "tid": 1381189, + "ts": 1655275208797.443, "dur": 48.343, + "args": { + "External id": 4056566,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[0, 1, 2048], [0, 5632, 1], [11534336, 5632, 1]], "Input Dims": [[1, 2048, 65536], [1, 65536, 5632], [1, 2048, 5632]], "Ev Idx": 3573 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275208855.105, "dur": 32.743, + "args": { + "External id": 4056567,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 5632], [2048, 1], [2048, 1]], "Input Dims": [[5632, 65536], [65536, 2048], [5632, 2048]], "Ev Idx": 3574 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275208895.484, "dur": 47.060, + "args": { + "External id": 4056568,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 5632], [5632, 2048], [65536, 2048]], "Ev Idx": 3575 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275208950.209, "dur": 28.096, + "args": { + "External id": 4056569,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 5632], [2048, 1], [2048, 1]], "Input Dims": [[5632, 65536], [65536, 2048], [5632, 2048]], "Ev Idx": 3576 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275209032.475, "dur": 48.938, + "args": { + "External id": 4056570,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 5632], [5632, 2048], [65536, 2048]], "Ev Idx": 3577 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_1", "pid": 1336756, "tid": 1381189, + "ts": 1655275209106.492, "dur": 22.419, + "args": { + "External id": 4056571,"kernel_hash": "cjd6g3jfgntyoifzno6l2urmnhif7alxtw6zz7miov66vywxwv7d", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/jd/cjd6g3jfgntyoifzno6l2urmnhif7alxtw6zz7miov66vywxwv7d.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[65536, 2048], [65536, 2048], []], "Ev Idx": 3578 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 1336756, "tid": 1381189, + "ts": 1655275209146.771, "dur": 27.302, + "args": { + "External id": 4056572,"kernel_hash": "cxhg545cyph4gbk5vymzyh72vho7oogk3ycan2lp4cxntklp5hew", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "65536", "2048", "1", "497", "132", "True", "2048", "True", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/xh/cxhg545cyph4gbk5vymzyh72vho7oogk3ycan2lp4cxntklp5hew.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [1], [2048, 1], [2048, 1], [2048, 1], [2048, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [2048], [65536, 2048], [65536, 2048], [132, 2048], [65536, 2048], [65536], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 3579 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 1336756, "tid": 1381189, + "ts": 1655275209192.186, "dur": 18.957, + "args": { + "External id": 4056573,"kernel_hash": "cu42i6zmxtvs2i7cs6x4ixaexke3lhgdiaye5oxwm7s3u6em6co4", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "66"], "kernel_file": "/tmp/torchinductor_cvm/u4/cu42i6zmxtvs2i7cs6x4ixaexke3lhgdiaye5oxwm7s3u6em6co4.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [4096, 1, 2048], [], []], "Input Dims": [[132, 2048], [1, 2048, 2], [], []], "Ev Idx": 3580 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 1336756, "tid": 1381189, + "ts": 1655275209227.021, "dur": 13.591, + "args": { + "External id": 4056574,"kernel_hash": "ckihofrorhmzazt2wfn2dz2m5wfx3auisu2gvfo2jsepr4zyekmq", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "2"], "kernel_file": "/tmp/torchinductor_cvm/ki/ckihofrorhmzazt2wfn2dz2m5wfx3auisu2gvfo2jsepr4zyekmq.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1, 2048], [2048, 1], [], []], "Input Dims": [[1, 2048, 2], [1, 2048], [], []], "Ev Idx": 3581 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275209250.134, "dur": 27.917, + "args": { + "External id": 4056575,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 3582 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275209281.354, "dur": 32.390, + "args": { + "External id": 4056576,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 3583 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 1336756, "tid": 1381189, + "ts": 1655275209362.556, "dur": 194.777, + "args": { + "External id": 4056577,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.125", "True", "-1", "-1", "0.", "", "False", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar", "long int"], "Input Strides": [[8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [131072, 4096, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 32, 4096], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 3584 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655275209459.676, "dur": 6.634, + "args": { + "External id": 4056578,"Record function id": 0, "Concrete Inputs": ["[16, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3585 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655275209468.760, "dur": 1.828, + "args": { + "External id": 4056579,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3586 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336756, "tid": 1381189, + "ts": 1655275209590.647, "dur": 23.685, + "args": { + "External id": 4056580,"kernel_hash": "cb6oumcqb462ndf2ivcd2sc6qg6mfjahptjw4ih7cesqhfpziv3b", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/b6/cb6oumcqb462ndf2ivcd2sc6qg6mfjahptjw4ih7cesqhfpziv3b.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 3587 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336756, "tid": 1381189, + "ts": 1655275209625.627, "dur": 13.379, + "args": { + "External id": 4056581,"kernel_hash": "cb6oumcqb462ndf2ivcd2sc6qg6mfjahptjw4ih7cesqhfpziv3b", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/b6/cb6oumcqb462ndf2ivcd2sc6qg6mfjahptjw4ih7cesqhfpziv3b.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 3588 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275209651.855, "dur": 40.301, + "args": { + "External id": 4056582,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 3589 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275209700.982, "dur": 36.117, + "args": { + "External id": 4056583,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 3590 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275209744.345, "dur": 21.390, + "args": { + "External id": 4056584,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 3591 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275209771.717, "dur": 31.264, + "args": { + "External id": 4056585,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 3592 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275209809.495, "dur": 20.255, + "args": { + "External id": 4056586,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 3593 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275209838.688, "dur": 32.166, + "args": { + "External id": 4056587,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 3594 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_4", "pid": 1336756, "tid": 1381189, + "ts": 1655275209887.757, "dur": 22.470, + "args": { + "External id": 4056588,"kernel_hash": "c7pqhdjojzeazwsh5g3ibnyk4m2nfh3q73e3zc7hljz4yvhe7c4h", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/7p/c7pqhdjojzeazwsh5g3ibnyk4m2nfh3q73e3zc7hljz4yvhe7c4h.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1], []], "Input Dims": [[65536, 2048], [65536, 2048], [65536, 2048], []], "Ev Idx": 3595 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_2", "pid": 1336756, "tid": 1381189, + "ts": 1655275209948.772, "dur": 28.560, + "args": { + "External id": 4056589,"kernel_hash": "cvgvwkysjpcw75q5t3guce5bep2so25f7i5zxc6ipt5f56shof73", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "65536", "2048", "1", "497", "132", "True", "2048", "False", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/vg/cvgvwkysjpcw75q5t3guce5bep2so25f7i5zxc6ipt5f56shof73.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [1], [2048, 1], [2048, 1], [2048, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [2048], [65536, 2048], [65536, 2048], [132, 2048], [65536], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 3596 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 1336756, "tid": 1381189, + "ts": 1655275210032.849, "dur": 23.893, + "args": { + "External id": 4056590,"kernel_hash": "cu42i6zmxtvs2i7cs6x4ixaexke3lhgdiaye5oxwm7s3u6em6co4", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "66"], "kernel_file": "/tmp/torchinductor_cvm/u4/cu42i6zmxtvs2i7cs6x4ixaexke3lhgdiaye5oxwm7s3u6em6co4.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [4096, 1, 2048], [], []], "Input Dims": [[132, 2048], [1, 2048, 2], [], []], "Ev Idx": 3597 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 1336756, "tid": 1381189, + "ts": 1655275210076.221, "dur": 15.148, + "args": { + "External id": 4056591,"kernel_hash": "ckihofrorhmzazt2wfn2dz2m5wfx3auisu2gvfo2jsepr4zyekmq", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "2"], "kernel_file": "/tmp/torchinductor_cvm/ki/ckihofrorhmzazt2wfn2dz2m5wfx3auisu2gvfo2jsepr4zyekmq.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1, 2048], [2048, 1], [], []], "Input Dims": [[1, 2048, 2], [1, 2048], [], []], "Ev Idx": 3598 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_5", "pid": 1336756, "tid": 1381189, + "ts": 1655275210107.240, "dur": 15.719, + "args": { + "External id": 4056592,"kernel_hash": "cckrpn5uuxyvbancoio3sz2onrjto236n54xx4ycphq5p6r3jlfj", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/ck/cckrpn5uuxyvbancoio3sz2onrjto236n54xx4ycphq5p6r3jlfj.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [8388608, 2048, 1], []], "Input Dims": [[65536, 2048], [65536, 2048], [16, 4096, 2048], []], "Ev Idx": 3599 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275210192.558, "dur": 17.323, + "args": { + "External id": 4056593,"Record function id": 0, "Ev Idx": 3600 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275210195.795, "dur": 12.959, + "args": { + "External id": 4056594,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 3601 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275210200.035, "dur": 7.723, + "args": { + "External id": 4056595,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 3602 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275210201.596, "dur": 6.016, + "args": { + "External id": 4056596,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 3603 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275210213.636, "dur": 4.536, + "args": { + "External id": 4056597,"Record function id": 0, "Ev Idx": 3604 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275210214.827, "dur": 2.929, + "args": { + "External id": 4056598,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 3605 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275210215.594, "dur": 1.663, + "args": { + "External id": 4056599,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 3606 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275210216.210, "dur": 0.977, + "args": { + "External id": 4056600,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 3607 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275210221.345, "dur": 3.488, + "args": { + "External id": 4056601,"Record function id": 0, "Ev Idx": 3608 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275210222.333, "dur": 2.079, + "args": { + "External id": 4056602,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 3609 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275210222.801, "dur": 1.205, + "args": { + "External id": 4056603,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 3610 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275210223.163, "dur": 0.753, + "args": { + "External id": 4056604,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 3611 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275210227.936, "dur": 3.529, + "args": { + "External id": 4056605,"Record function id": 0, "Ev Idx": 3612 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275210228.878, "dur": 2.195, + "args": { + "External id": 4056606,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 3613 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275210229.364, "dur": 1.339, + "args": { + "External id": 4056607,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 3614 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275210229.859, "dur": 0.748, + "args": { + "External id": 4056608,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 3615 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275210234.455, "dur": 3.883, + "args": { + "External id": 4056609,"Record function id": 0, "Ev Idx": 3616 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275210235.714, "dur": 2.232, + "args": { + "External id": 4056610,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 3617 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275210236.350, "dur": 1.202, + "args": { + "External id": 4056611,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 3618 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275210236.800, "dur": 0.678, + "args": { + "External id": 4056612,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 3619 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275210241.429, "dur": 3.805, + "args": { + "External id": 4056613,"Record function id": 0, "Ev Idx": 3620 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275210242.460, "dur": 2.382, + "args": { + "External id": 4056614,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 3621 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275210243.192, "dur": 1.273, + "args": { + "External id": 4056615,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 3622 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275210243.672, "dur": 0.683, + "args": { + "External id": 4056616,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 3623 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275210248.362, "dur": 3.570, + "args": { + "External id": 4056617,"Record function id": 0, "Ev Idx": 3624 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275210249.474, "dur": 2.040, + "args": { + "External id": 4056618,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 3625 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275210249.899, "dur": 1.239, + "args": { + "External id": 4056619,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 3626 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275210250.413, "dur": 0.625, + "args": { + "External id": 4056620,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 3627 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275210254.934, "dur": 5.480, + "args": { + "External id": 4056621,"Record function id": 0, "Ev Idx": 3628 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275210255.897, "dur": 4.119, + "args": { + "External id": 4056622,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 3629 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275210256.512, "dur": 3.125, + "args": { + "External id": 4056623,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 3630 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275210256.762, "dur": 2.800, + "args": { + "External id": 4056624,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 3631 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275210263.460, "dur": 4.158, + "args": { + "External id": 4056625,"Record function id": 0, "Ev Idx": 3632 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275210264.524, "dur": 2.667, + "args": { + "External id": 4056626,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 3633 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275210264.996, "dur": 1.799, + "args": { + "External id": 4056627,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 3634 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275210265.870, "dur": 0.841, + "args": { + "External id": 4056628,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 3635 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RegisterPostBackwardFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1655275210271.440, "dur": 37437.046, + "args": { + "External id": 4056629,"Record function id": 0, "Sequence number": 40618381, "Fwd thread id": 1, "Ev Idx": 3636 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1655275210272.898, "dur": 37427.231, + "args": { + "External id": 4056630,"Sequence number": 40618381, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 3637 + } + }, + { + "ph": "f", "id": 199, "pid": 1336756, "tid": 1381189, "ts": 1655275210272.898, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.14)", "pid": 1336756, "tid": 1381189, + "ts": 1655275210303.546, "dur": 39.550, + "args": { + "External id": 4056631,"Record function id": 0, "Ev Idx": 3638 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.14)", "pid": 1336756, "tid": 1381189, + "ts": 1655275210351.053, "dur": 62.303, + "args": { + "External id": 4056632,"Record function id": 0, "Ev Idx": 3639 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.14)", "pid": 1336756, "tid": 1381189, + "ts": 1655275210437.781, "dur": 37253.529, + "args": { + "External id": 4056633,"Record function id": 0, "Ev Idx": 3640 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655275210527.751, "dur": 6.717, + "args": { + "External id": 4056634,"Record function id": 0, "Concrete Inputs": ["[51384320]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3641 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275210544.972, "dur": 5.304, + "args": { + "External id": 4056635,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[51384320], []], "Ev Idx": 3642 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::chunk_cat", "pid": 1336756, "tid": 1381189, + "ts": 1655275210564.305, "dur": 36292.768, + "args": { + "External id": 4056636,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [2048, 1], [2048, 1], [2048, 1], [2048, 1], [1], [2048, 1], [2048, 1], [5632, 1]], [], [], [6423040, 1]], "Input Dims": [[[2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048], [5632, 2048], [5632, 2048], [2048, 5632]], [], [], [8, 6423040]], "Ev Idx": 3643 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_chunk_cat", "pid": 1336756, "tid": 1381189, + "ts": 1655275210577.312, "dur": 36270.513, + "args": { + "External id": 4056637,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [2048, 1], [2048, 1], [2048, 1], [2048, 1], [1], [2048, 1], [2048, 1], [5632, 1]], [], [], [6423040, 1]], "Input Dims": [[[2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048], [5632, 2048], [5632, 2048], [2048, 5632]], [], [], [8, 6423040]], "Ev Idx": 3644 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655275210616.585, "dur": 12.957, + "args": { + "External id": 4056638,"Record function id": 0, "Concrete Inputs": ["[12602]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3645 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1381189, + "ts": 1655275210635.794, "dur": 36166.492, + "args": { + "External id": 4056639,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[12602], [], [], [], [], [], [], []], "Ev Idx": 3646 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336756, "tid": 1381189, + "ts": 1655275210638.640, "dur": 36162.923, + "args": { + "External id": 4056640,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[12602], [], [], [], [], [], []], "Ev Idx": 3647 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275210642.312, "dur": 5.242, + "args": { + "External id": 4056641,"Record function id": 0, "Concrete Inputs": ["[12602]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3648 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1381189, + "ts": 1655275210649.383, "dur": 36148.501, + "args": { + "External id": 4056642,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[12602], [12602], []], "Ev Idx": 3649 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 1336756, "tid": 1381189, + "ts": 1655275246945.976, "dur": 9.077, + "args": { + "External id": 4056643,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "", "", "", "False"], "Input type": ["float", "ScalarList", "", "", "", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[51384320], [], [], [], [], []], "Ev Idx": 3650 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655275246949.378, "dur": 5.262, + "args": { + "External id": 4056644,"Record function id": 0, "Concrete Inputs": ["[6423040]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3651 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_reduce_scatter_base_", "pid": 1336756, "tid": 1381189, + "ts": 1655275247011.551, "dur": 364.148, + "args": { + "External id": 4056645,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "-1"], "Input type": ["float", "float", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], [], []], "Input Dims": [[6423040], [51384320], [], [], [], []], "Ev Idx": 3652 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336756, "tid": 1381189, + "ts": 1655275247037.904, "dur": 332.152, + "args": { + "External id": 4056646,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 3, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "3", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 6423040, "Process Group Name": "0", "Input type": ["float", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[51384320], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 3653, "In msg nelems": 51384320 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_reduce_scatter_base", "pid": 1336756, "tid": 1381189, + "ts": 1655275247050.423, "dur": 313.940, + "args": { + "External id": 4056647,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[51384320]], "Ev Idx": 3654 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336756, "tid": 1381189, + "ts": 1655275247397.328, "dur": 2.291, + "args": { + "External id": 4056648,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "3", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 3655, "In msg nelems": 0, "Rank": 3, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275247478.021, "dur": 7.275, + "args": { + "External id": 4056649,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3656 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275247534.936, "dur": 1.412, + "args": { + "External id": 4056650,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "256"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3657 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275247552.305, "dur": 0.937, + "args": { + "External id": 4056651,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "524544"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3658 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275247565.343, "dur": 1.040, + "args": { + "External id": 4056652,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "1048832"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3659 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275247578.558, "dur": 1.037, + "args": { + "External id": 4056653,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "1573120"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3660 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275247592.188, "dur": 1.266, + "args": { + "External id": 4056654,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3661 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275247603.821, "dur": 1.030, + "args": { + "External id": 4056655,"Record function id": 0, "Concrete Inputs": ["", "[704, 2048]", "[2048, 1]", "2097664"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3662 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275247615.777, "dur": 1.801, + "args": { + "External id": 4056656,"Record function id": 0, "Concrete Inputs": ["", "[704, 2048]", "[2048, 1]", "3539456"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3663 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275247627.971, "dur": 0.775, + "args": { + "External id": 4056657,"Record function id": 0, "Concrete Inputs": ["", "[256, 5632]", "[5632, 1]", "4981248"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3664 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: CompiledFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1655275247724.766, "dur": 2730.890, + "args": { + "External id": 4056658,"Record function id": 0, "Ev Idx": 3665 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.13)", "pid": 1336756, "tid": 1381189, + "ts": 1655275247745.243, "dur": 1003.883, + "args": { + "External id": 4056659,"Record function id": 0, "Ev Idx": 3666 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.13)", "pid": 1336756, "tid": 1381189, + "ts": 1655275247760.424, "dur": 354.753, + "args": { + "External id": 4056660,"Record function id": 0, "Ev Idx": 3667 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275247834.698, "dur": 3.925, + "args": { + "External id": 4056661,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[51384320], []], "Ev Idx": 3668 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275247841.661, "dur": 0.925, + "args": { + "External id": 4056662,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 3669 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275247844.183, "dur": 1.336, + "args": { + "External id": 4056663,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 3670 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275247846.776, "dur": 0.824, + "args": { + "External id": 4056664,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 3671 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275247848.931, "dur": 0.632, + "args": { + "External id": 4056665,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 3672 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275247851.356, "dur": 0.963, + "args": { + "External id": 4056666,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 3673 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275247853.747, "dur": 1.647, + "args": { + "External id": 4056667,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 3674 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275247856.803, "dur": 2.502, + "args": { + "External id": 4056668,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 3675 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275247860.461, "dur": 0.821, + "args": { + "External id": 4056669,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 3676 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275247862.880, "dur": 0.692, + "args": { + "External id": 4056670,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 3677 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 1336756, "tid": 1381189, + "ts": 1655275247882.454, "dur": 194.651, + "args": { + "External id": 4056671,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 3678 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 1336756, "tid": 1381189, + "ts": 1655275247897.689, "dur": 174.228, + "args": { + "External id": 4056672,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 3679 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655275247921.259, "dur": 13.049, + "args": { + "External id": 4056673,"Record function id": 0, "Concrete Inputs": ["[2133]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3680 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1381189, + "ts": 1655275247937.635, "dur": 104.414, + "args": { + "External id": 4056674,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], [], []], "Ev Idx": 3681 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336756, "tid": 1381189, + "ts": 1655275247940.184, "dur": 101.474, + "args": { + "External id": 4056675,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], []], "Ev Idx": 3682 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275247944.263, "dur": 5.268, + "args": { + "External id": 4056676,"Record function id": 0, "Concrete Inputs": ["[2133]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3683 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1381189, + "ts": 1655275247951.332, "dur": 88.785, + "args": { + "External id": 4056677,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[2133], [2133], []], "Ev Idx": 3684 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::backward_prefetch for model.layers.12", "pid": 1336756, "tid": 1381189, + "ts": 1655275248194.040, "dur": 546.292, + "args": { + "External id": 4056678,"Record function id": 0, "Ev Idx": 3685 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.12)", "pid": 1336756, "tid": 1381189, + "ts": 1655275248213.357, "dur": 513.991, + "args": { + "External id": 4056679,"Record function id": 0, "Ev Idx": 3686 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655275248267.895, "dur": 6.051, + "args": { + "External id": 4056680,"Record function id": 0, "Concrete Inputs": ["[6423040]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3687 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336756, "tid": 1381189, + "ts": 1655275248289.408, "dur": 28.135, + "args": { + "External id": 4056681,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 3688 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275248293.988, "dur": 1.450, + "args": { + "External id": 4056682,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3689 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275248297.526, "dur": 0.410, + "args": { + "External id": 4056683,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3690 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275248299.516, "dur": 2.173, + "args": { + "External id": 4056684,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3691 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275248303.136, "dur": 0.383, + "args": { + "External id": 4056685,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3692 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275248305.291, "dur": 0.378, + "args": { + "External id": 4056686,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3693 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275248307.440, "dur": 0.349, + "args": { + "External id": 4056687,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3694 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275248309.117, "dur": 0.402, + "args": { + "External id": 4056688,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3695 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275248310.930, "dur": 0.489, + "args": { + "External id": 4056689,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3696 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275248313.055, "dur": 0.317, + "args": { + "External id": 4056690,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3697 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336756, "tid": 1381189, + "ts": 1655275248327.716, "dur": 28.818, + "args": { + "External id": 4056691,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 3698 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 1336756, "tid": 1381189, + "ts": 1655275248387.382, "dur": 121.500, + "args": { + "External id": 4056692,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "6423040", "8", "3", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [], [], [], [], [], []], "Ev Idx": 3699 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655275248397.537, "dur": 4.388, + "args": { + "External id": 4056693,"Record function id": 0, "Concrete Inputs": ["[51384320]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3700 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 1336756, "tid": 1381189, + "ts": 1655275248407.139, "dur": 30.330, + "args": { + "External id": 4056694,"Record function id": 0, "Concrete Inputs": ["", "0", "19269120", "6423040"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 3701 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1381189, + "ts": 1655275248411.625, "dur": 25.412, + "args": { + "External id": 4056695,"Record function id": 0, "Concrete Inputs": ["", "0", "19269120", "25692160", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[51384320], [], [], [], []], "Ev Idx": 3702 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275248432.413, "dur": 2.697, + "args": { + "External id": 4056696,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "[1]", "19269120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 3703 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336756, "tid": 1381189, + "ts": 1655275248446.168, "dur": 23.502, + "args": { + "External id": 4056697,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 3704 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275248448.739, "dur": 0.434, + "args": { + "External id": 4056698,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "19269120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3705 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275248450.920, "dur": 0.492, + "args": { + "External id": 4056699,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "19269376"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3706 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275248453.002, "dur": 0.468, + "args": { + "External id": 4056700,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "19793664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3707 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275248455.016, "dur": 0.488, + "args": { + "External id": 4056701,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "20317952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3708 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275248457.001, "dur": 0.436, + "args": { + "External id": 4056702,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "20842240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3709 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275248458.904, "dur": 0.392, + "args": { + "External id": 4056703,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "21366528"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3710 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275248460.925, "dur": 0.365, + "args": { + "External id": 4056704,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "21366784"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3711 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275248462.709, "dur": 2.026, + "args": { + "External id": 4056705,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "22808576"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3712 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275248465.990, "dur": 0.443, + "args": { + "External id": 4056706,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "24250368"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3713 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336756, "tid": 1381189, + "ts": 1655275248479.437, "dur": 21.919, + "args": { + "External id": 4056707,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 3714 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 1336756, "tid": 1381189, + "ts": 1655275248558.329, "dur": 106.069, + "args": { + "External id": 4056708,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[51384320], [6423040], [], [], []], "Ev Idx": 3715 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336756, "tid": 1381189, + "ts": 1655275248578.770, "dur": 81.876, + "args": { + "External id": 4056709,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 3, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "3", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 51384320, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[6423040], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 3716, "In msg nelems": 6423040 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 1336756, "tid": 1381189, + "ts": 1655275248588.537, "dur": 67.545, + "args": { + "External id": 4056710,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[6423040]], "Ev Idx": 3717 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336756, "tid": 1381189, + "ts": 1655275248677.728, "dur": 1.730, + "args": { + "External id": 4056711,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "3", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 3718, "In msg nelems": 0, "Rank": 3, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1655275248756.196, "dur": 1678.853, + "args": { + "External id": 4056712,"Sequence number": 40618380, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 3719 + } + }, + { + "ph": "f", "id": 200, "pid": 1336756, "tid": 1381189, "ts": 1655275248756.196, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275248861.906, "dur": 102.518, + "args": { + "External id": 4056713,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [5632, 1], [5632, 1]], "Input Dims": [[65536, 2048], [2048, 5632], [65536, 5632]], "Ev Idx": 3720 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_add_mul_rsub_silu_0", "pid": 1336756, "tid": 1381189, + "ts": 1655275249045.652, "dur": 41.207, + "args": { + "External id": 4056714,"kernel_hash": "c2zszzsomz26dv2qwvmiurvgyrl5qxtyn6ocoqkdpzzhfzwqp5q6", "grid": "grid(369098752,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "369098752"], "kernel_file": "/tmp/torchinductor_cvm/2z/c2zszzsomz26dv2qwvmiurvgyrl5qxtyn6ocoqkdpzzhfzwqp5q6.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[5632, 1], [5632, 1], [5632, 1], [23068672, 5632, 1], [23068672, 5632, 1], [23068672, 5632, 1], []], "Input Dims": [[65536, 5632], [65536, 5632], [65536, 5632], [16, 4096, 5632], [16, 4096, 5632], [16, 4096, 5632], []], "Ev Idx": 3721 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 1336756, "tid": 1381189, + "ts": 1655275249109.528, "dur": 57.755, + "args": { + "External id": 4056715,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[0, 1, 2048], [0, 5632, 1], [11534336, 5632, 1]], "Input Dims": [[1, 2048, 65536], [1, 65536, 5632], [1, 2048, 5632]], "Ev Idx": 3722 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275249177.835, "dur": 33.733, + "args": { + "External id": 4056716,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 5632], [2048, 1], [2048, 1]], "Input Dims": [[5632, 65536], [65536, 2048], [5632, 2048]], "Ev Idx": 3723 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275249219.444, "dur": 46.631, + "args": { + "External id": 4056717,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 5632], [5632, 2048], [65536, 2048]], "Ev Idx": 3724 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275249273.516, "dur": 29.092, + "args": { + "External id": 4056718,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 5632], [2048, 1], [2048, 1]], "Input Dims": [[5632, 65536], [65536, 2048], [5632, 2048]], "Ev Idx": 3725 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275249311.584, "dur": 44.164, + "args": { + "External id": 4056719,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 5632], [5632, 2048], [65536, 2048]], "Ev Idx": 3726 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_1", "pid": 1336756, "tid": 1381189, + "ts": 1655275249378.574, "dur": 21.602, + "args": { + "External id": 4056720,"kernel_hash": "cjd6g3jfgntyoifzno6l2urmnhif7alxtw6zz7miov66vywxwv7d", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/jd/cjd6g3jfgntyoifzno6l2urmnhif7alxtw6zz7miov66vywxwv7d.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[65536, 2048], [65536, 2048], []], "Ev Idx": 3727 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 1336756, "tid": 1381189, + "ts": 1655275249434.816, "dur": 29.474, + "args": { + "External id": 4056721,"kernel_hash": "cxhg545cyph4gbk5vymzyh72vho7oogk3ycan2lp4cxntklp5hew", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "65536", "2048", "1", "497", "132", "True", "2048", "True", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/xh/cxhg545cyph4gbk5vymzyh72vho7oogk3ycan2lp4cxntklp5hew.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [1], [2048, 1], [2048, 1], [2048, 1], [2048, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [2048], [65536, 2048], [65536, 2048], [132, 2048], [65536, 2048], [65536], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 3728 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 1336756, "tid": 1381189, + "ts": 1655275249486.331, "dur": 18.607, + "args": { + "External id": 4056722,"kernel_hash": "cu42i6zmxtvs2i7cs6x4ixaexke3lhgdiaye5oxwm7s3u6em6co4", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "66"], "kernel_file": "/tmp/torchinductor_cvm/u4/cu42i6zmxtvs2i7cs6x4ixaexke3lhgdiaye5oxwm7s3u6em6co4.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [4096, 1, 2048], [], []], "Input Dims": [[132, 2048], [1, 2048, 2], [], []], "Ev Idx": 3729 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 1336756, "tid": 1381189, + "ts": 1655275249519.255, "dur": 14.482, + "args": { + "External id": 4056723,"kernel_hash": "ckihofrorhmzazt2wfn2dz2m5wfx3auisu2gvfo2jsepr4zyekmq", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "2"], "kernel_file": "/tmp/torchinductor_cvm/ki/ckihofrorhmzazt2wfn2dz2m5wfx3auisu2gvfo2jsepr4zyekmq.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1, 2048], [2048, 1], [], []], "Input Dims": [[1, 2048, 2], [1, 2048], [], []], "Ev Idx": 3730 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275249544.443, "dur": 32.657, + "args": { + "External id": 4056724,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 3731 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275249580.523, "dur": 33.950, + "args": { + "External id": 4056725,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 3732 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 1336756, "tid": 1381189, + "ts": 1655275249642.154, "dur": 166.131, + "args": { + "External id": 4056726,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.125", "True", "-1", "-1", "0.", "", "False", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar", "long int"], "Input Strides": [[8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [131072, 4096, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 32, 4096], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 3733 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655275249717.493, "dur": 6.255, + "args": { + "External id": 4056727,"Record function id": 0, "Concrete Inputs": ["[16, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3734 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655275249725.621, "dur": 2.013, + "args": { + "External id": 4056728,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3735 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336756, "tid": 1381189, + "ts": 1655275249839.650, "dur": 24.364, + "args": { + "External id": 4056729,"kernel_hash": "cb6oumcqb462ndf2ivcd2sc6qg6mfjahptjw4ih7cesqhfpziv3b", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/b6/cb6oumcqb462ndf2ivcd2sc6qg6mfjahptjw4ih7cesqhfpziv3b.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 3736 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336756, "tid": 1381189, + "ts": 1655275249895.840, "dur": 14.809, + "args": { + "External id": 4056730,"kernel_hash": "cb6oumcqb462ndf2ivcd2sc6qg6mfjahptjw4ih7cesqhfpziv3b", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/b6/cb6oumcqb462ndf2ivcd2sc6qg6mfjahptjw4ih7cesqhfpziv3b.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 3737 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275249921.931, "dur": 37.189, + "args": { + "External id": 4056731,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 3738 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275249966.139, "dur": 77.024, + "args": { + "External id": 4056732,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 3739 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275250054.329, "dur": 25.327, + "args": { + "External id": 4056733,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 3740 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275250085.654, "dur": 31.699, + "args": { + "External id": 4056734,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 3741 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275250125.455, "dur": 20.286, + "args": { + "External id": 4056735,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 3742 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275250153.400, "dur": 30.710, + "args": { + "External id": 4056736,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 3743 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_4", "pid": 1336756, "tid": 1381189, + "ts": 1655275250216.830, "dur": 32.515, + "args": { + "External id": 4056737,"kernel_hash": "c7pqhdjojzeazwsh5g3ibnyk4m2nfh3q73e3zc7hljz4yvhe7c4h", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/7p/c7pqhdjojzeazwsh5g3ibnyk4m2nfh3q73e3zc7hljz4yvhe7c4h.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1], []], "Input Dims": [[65536, 2048], [65536, 2048], [65536, 2048], []], "Ev Idx": 3744 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_2", "pid": 1336756, "tid": 1381189, + "ts": 1655275250267.571, "dur": 25.796, + "args": { + "External id": 4056738,"kernel_hash": "cvgvwkysjpcw75q5t3guce5bep2so25f7i5zxc6ipt5f56shof73", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "65536", "2048", "1", "497", "132", "True", "2048", "False", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/vg/cvgvwkysjpcw75q5t3guce5bep2so25f7i5zxc6ipt5f56shof73.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [1], [2048, 1], [2048, 1], [2048, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [2048], [65536, 2048], [65536, 2048], [132, 2048], [65536], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 3745 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 1336756, "tid": 1381189, + "ts": 1655275250306.992, "dur": 16.566, + "args": { + "External id": 4056739,"kernel_hash": "cu42i6zmxtvs2i7cs6x4ixaexke3lhgdiaye5oxwm7s3u6em6co4", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "66"], "kernel_file": "/tmp/torchinductor_cvm/u4/cu42i6zmxtvs2i7cs6x4ixaexke3lhgdiaye5oxwm7s3u6em6co4.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [4096, 1, 2048], [], []], "Input Dims": [[132, 2048], [1, 2048, 2], [], []], "Ev Idx": 3746 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 1336756, "tid": 1381189, + "ts": 1655275250340.489, "dur": 14.727, + "args": { + "External id": 4056740,"kernel_hash": "ckihofrorhmzazt2wfn2dz2m5wfx3auisu2gvfo2jsepr4zyekmq", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "2"], "kernel_file": "/tmp/torchinductor_cvm/ki/ckihofrorhmzazt2wfn2dz2m5wfx3auisu2gvfo2jsepr4zyekmq.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1, 2048], [2048, 1], [], []], "Input Dims": [[1, 2048, 2], [1, 2048], [], []], "Ev Idx": 3747 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_5", "pid": 1336756, "tid": 1381189, + "ts": 1655275250368.040, "dur": 18.354, + "args": { + "External id": 4056741,"kernel_hash": "cckrpn5uuxyvbancoio3sz2onrjto236n54xx4ycphq5p6r3jlfj", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/ck/cckrpn5uuxyvbancoio3sz2onrjto236n54xx4ycphq5p6r3jlfj.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [8388608, 2048, 1], []], "Input Dims": [[65536, 2048], [65536, 2048], [16, 4096, 2048], []], "Ev Idx": 3748 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275250478.874, "dur": 15.470, + "args": { + "External id": 4056742,"Record function id": 0, "Ev Idx": 3749 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275250482.087, "dur": 11.339, + "args": { + "External id": 4056743,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 3750 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275250486.216, "dur": 6.304, + "args": { + "External id": 4056744,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 3751 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275250488.140, "dur": 4.258, + "args": { + "External id": 4056745,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 3752 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275250498.102, "dur": 4.436, + "args": { + "External id": 4056746,"Record function id": 0, "Ev Idx": 3753 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275250499.372, "dur": 2.739, + "args": { + "External id": 4056747,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 3754 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275250499.933, "dur": 1.700, + "args": { + "External id": 4056748,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 3755 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275250500.657, "dur": 0.882, + "args": { + "External id": 4056749,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 3756 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275250505.727, "dur": 4.101, + "args": { + "External id": 4056750,"Record function id": 0, "Ev Idx": 3757 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275250507.088, "dur": 2.345, + "args": { + "External id": 4056751,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 3758 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275250507.651, "dur": 1.340, + "args": { + "External id": 4056752,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 3759 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275250507.954, "dur": 0.938, + "args": { + "External id": 4056753,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 3760 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275250512.920, "dur": 3.848, + "args": { + "External id": 4056754,"Record function id": 0, "Ev Idx": 3761 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275250514.031, "dur": 2.349, + "args": { + "External id": 4056755,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 3762 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275250514.644, "dur": 1.324, + "args": { + "External id": 4056756,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 3763 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275250515.008, "dur": 0.891, + "args": { + "External id": 4056757,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 3764 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275250519.870, "dur": 3.526, + "args": { + "External id": 4056758,"Record function id": 0, "Ev Idx": 3765 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275250521.054, "dur": 1.924, + "args": { + "External id": 4056759,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 3766 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275250521.555, "dur": 1.005, + "args": { + "External id": 4056760,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 3767 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275250521.835, "dur": 0.651, + "args": { + "External id": 4056761,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 3768 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275250526.464, "dur": 3.623, + "args": { + "External id": 4056762,"Record function id": 0, "Ev Idx": 3769 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275250527.534, "dur": 2.156, + "args": { + "External id": 4056763,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 3770 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275250527.967, "dur": 1.231, + "args": { + "External id": 4056764,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 3771 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275250528.487, "dur": 0.587, + "args": { + "External id": 4056765,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 3772 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275250533.298, "dur": 5.193, + "args": { + "External id": 4056766,"Record function id": 0, "Ev Idx": 3773 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275250534.200, "dur": 3.885, + "args": { + "External id": 4056767,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 3774 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275250534.636, "dur": 3.001, + "args": { + "External id": 4056768,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 3775 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275250534.926, "dur": 2.625, + "args": { + "External id": 4056769,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 3776 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275250541.615, "dur": 3.449, + "args": { + "External id": 4056770,"Record function id": 0, "Ev Idx": 3777 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275250542.606, "dur": 2.029, + "args": { + "External id": 4056771,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 3778 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275250543.096, "dur": 1.115, + "args": { + "External id": 4056772,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 3779 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275250543.381, "dur": 0.734, + "args": { + "External id": 4056773,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 3780 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275250547.998, "dur": 3.760, + "args": { + "External id": 4056774,"Record function id": 0, "Ev Idx": 3781 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275250549.206, "dur": 2.165, + "args": { + "External id": 4056775,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 3782 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275250549.648, "dur": 1.263, + "args": { + "External id": 4056776,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 3783 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275250550.228, "dur": 0.593, + "args": { + "External id": 4056777,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 3784 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RegisterPostBackwardFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1655275250555.153, "dur": 36660.077, + "args": { + "External id": 4056778,"Record function id": 0, "Sequence number": 40618379, "Fwd thread id": 1, "Ev Idx": 3785 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1655275250556.319, "dur": 36649.909, + "args": { + "External id": 4056779,"Sequence number": 40618379, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 3786 + } + }, + { + "ph": "f", "id": 201, "pid": 1336756, "tid": 1381189, "ts": 1655275250556.319, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.13)", "pid": 1336756, "tid": 1381189, + "ts": 1655275250588.219, "dur": 37.741, + "args": { + "External id": 4056780,"Record function id": 0, "Ev Idx": 3787 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.13)", "pid": 1336756, "tid": 1381189, + "ts": 1655275250633.683, "dur": 61.904, + "args": { + "External id": 4056781,"Record function id": 0, "Ev Idx": 3788 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.13)", "pid": 1336756, "tid": 1381189, + "ts": 1655275250701.448, "dur": 36496.282, + "args": { + "External id": 4056782,"Record function id": 0, "Ev Idx": 3789 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655275250787.401, "dur": 6.371, + "args": { + "External id": 4056783,"Record function id": 0, "Concrete Inputs": ["[51384320]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3790 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275250803.476, "dur": 4.748, + "args": { + "External id": 4056784,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[51384320], []], "Ev Idx": 3791 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::chunk_cat", "pid": 1336756, "tid": 1381189, + "ts": 1655275250822.401, "dur": 35516.963, + "args": { + "External id": 4056785,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [2048, 1], [2048, 1], [2048, 1], [2048, 1], [1], [2048, 1], [2048, 1], [5632, 1]], [], [], [6423040, 1]], "Input Dims": [[[2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048], [5632, 2048], [5632, 2048], [2048, 5632]], [], [], [8, 6423040]], "Ev Idx": 3792 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_chunk_cat", "pid": 1336756, "tid": 1381189, + "ts": 1655275250835.339, "dur": 35495.182, + "args": { + "External id": 4056786,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [2048, 1], [2048, 1], [2048, 1], [2048, 1], [1], [2048, 1], [2048, 1], [5632, 1]], [], [], [6423040, 1]], "Input Dims": [[[2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048], [5632, 2048], [5632, 2048], [2048, 5632]], [], [], [8, 6423040]], "Ev Idx": 3793 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655275250874.924, "dur": 12.896, + "args": { + "External id": 4056787,"Record function id": 0, "Concrete Inputs": ["[12602]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3794 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1381189, + "ts": 1655275250894.285, "dur": 35398.050, + "args": { + "External id": 4056788,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[12602], [], [], [], [], [], [], []], "Ev Idx": 3795 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336756, "tid": 1381189, + "ts": 1655275250896.926, "dur": 35394.747, + "args": { + "External id": 4056789,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[12602], [], [], [], [], [], []], "Ev Idx": 3796 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275250901.027, "dur": 5.350, + "args": { + "External id": 4056790,"Record function id": 0, "Concrete Inputs": ["[12602]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3797 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1381189, + "ts": 1655275250908.343, "dur": 35379.317, + "args": { + "External id": 4056791,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[12602], [12602], []], "Ev Idx": 3798 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 1336756, "tid": 1381189, + "ts": 1655275286438.429, "dur": 9.596, + "args": { + "External id": 4056792,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "", "", "", "False"], "Input type": ["float", "ScalarList", "", "", "", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[51384320], [], [], [], [], []], "Ev Idx": 3799 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655275286441.926, "dur": 5.569, + "args": { + "External id": 4056793,"Record function id": 0, "Concrete Inputs": ["[6423040]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3800 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_reduce_scatter_base_", "pid": 1336756, "tid": 1381189, + "ts": 1655275286478.903, "dur": 385.087, + "args": { + "External id": 4056794,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "-1"], "Input type": ["float", "float", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], [], []], "Input Dims": [[6423040], [51384320], [], [], [], []], "Ev Idx": 3801 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336756, "tid": 1381189, + "ts": 1655275286504.198, "dur": 354.601, + "args": { + "External id": 4056795,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 3, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "3", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 6423040, "Process Group Name": "0", "Input type": ["float", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[51384320], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 3802, "In msg nelems": 51384320 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_reduce_scatter_base", "pid": 1336756, "tid": 1381189, + "ts": 1655275286515.877, "dur": 337.853, + "args": { + "External id": 4056796,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[51384320]], "Ev Idx": 3803 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336756, "tid": 1381189, + "ts": 1655275286883.208, "dur": 2.326, + "args": { + "External id": 4056797,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "3", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 3804, "In msg nelems": 0, "Rank": 3, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275286945.674, "dur": 8.710, + "args": { + "External id": 4056798,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3805 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275287035.388, "dur": 2.119, + "args": { + "External id": 4056799,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "256"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3806 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275287054.421, "dur": 1.106, + "args": { + "External id": 4056800,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "524544"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3807 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275287067.441, "dur": 0.935, + "args": { + "External id": 4056801,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "1048832"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3808 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275287080.231, "dur": 2.937, + "args": { + "External id": 4056802,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "1573120"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3809 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275287093.392, "dur": 1.044, + "args": { + "External id": 4056803,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3810 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275287105.084, "dur": 0.887, + "args": { + "External id": 4056804,"Record function id": 0, "Concrete Inputs": ["", "[704, 2048]", "[2048, 1]", "2097664"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3811 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275287117.253, "dur": 2.010, + "args": { + "External id": 4056805,"Record function id": 0, "Concrete Inputs": ["", "[704, 2048]", "[2048, 1]", "3539456"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3812 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275287130.754, "dur": 2.849, + "args": { + "External id": 4056806,"Record function id": 0, "Concrete Inputs": ["", "[256, 5632]", "[5632, 1]", "4981248"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3813 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: CompiledFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1655275287231.406, "dur": 2644.464, + "args": { + "External id": 4056807,"Record function id": 0, "Ev Idx": 3814 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.12)", "pid": 1336756, "tid": 1381189, + "ts": 1655275287250.483, "dur": 1006.845, + "args": { + "External id": 4056808,"Record function id": 0, "Ev Idx": 3815 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.12)", "pid": 1336756, "tid": 1381189, + "ts": 1655275287264.278, "dur": 334.661, + "args": { + "External id": 4056809,"Record function id": 0, "Ev Idx": 3816 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275287338.718, "dur": 4.064, + "args": { + "External id": 4056810,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[51384320], []], "Ev Idx": 3817 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275287345.890, "dur": 0.927, + "args": { + "External id": 4056811,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 3818 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275287348.790, "dur": 0.902, + "args": { + "External id": 4056812,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 3819 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275287351.324, "dur": 1.012, + "args": { + "External id": 4056813,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 3820 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275287353.903, "dur": 1.115, + "args": { + "External id": 4056814,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 3821 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275287356.904, "dur": 0.686, + "args": { + "External id": 4056815,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 3822 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275287359.070, "dur": 3.904, + "args": { + "External id": 4056816,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 3823 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275287364.647, "dur": 0.936, + "args": { + "External id": 4056817,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 3824 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275287367.033, "dur": 0.878, + "args": { + "External id": 4056818,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 3825 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275287369.101, "dur": 0.890, + "args": { + "External id": 4056819,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 3826 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 1336756, "tid": 1381189, + "ts": 1655275287388.543, "dur": 175.523, + "args": { + "External id": 4056820,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 3827 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 1336756, "tid": 1381189, + "ts": 1655275287404.829, "dur": 154.330, + "args": { + "External id": 4056821,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 3828 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655275287444.902, "dur": 12.564, + "args": { + "External id": 4056822,"Record function id": 0, "Concrete Inputs": ["[2133]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3829 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1381189, + "ts": 1655275287461.582, "dur": 69.064, + "args": { + "External id": 4056823,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], [], []], "Ev Idx": 3830 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336756, "tid": 1381189, + "ts": 1655275287464.101, "dur": 66.135, + "args": { + "External id": 4056824,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], []], "Ev Idx": 3831 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275287468.531, "dur": 6.186, + "args": { + "External id": 4056825,"Record function id": 0, "Concrete Inputs": ["[2133]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3832 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1381189, + "ts": 1655275287476.657, "dur": 52.944, + "args": { + "External id": 4056826,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[2133], [2133], []], "Ev Idx": 3833 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::backward_prefetch for model.layers.11", "pid": 1336756, "tid": 1381189, + "ts": 1655275287675.989, "dur": 572.968, + "args": { + "External id": 4056827,"Record function id": 0, "Ev Idx": 3834 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.11)", "pid": 1336756, "tid": 1381189, + "ts": 1655275287692.966, "dur": 542.455, + "args": { + "External id": 4056828,"Record function id": 0, "Ev Idx": 3835 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655275287745.856, "dur": 5.700, + "args": { + "External id": 4056829,"Record function id": 0, "Concrete Inputs": ["[6423040]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3836 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336756, "tid": 1381189, + "ts": 1655275287767.082, "dur": 29.486, + "args": { + "External id": 4056830,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 3837 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275287772.228, "dur": 1.473, + "args": { + "External id": 4056831,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3838 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275287775.941, "dur": 2.486, + "args": { + "External id": 4056832,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3839 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275287779.972, "dur": 0.534, + "args": { + "External id": 4056833,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3840 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275287782.313, "dur": 0.416, + "args": { + "External id": 4056834,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3841 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275287784.171, "dur": 0.417, + "args": { + "External id": 4056835,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3842 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275287786.304, "dur": 0.410, + "args": { + "External id": 4056836,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3843 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275287788.288, "dur": 0.567, + "args": { + "External id": 4056837,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3844 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275287790.387, "dur": 0.415, + "args": { + "External id": 4056838,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3845 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275287792.334, "dur": 0.309, + "args": { + "External id": 4056839,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3846 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336756, "tid": 1381189, + "ts": 1655275287805.768, "dur": 27.364, + "args": { + "External id": 4056840,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 3847 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 1336756, "tid": 1381189, + "ts": 1655275287864.762, "dur": 98.610, + "args": { + "External id": 4056841,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "6423040", "8", "3", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [], [], [], [], [], []], "Ev Idx": 3848 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655275287874.993, "dur": 5.479, + "args": { + "External id": 4056842,"Record function id": 0, "Concrete Inputs": ["[51384320]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3849 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 1336756, "tid": 1381189, + "ts": 1655275287885.821, "dur": 10.018, + "args": { + "External id": 4056843,"Record function id": 0, "Concrete Inputs": ["", "0", "19269120", "6423040"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 3850 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1381189, + "ts": 1655275287890.026, "dur": 5.395, + "args": { + "External id": 4056844,"Record function id": 0, "Concrete Inputs": ["", "0", "19269120", "25692160", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[51384320], [], [], [], []], "Ev Idx": 3851 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275287893.729, "dur": 0.507, + "args": { + "External id": 4056845,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "[1]", "19269120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 3852 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336756, "tid": 1381189, + "ts": 1655275287903.469, "dur": 23.768, + "args": { + "External id": 4056846,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 3853 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275287905.890, "dur": 0.381, + "args": { + "External id": 4056847,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "19269120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3854 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275287907.668, "dur": 0.329, + "args": { + "External id": 4056848,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "19269376"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3855 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275287909.703, "dur": 0.626, + "args": { + "External id": 4056849,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "19793664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3856 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275287911.689, "dur": 0.341, + "args": { + "External id": 4056850,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "20317952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3857 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275287913.738, "dur": 0.554, + "args": { + "External id": 4056851,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "20842240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3858 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275287915.840, "dur": 0.361, + "args": { + "External id": 4056852,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "21366528"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3859 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275287917.854, "dur": 2.523, + "args": { + "External id": 4056853,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "21366784"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3860 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275287921.983, "dur": 0.460, + "args": { + "External id": 4056854,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "22808576"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3861 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275287924.193, "dur": 0.281, + "args": { + "External id": 4056855,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "24250368"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3862 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336756, "tid": 1381189, + "ts": 1655275287937.014, "dur": 20.007, + "args": { + "External id": 4056856,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 3863 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 1336756, "tid": 1381189, + "ts": 1655275288052.442, "dur": 115.022, + "args": { + "External id": 4056857,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[51384320], [6423040], [], [], []], "Ev Idx": 3864 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336756, "tid": 1381189, + "ts": 1655275288075.672, "dur": 88.056, + "args": { + "External id": 4056858,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 3, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "3", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 51384320, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[6423040], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 3865, "In msg nelems": 6423040 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 1336756, "tid": 1381189, + "ts": 1655275288086.112, "dur": 73.512, + "args": { + "External id": 4056859,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[6423040]], "Ev Idx": 3866 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336756, "tid": 1381189, + "ts": 1655275288180.733, "dur": 1.587, + "args": { + "External id": 4056860,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "3", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 3867, "In msg nelems": 0, "Rank": 3, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1655275288263.856, "dur": 1593.224, + "args": { + "External id": 4056861,"Sequence number": 40618378, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 3868 + } + }, + { + "ph": "f", "id": 202, "pid": 1336756, "tid": 1381189, "ts": 1655275288263.856, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275288370.044, "dur": 125.783, + "args": { + "External id": 4056862,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [5632, 1], [5632, 1]], "Input Dims": [[65536, 2048], [2048, 5632], [65536, 5632]], "Ev Idx": 3869 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_add_mul_rsub_silu_0", "pid": 1336756, "tid": 1381189, + "ts": 1655275288538.463, "dur": 38.099, + "args": { + "External id": 4056863,"kernel_hash": "c2zszzsomz26dv2qwvmiurvgyrl5qxtyn6ocoqkdpzzhfzwqp5q6", "grid": "grid(369098752,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "369098752"], "kernel_file": "/tmp/torchinductor_cvm/2z/c2zszzsomz26dv2qwvmiurvgyrl5qxtyn6ocoqkdpzzhfzwqp5q6.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[5632, 1], [5632, 1], [5632, 1], [23068672, 5632, 1], [23068672, 5632, 1], [23068672, 5632, 1], []], "Input Dims": [[65536, 5632], [65536, 5632], [65536, 5632], [16, 4096, 5632], [16, 4096, 5632], [16, 4096, 5632], []], "Ev Idx": 3870 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 1336756, "tid": 1381189, + "ts": 1655275288596.096, "dur": 51.753, + "args": { + "External id": 4056864,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[0, 1, 2048], [0, 5632, 1], [11534336, 5632, 1]], "Input Dims": [[1, 2048, 65536], [1, 65536, 5632], [1, 2048, 5632]], "Ev Idx": 3871 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275288657.517, "dur": 32.626, + "args": { + "External id": 4056865,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 5632], [2048, 1], [2048, 1]], "Input Dims": [[5632, 65536], [65536, 2048], [5632, 2048]], "Ev Idx": 3872 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275288697.330, "dur": 46.314, + "args": { + "External id": 4056866,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 5632], [5632, 2048], [65536, 2048]], "Ev Idx": 3873 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275288753.768, "dur": 28.434, + "args": { + "External id": 4056867,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 5632], [2048, 1], [2048, 1]], "Input Dims": [[5632, 65536], [65536, 2048], [5632, 2048]], "Ev Idx": 3874 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275288790.009, "dur": 42.087, + "args": { + "External id": 4056868,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 5632], [5632, 2048], [65536, 2048]], "Ev Idx": 3875 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_1", "pid": 1336756, "tid": 1381189, + "ts": 1655275288855.138, "dur": 20.540, + "args": { + "External id": 4056869,"kernel_hash": "cjd6g3jfgntyoifzno6l2urmnhif7alxtw6zz7miov66vywxwv7d", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/jd/cjd6g3jfgntyoifzno6l2urmnhif7alxtw6zz7miov66vywxwv7d.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[65536, 2048], [65536, 2048], []], "Ev Idx": 3876 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 1336756, "tid": 1381189, + "ts": 1655275288894.214, "dur": 27.147, + "args": { + "External id": 4056870,"kernel_hash": "cxhg545cyph4gbk5vymzyh72vho7oogk3ycan2lp4cxntklp5hew", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "65536", "2048", "1", "497", "132", "True", "2048", "True", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/xh/cxhg545cyph4gbk5vymzyh72vho7oogk3ycan2lp4cxntklp5hew.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [1], [2048, 1], [2048, 1], [2048, 1], [2048, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [2048], [65536, 2048], [65536, 2048], [132, 2048], [65536, 2048], [65536], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 3877 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 1336756, "tid": 1381189, + "ts": 1655275288938.874, "dur": 18.233, + "args": { + "External id": 4056871,"kernel_hash": "cu42i6zmxtvs2i7cs6x4ixaexke3lhgdiaye5oxwm7s3u6em6co4", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "66"], "kernel_file": "/tmp/torchinductor_cvm/u4/cu42i6zmxtvs2i7cs6x4ixaexke3lhgdiaye5oxwm7s3u6em6co4.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [4096, 1, 2048], [], []], "Input Dims": [[132, 2048], [1, 2048, 2], [], []], "Ev Idx": 3878 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 1336756, "tid": 1381189, + "ts": 1655275288971.932, "dur": 52.955, + "args": { + "External id": 4056872,"kernel_hash": "ckihofrorhmzazt2wfn2dz2m5wfx3auisu2gvfo2jsepr4zyekmq", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "2"], "kernel_file": "/tmp/torchinductor_cvm/ki/ckihofrorhmzazt2wfn2dz2m5wfx3auisu2gvfo2jsepr4zyekmq.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1, 2048], [2048, 1], [], []], "Input Dims": [[1, 2048, 2], [1, 2048], [], []], "Ev Idx": 3879 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275289039.090, "dur": 34.014, + "args": { + "External id": 4056873,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 3880 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275289076.780, "dur": 33.459, + "args": { + "External id": 4056874,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 3881 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 1336756, "tid": 1381189, + "ts": 1655275289137.507, "dur": 169.954, + "args": { + "External id": 4056875,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.125", "True", "-1", "-1", "0.", "", "False", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar", "long int"], "Input Strides": [[8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [131072, 4096, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 32, 4096], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 3882 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655275289213.317, "dur": 6.260, + "args": { + "External id": 4056876,"Record function id": 0, "Concrete Inputs": ["[16, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3883 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655275289221.615, "dur": 4.394, + "args": { + "External id": 4056877,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3884 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336756, "tid": 1381189, + "ts": 1655275289340.500, "dur": 23.287, + "args": { + "External id": 4056878,"kernel_hash": "cb6oumcqb462ndf2ivcd2sc6qg6mfjahptjw4ih7cesqhfpziv3b", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/b6/cb6oumcqb462ndf2ivcd2sc6qg6mfjahptjw4ih7cesqhfpziv3b.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 3885 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336756, "tid": 1381189, + "ts": 1655275289375.100, "dur": 13.981, + "args": { + "External id": 4056879,"kernel_hash": "cb6oumcqb462ndf2ivcd2sc6qg6mfjahptjw4ih7cesqhfpziv3b", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/b6/cb6oumcqb462ndf2ivcd2sc6qg6mfjahptjw4ih7cesqhfpziv3b.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 3886 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275289397.602, "dur": 52.904, + "args": { + "External id": 4056880,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 3887 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275289459.814, "dur": 38.057, + "args": { + "External id": 4056881,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 3888 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275289505.426, "dur": 21.408, + "args": { + "External id": 4056882,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 3889 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275289534.710, "dur": 30.769, + "args": { + "External id": 4056883,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 3890 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275289571.657, "dur": 19.928, + "args": { + "External id": 4056884,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 3891 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275289599.169, "dur": 30.461, + "args": { + "External id": 4056885,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 3892 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_4", "pid": 1336756, "tid": 1381189, + "ts": 1655275289650.027, "dur": 21.952, + "args": { + "External id": 4056886,"kernel_hash": "c7pqhdjojzeazwsh5g3ibnyk4m2nfh3q73e3zc7hljz4yvhe7c4h", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/7p/c7pqhdjojzeazwsh5g3ibnyk4m2nfh3q73e3zc7hljz4yvhe7c4h.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1], []], "Input Dims": [[65536, 2048], [65536, 2048], [65536, 2048], []], "Ev Idx": 3893 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_2", "pid": 1336756, "tid": 1381189, + "ts": 1655275289705.821, "dur": 27.908, + "args": { + "External id": 4056887,"kernel_hash": "cvgvwkysjpcw75q5t3guce5bep2so25f7i5zxc6ipt5f56shof73", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "65536", "2048", "1", "497", "132", "True", "2048", "False", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/vg/cvgvwkysjpcw75q5t3guce5bep2so25f7i5zxc6ipt5f56shof73.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [1], [2048, 1], [2048, 1], [2048, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [2048], [65536, 2048], [65536, 2048], [132, 2048], [65536], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 3894 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 1336756, "tid": 1381189, + "ts": 1655275289748.005, "dur": 16.879, + "args": { + "External id": 4056888,"kernel_hash": "cu42i6zmxtvs2i7cs6x4ixaexke3lhgdiaye5oxwm7s3u6em6co4", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "66"], "kernel_file": "/tmp/torchinductor_cvm/u4/cu42i6zmxtvs2i7cs6x4ixaexke3lhgdiaye5oxwm7s3u6em6co4.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [4096, 1, 2048], [], []], "Input Dims": [[132, 2048], [1, 2048, 2], [], []], "Ev Idx": 3895 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 1336756, "tid": 1381189, + "ts": 1655275289779.487, "dur": 17.351, + "args": { + "External id": 4056889,"kernel_hash": "ckihofrorhmzazt2wfn2dz2m5wfx3auisu2gvfo2jsepr4zyekmq", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "2"], "kernel_file": "/tmp/torchinductor_cvm/ki/ckihofrorhmzazt2wfn2dz2m5wfx3auisu2gvfo2jsepr4zyekmq.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1, 2048], [2048, 1], [], []], "Input Dims": [[1, 2048, 2], [1, 2048], [], []], "Ev Idx": 3896 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_5", "pid": 1336756, "tid": 1381189, + "ts": 1655275289810.868, "dur": 14.911, + "args": { + "External id": 4056890,"kernel_hash": "cckrpn5uuxyvbancoio3sz2onrjto236n54xx4ycphq5p6r3jlfj", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/ck/cckrpn5uuxyvbancoio3sz2onrjto236n54xx4ycphq5p6r3jlfj.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [8388608, 2048, 1], []], "Input Dims": [[65536, 2048], [65536, 2048], [16, 4096, 2048], []], "Ev Idx": 3897 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275289898.566, "dur": 15.484, + "args": { + "External id": 4056891,"Record function id": 0, "Ev Idx": 3898 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275289902.319, "dur": 10.909, + "args": { + "External id": 4056892,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 3899 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275289906.569, "dur": 5.757, + "args": { + "External id": 4056893,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 3900 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275289908.260, "dur": 3.943, + "args": { + "External id": 4056894,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 3901 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275289917.933, "dur": 4.725, + "args": { + "External id": 4056895,"Record function id": 0, "Ev Idx": 3902 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275289919.348, "dur": 2.857, + "args": { + "External id": 4056896,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 3903 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275289919.974, "dur": 1.811, + "args": { + "External id": 4056897,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 3904 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275289920.709, "dur": 0.979, + "args": { + "External id": 4056898,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 3905 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275289925.781, "dur": 4.631, + "args": { + "External id": 4056899,"Record function id": 0, "Ev Idx": 3906 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275289927.035, "dur": 2.973, + "args": { + "External id": 4056900,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 3907 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275289927.683, "dur": 1.924, + "args": { + "External id": 4056901,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 3908 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275289928.408, "dur": 1.107, + "args": { + "External id": 4056902,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 3909 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275289933.588, "dur": 5.766, + "args": { + "External id": 4056903,"Record function id": 0, "Ev Idx": 3910 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275289934.673, "dur": 4.285, + "args": { + "External id": 4056904,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 3911 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275289935.530, "dur": 3.018, + "args": { + "External id": 4056905,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 3912 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275289935.993, "dur": 2.488, + "args": { + "External id": 4056906,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 3913 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275289942.397, "dur": 3.616, + "args": { + "External id": 4056907,"Record function id": 0, "Ev Idx": 3914 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275289943.327, "dur": 2.289, + "args": { + "External id": 4056908,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 3915 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275289944.175, "dur": 1.022, + "args": { + "External id": 4056909,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 3916 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275289944.454, "dur": 0.670, + "args": { + "External id": 4056910,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 3917 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275289949.079, "dur": 3.781, + "args": { + "External id": 4056911,"Record function id": 0, "Ev Idx": 3918 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275289950.174, "dur": 2.274, + "args": { + "External id": 4056912,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 3919 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275289950.891, "dur": 1.176, + "args": { + "External id": 4056913,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 3920 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275289951.369, "dur": 0.566, + "args": { + "External id": 4056914,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 3921 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275289956.066, "dur": 3.707, + "args": { + "External id": 4056915,"Record function id": 0, "Ev Idx": 3922 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275289957.127, "dur": 2.231, + "args": { + "External id": 4056916,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 3923 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275289957.824, "dur": 1.154, + "args": { + "External id": 4056917,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 3924 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275289958.113, "dur": 0.759, + "args": { + "External id": 4056918,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 3925 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275289962.740, "dur": 3.786, + "args": { + "External id": 4056919,"Record function id": 0, "Ev Idx": 3926 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275289964.008, "dur": 2.122, + "args": { + "External id": 4056920,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 3927 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275289964.476, "dur": 1.287, + "args": { + "External id": 4056921,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 3928 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275289964.934, "dur": 0.765, + "args": { + "External id": 4056922,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 3929 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275289969.458, "dur": 64.361, + "args": { + "External id": 4056923,"Record function id": 0, "Ev Idx": 3930 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275289970.403, "dur": 62.048, + "args": { + "External id": 4056924,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 3931 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275289970.844, "dur": 60.321, + "args": { + "External id": 4056925,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 3932 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275290028.721, "dur": 1.966, + "args": { + "External id": 4056926,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 3933 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RegisterPostBackwardFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1655275290039.727, "dur": 37782.421, + "args": { + "External id": 4056927,"Record function id": 0, "Sequence number": 40618377, "Fwd thread id": 1, "Ev Idx": 3934 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1655275290041.333, "dur": 37772.291, + "args": { + "External id": 4056928,"Sequence number": 40618377, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 3935 + } + }, + { + "ph": "f", "id": 203, "pid": 1336756, "tid": 1381189, "ts": 1655275290041.333, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.12)", "pid": 1336756, "tid": 1381189, + "ts": 1655275290072.787, "dur": 37.627, + "args": { + "External id": 4056929,"Record function id": 0, "Ev Idx": 3936 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.12)", "pid": 1336756, "tid": 1381189, + "ts": 1655275290117.971, "dur": 62.431, + "args": { + "External id": 4056930,"Record function id": 0, "Ev Idx": 3937 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.12)", "pid": 1336756, "tid": 1381189, + "ts": 1655275290185.996, "dur": 37619.660, + "args": { + "External id": 4056931,"Record function id": 0, "Ev Idx": 3938 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655275290271.257, "dur": 6.779, + "args": { + "External id": 4056932,"Record function id": 0, "Concrete Inputs": ["[51384320]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3939 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275290288.080, "dur": 4.820, + "args": { + "External id": 4056933,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[51384320], []], "Ev Idx": 3940 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::chunk_cat", "pid": 1336756, "tid": 1381189, + "ts": 1655275290308.300, "dur": 36707.154, + "args": { + "External id": 4056934,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [2048, 1], [2048, 1], [2048, 1], [2048, 1], [1], [2048, 1], [2048, 1], [5632, 1]], [], [], [6423040, 1]], "Input Dims": [[[2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048], [5632, 2048], [5632, 2048], [2048, 5632]], [], [], [8, 6423040]], "Ev Idx": 3941 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_chunk_cat", "pid": 1336756, "tid": 1381189, + "ts": 1655275290320.995, "dur": 36685.265, + "args": { + "External id": 4056935,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [2048, 1], [2048, 1], [2048, 1], [2048, 1], [1], [2048, 1], [2048, 1], [5632, 1]], [], [], [6423040, 1]], "Input Dims": [[[2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048], [5632, 2048], [5632, 2048], [2048, 5632]], [], [], [8, 6423040]], "Ev Idx": 3942 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655275290359.634, "dur": 15.705, + "args": { + "External id": 4056936,"Record function id": 0, "Concrete Inputs": ["[12602]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3943 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1381189, + "ts": 1655275290381.964, "dur": 36561.167, + "args": { + "External id": 4056937,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[12602], [], [], [], [], [], [], []], "Ev Idx": 3944 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336756, "tid": 1381189, + "ts": 1655275290384.682, "dur": 36557.792, + "args": { + "External id": 4056938,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[12602], [], [], [], [], [], []], "Ev Idx": 3945 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275290388.671, "dur": 5.226, + "args": { + "External id": 4056939,"Record function id": 0, "Concrete Inputs": ["[12602]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3946 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1381189, + "ts": 1655275290395.884, "dur": 36542.977, + "args": { + "External id": 4056940,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[12602], [12602], []], "Ev Idx": 3947 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 1336756, "tid": 1381189, + "ts": 1655275327102.730, "dur": 9.447, + "args": { + "External id": 4056941,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "", "", "", "False"], "Input type": ["float", "ScalarList", "", "", "", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[51384320], [], [], [], [], []], "Ev Idx": 3948 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655275327106.021, "dur": 5.749, + "args": { + "External id": 4056942,"Record function id": 0, "Concrete Inputs": ["[6423040]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3949 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_reduce_scatter_base_", "pid": 1336756, "tid": 1381189, + "ts": 1655275327143.933, "dur": 360.432, + "args": { + "External id": 4056943,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "-1"], "Input type": ["float", "float", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], [], []], "Input Dims": [[6423040], [51384320], [], [], [], []], "Ev Idx": 3950 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336756, "tid": 1381189, + "ts": 1655275327170.844, "dur": 328.076, + "args": { + "External id": 4056944,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 3, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "3", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 6423040, "Process Group Name": "0", "Input type": ["float", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[51384320], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 3951, "In msg nelems": 51384320 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_reduce_scatter_base", "pid": 1336756, "tid": 1381189, + "ts": 1655275327182.515, "dur": 310.024, + "args": { + "External id": 4056945,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[51384320]], "Ev Idx": 3952 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336756, "tid": 1381189, + "ts": 1655275327526.031, "dur": 2.309, + "args": { + "External id": 4056946,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "3", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 3953, "In msg nelems": 0, "Rank": 3, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275327590.140, "dur": 6.615, + "args": { + "External id": 4056947,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3954 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275327646.935, "dur": 1.399, + "args": { + "External id": 4056948,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "256"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3955 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275327665.724, "dur": 1.062, + "args": { + "External id": 4056949,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "524544"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3956 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275327681.266, "dur": 0.969, + "args": { + "External id": 4056950,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "1048832"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3957 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275327693.879, "dur": 0.942, + "args": { + "External id": 4056951,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "1573120"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3958 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275327705.700, "dur": 1.088, + "args": { + "External id": 4056952,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3959 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275327718.994, "dur": 0.867, + "args": { + "External id": 4056953,"Record function id": 0, "Concrete Inputs": ["", "[704, 2048]", "[2048, 1]", "2097664"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3960 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275327732.988, "dur": 1.912, + "args": { + "External id": 4056954,"Record function id": 0, "Concrete Inputs": ["", "[704, 2048]", "[2048, 1]", "3539456"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3961 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275327745.168, "dur": 0.713, + "args": { + "External id": 4056955,"Record function id": 0, "Concrete Inputs": ["", "[256, 5632]", "[5632, 1]", "4981248"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3962 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: CompiledFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1655275327836.618, "dur": 2644.683, + "args": { + "External id": 4056956,"Record function id": 0, "Ev Idx": 3963 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.11)", "pid": 1336756, "tid": 1381189, + "ts": 1655275327856.136, "dur": 983.235, + "args": { + "External id": 4056957,"Record function id": 0, "Ev Idx": 3964 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.11)", "pid": 1336756, "tid": 1381189, + "ts": 1655275327870.573, "dur": 349.804, + "args": { + "External id": 4056958,"Record function id": 0, "Ev Idx": 3965 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275327944.122, "dur": 4.097, + "args": { + "External id": 4056959,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[51384320], []], "Ev Idx": 3966 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275327950.802, "dur": 1.000, + "args": { + "External id": 4056960,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 3967 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275327953.711, "dur": 0.927, + "args": { + "External id": 4056961,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 3968 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275327956.191, "dur": 2.497, + "args": { + "External id": 4056962,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 3969 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275327959.874, "dur": 0.847, + "args": { + "External id": 4056963,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 3970 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275327962.155, "dur": 0.852, + "args": { + "External id": 4056964,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 3971 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275327964.622, "dur": 1.501, + "args": { + "External id": 4056965,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 3972 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275327967.390, "dur": 1.171, + "args": { + "External id": 4056966,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 3973 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275327969.928, "dur": 0.831, + "args": { + "External id": 4056967,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 3974 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275327972.037, "dur": 1.077, + "args": { + "External id": 4056968,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 3975 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 1336756, "tid": 1381189, + "ts": 1655275328029.138, "dur": 156.425, + "args": { + "External id": 4056969,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 3976 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 1336756, "tid": 1381189, + "ts": 1655275328046.446, "dur": 134.617, + "args": { + "External id": 4056970,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 3977 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655275328066.671, "dur": 12.514, + "args": { + "External id": 4056971,"Record function id": 0, "Concrete Inputs": ["[2133]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3978 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1381189, + "ts": 1655275328082.657, "dur": 70.071, + "args": { + "External id": 4056972,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], [], []], "Ev Idx": 3979 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336756, "tid": 1381189, + "ts": 1655275328085.545, "dur": 66.772, + "args": { + "External id": 4056973,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], []], "Ev Idx": 3980 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275328089.561, "dur": 7.953, + "args": { + "External id": 4056974,"Record function id": 0, "Concrete Inputs": ["[2133]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3981 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1381189, + "ts": 1655275328099.491, "dur": 52.076, + "args": { + "External id": 4056975,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[2133], [2133], []], "Ev Idx": 3982 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::backward_prefetch for model.layers.10", "pid": 1336756, "tid": 1381189, + "ts": 1655275328295.147, "dur": 535.669, + "args": { + "External id": 4056976,"Record function id": 0, "Ev Idx": 3983 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.10)", "pid": 1336756, "tid": 1381189, + "ts": 1655275328313.829, "dur": 504.826, + "args": { + "External id": 4056977,"Record function id": 0, "Ev Idx": 3984 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655275328369.754, "dur": 4.647, + "args": { + "External id": 4056978,"Record function id": 0, "Concrete Inputs": ["[6423040]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3985 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336756, "tid": 1381189, + "ts": 1655275328389.769, "dur": 44.176, + "args": { + "External id": 4056979,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 3986 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275328394.900, "dur": 1.338, + "args": { + "External id": 4056980,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3987 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275328398.235, "dur": 0.441, + "args": { + "External id": 4056981,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3988 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275328400.188, "dur": 0.424, + "args": { + "External id": 4056982,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3989 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275328402.038, "dur": 0.372, + "args": { + "External id": 4056983,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3990 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275328404.054, "dur": 0.567, + "args": { + "External id": 4056984,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3991 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275328406.161, "dur": 0.358, + "args": { + "External id": 4056985,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3992 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275328407.957, "dur": 2.166, + "args": { + "External id": 4056986,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3993 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275328411.868, "dur": 0.385, + "args": { + "External id": 4056987,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3994 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275328413.869, "dur": 0.388, + "args": { + "External id": 4056988,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 3995 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336756, "tid": 1381189, + "ts": 1655275328444.790, "dur": 33.322, + "args": { + "External id": 4056989,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 3996 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 1336756, "tid": 1381189, + "ts": 1655275328510.226, "dur": 98.618, + "args": { + "External id": 4056990,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "6423040", "8", "3", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [], [], [], [], [], []], "Ev Idx": 3997 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655275328520.848, "dur": 3.888, + "args": { + "External id": 4056991,"Record function id": 0, "Concrete Inputs": ["[51384320]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 3998 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 1336756, "tid": 1381189, + "ts": 1655275328530.131, "dur": 10.598, + "args": { + "External id": 4056992,"Record function id": 0, "Concrete Inputs": ["", "0", "19269120", "6423040"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 3999 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1381189, + "ts": 1655275328534.425, "dur": 5.904, + "args": { + "External id": 4056993,"Record function id": 0, "Concrete Inputs": ["", "0", "19269120", "25692160", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[51384320], [], [], [], []], "Ev Idx": 4000 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275328538.413, "dur": 0.632, + "args": { + "External id": 4056994,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "[1]", "19269120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 4001 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336756, "tid": 1381189, + "ts": 1655275328547.948, "dur": 23.719, + "args": { + "External id": 4056995,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 4002 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275328550.067, "dur": 0.488, + "args": { + "External id": 4056996,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "19269120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4003 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275328552.131, "dur": 0.502, + "args": { + "External id": 4056997,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "19269376"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4004 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275328554.056, "dur": 0.402, + "args": { + "External id": 4056998,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "19793664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4005 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275328556.052, "dur": 2.292, + "args": { + "External id": 4056999,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "20317952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4006 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275328559.928, "dur": 0.444, + "args": { + "External id": 4057000,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "20842240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4007 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275328562.230, "dur": 0.399, + "args": { + "External id": 4057001,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "21366528"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4008 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275328564.213, "dur": 0.365, + "args": { + "External id": 4057002,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "21366784"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4009 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275328565.863, "dur": 0.364, + "args": { + "External id": 4057003,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "22808576"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4010 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275328567.747, "dur": 0.383, + "args": { + "External id": 4057004,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "24250368"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4011 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336756, "tid": 1381189, + "ts": 1655275328581.316, "dur": 20.104, + "args": { + "External id": 4057005,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 4012 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 1336756, "tid": 1381189, + "ts": 1655275328652.482, "dur": 104.068, + "args": { + "External id": 4057006,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[51384320], [6423040], [], [], []], "Ev Idx": 4013 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336756, "tid": 1381189, + "ts": 1655275328672.872, "dur": 80.201, + "args": { + "External id": 4057007,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 3, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "3", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 51384320, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[6423040], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 4014, "In msg nelems": 6423040 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 1336756, "tid": 1381189, + "ts": 1655275328682.269, "dur": 66.879, + "args": { + "External id": 4057008,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[6423040]], "Ev Idx": 4015 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336756, "tid": 1381189, + "ts": 1655275328769.977, "dur": 1.695, + "args": { + "External id": 4057009,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "3", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 4016, "In msg nelems": 0, "Rank": 3, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1655275328845.684, "dur": 1611.906, + "args": { + "External id": 4057010,"Sequence number": 40618376, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 4017 + } + }, + { + "ph": "f", "id": 204, "pid": 1336756, "tid": 1381189, "ts": 1655275328845.684, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275328950.180, "dur": 145.564, + "args": { + "External id": 4057011,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [5632, 1], [5632, 1]], "Input Dims": [[65536, 2048], [2048, 5632], [65536, 5632]], "Ev Idx": 4018 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_add_mul_rsub_silu_0", "pid": 1336756, "tid": 1381189, + "ts": 1655275329140.575, "dur": 37.484, + "args": { + "External id": 4057012,"kernel_hash": "c2zszzsomz26dv2qwvmiurvgyrl5qxtyn6ocoqkdpzzhfzwqp5q6", "grid": "grid(369098752,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "369098752"], "kernel_file": "/tmp/torchinductor_cvm/2z/c2zszzsomz26dv2qwvmiurvgyrl5qxtyn6ocoqkdpzzhfzwqp5q6.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[5632, 1], [5632, 1], [5632, 1], [23068672, 5632, 1], [23068672, 5632, 1], [23068672, 5632, 1], []], "Input Dims": [[65536, 5632], [65536, 5632], [65536, 5632], [16, 4096, 5632], [16, 4096, 5632], [16, 4096, 5632], []], "Ev Idx": 4019 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 1336756, "tid": 1381189, + "ts": 1655275329196.087, "dur": 52.709, + "args": { + "External id": 4057013,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[0, 1, 2048], [0, 5632, 1], [11534336, 5632, 1]], "Input Dims": [[1, 2048, 65536], [1, 65536, 5632], [1, 2048, 5632]], "Ev Idx": 4020 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275329258.513, "dur": 33.881, + "args": { + "External id": 4057014,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 5632], [2048, 1], [2048, 1]], "Input Dims": [[5632, 65536], [65536, 2048], [5632, 2048]], "Ev Idx": 4021 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275329301.671, "dur": 46.027, + "args": { + "External id": 4057015,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 5632], [5632, 2048], [65536, 2048]], "Ev Idx": 4022 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275329355.364, "dur": 28.879, + "args": { + "External id": 4057016,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 5632], [2048, 1], [2048, 1]], "Input Dims": [[5632, 65536], [65536, 2048], [5632, 2048]], "Ev Idx": 4023 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275329391.346, "dur": 54.390, + "args": { + "External id": 4057017,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 5632], [5632, 2048], [65536, 2048]], "Ev Idx": 4024 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_1", "pid": 1336756, "tid": 1381189, + "ts": 1655275329471.367, "dur": 22.798, + "args": { + "External id": 4057018,"kernel_hash": "cjd6g3jfgntyoifzno6l2urmnhif7alxtw6zz7miov66vywxwv7d", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/jd/cjd6g3jfgntyoifzno6l2urmnhif7alxtw6zz7miov66vywxwv7d.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[65536, 2048], [65536, 2048], []], "Ev Idx": 4025 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 1336756, "tid": 1381189, + "ts": 1655275329513.368, "dur": 25.284, + "args": { + "External id": 4057019,"kernel_hash": "cxhg545cyph4gbk5vymzyh72vho7oogk3ycan2lp4cxntklp5hew", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "65536", "2048", "1", "497", "132", "True", "2048", "True", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/xh/cxhg545cyph4gbk5vymzyh72vho7oogk3ycan2lp4cxntklp5hew.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [1], [2048, 1], [2048, 1], [2048, 1], [2048, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [2048], [65536, 2048], [65536, 2048], [132, 2048], [65536, 2048], [65536], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 4026 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 1336756, "tid": 1381189, + "ts": 1655275329559.833, "dur": 19.257, + "args": { + "External id": 4057020,"kernel_hash": "cu42i6zmxtvs2i7cs6x4ixaexke3lhgdiaye5oxwm7s3u6em6co4", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "66"], "kernel_file": "/tmp/torchinductor_cvm/u4/cu42i6zmxtvs2i7cs6x4ixaexke3lhgdiaye5oxwm7s3u6em6co4.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [4096, 1, 2048], [], []], "Input Dims": [[132, 2048], [1, 2048, 2], [], []], "Ev Idx": 4027 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 1336756, "tid": 1381189, + "ts": 1655275329591.770, "dur": 17.271, + "args": { + "External id": 4057021,"kernel_hash": "ckihofrorhmzazt2wfn2dz2m5wfx3auisu2gvfo2jsepr4zyekmq", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "2"], "kernel_file": "/tmp/torchinductor_cvm/ki/ckihofrorhmzazt2wfn2dz2m5wfx3auisu2gvfo2jsepr4zyekmq.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1, 2048], [2048, 1], [], []], "Input Dims": [[1, 2048, 2], [1, 2048], [], []], "Ev Idx": 4028 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275329618.730, "dur": 31.036, + "args": { + "External id": 4057022,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 4029 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275329653.212, "dur": 33.012, + "args": { + "External id": 4057023,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 4030 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 1336756, "tid": 1381189, + "ts": 1655275329714.424, "dur": 166.017, + "args": { + "External id": 4057024,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.125", "True", "-1", "-1", "0.", "", "False", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar", "long int"], "Input Strides": [[8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [131072, 4096, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 32, 4096], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 4031 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655275329789.887, "dur": 5.553, + "args": { + "External id": 4057025,"Record function id": 0, "Concrete Inputs": ["[16, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4032 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655275329797.504, "dur": 2.271, + "args": { + "External id": 4057026,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4033 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336756, "tid": 1381189, + "ts": 1655275329909.930, "dur": 23.020, + "args": { + "External id": 4057027,"kernel_hash": "cb6oumcqb462ndf2ivcd2sc6qg6mfjahptjw4ih7cesqhfpziv3b", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/b6/cb6oumcqb462ndf2ivcd2sc6qg6mfjahptjw4ih7cesqhfpziv3b.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 4034 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336756, "tid": 1381189, + "ts": 1655275329943.859, "dur": 13.384, + "args": { + "External id": 4057028,"kernel_hash": "cb6oumcqb462ndf2ivcd2sc6qg6mfjahptjw4ih7cesqhfpziv3b", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/b6/cb6oumcqb462ndf2ivcd2sc6qg6mfjahptjw4ih7cesqhfpziv3b.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 4035 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275329965.726, "dur": 73.290, + "args": { + "External id": 4057029,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 4036 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275330048.914, "dur": 39.326, + "args": { + "External id": 4057030,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 4037 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275330098.345, "dur": 21.978, + "args": { + "External id": 4057031,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 4038 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275330126.260, "dur": 30.496, + "args": { + "External id": 4057032,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 4039 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275330163.282, "dur": 20.524, + "args": { + "External id": 4057033,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 4040 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275330191.324, "dur": 30.062, + "args": { + "External id": 4057034,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 4041 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_4", "pid": 1336756, "tid": 1381189, + "ts": 1655275330239.622, "dur": 22.062, + "args": { + "External id": 4057035,"kernel_hash": "c7pqhdjojzeazwsh5g3ibnyk4m2nfh3q73e3zc7hljz4yvhe7c4h", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/7p/c7pqhdjojzeazwsh5g3ibnyk4m2nfh3q73e3zc7hljz4yvhe7c4h.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1], []], "Input Dims": [[65536, 2048], [65536, 2048], [65536, 2048], []], "Ev Idx": 4042 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_2", "pid": 1336756, "tid": 1381189, + "ts": 1655275330278.171, "dur": 22.246, + "args": { + "External id": 4057036,"kernel_hash": "cvgvwkysjpcw75q5t3guce5bep2so25f7i5zxc6ipt5f56shof73", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "65536", "2048", "1", "497", "132", "True", "2048", "False", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/vg/cvgvwkysjpcw75q5t3guce5bep2so25f7i5zxc6ipt5f56shof73.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [1], [2048, 1], [2048, 1], [2048, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [2048], [65536, 2048], [65536, 2048], [132, 2048], [65536], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 4043 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 1336756, "tid": 1381189, + "ts": 1655275330328.088, "dur": 21.856, + "args": { + "External id": 4057037,"kernel_hash": "cu42i6zmxtvs2i7cs6x4ixaexke3lhgdiaye5oxwm7s3u6em6co4", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "66"], "kernel_file": "/tmp/torchinductor_cvm/u4/cu42i6zmxtvs2i7cs6x4ixaexke3lhgdiaye5oxwm7s3u6em6co4.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [4096, 1, 2048], [], []], "Input Dims": [[132, 2048], [1, 2048, 2], [], []], "Ev Idx": 4044 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 1336756, "tid": 1381189, + "ts": 1655275330366.025, "dur": 14.745, + "args": { + "External id": 4057038,"kernel_hash": "ckihofrorhmzazt2wfn2dz2m5wfx3auisu2gvfo2jsepr4zyekmq", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "2"], "kernel_file": "/tmp/torchinductor_cvm/ki/ckihofrorhmzazt2wfn2dz2m5wfx3auisu2gvfo2jsepr4zyekmq.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1, 2048], [2048, 1], [], []], "Input Dims": [[1, 2048, 2], [1, 2048], [], []], "Ev Idx": 4045 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_5", "pid": 1336756, "tid": 1381189, + "ts": 1655275330393.028, "dur": 15.210, + "args": { + "External id": 4057039,"kernel_hash": "cckrpn5uuxyvbancoio3sz2onrjto236n54xx4ycphq5p6r3jlfj", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/ck/cckrpn5uuxyvbancoio3sz2onrjto236n54xx4ycphq5p6r3jlfj.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [8388608, 2048, 1], []], "Input Dims": [[65536, 2048], [65536, 2048], [16, 4096, 2048], []], "Ev Idx": 4046 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275330504.395, "dur": 15.845, + "args": { + "External id": 4057040,"Record function id": 0, "Ev Idx": 4047 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275330507.738, "dur": 11.440, + "args": { + "External id": 4057041,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 4048 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275330512.127, "dur": 6.228, + "args": { + "External id": 4057042,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 4049 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275330514.074, "dur": 4.150, + "args": { + "External id": 4057043,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 4050 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275330523.890, "dur": 4.681, + "args": { + "External id": 4057044,"Record function id": 0, "Ev Idx": 4051 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275330525.133, "dur": 2.980, + "args": { + "External id": 4057045,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 4052 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275330525.747, "dur": 1.862, + "args": { + "External id": 4057046,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 4053 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275330526.384, "dur": 1.116, + "args": { + "External id": 4057047,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 4054 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275330531.823, "dur": 6.643, + "args": { + "External id": 4057048,"Record function id": 0, "Ev Idx": 4055 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275330533.300, "dur": 4.731, + "args": { + "External id": 4057049,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 4056 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275330533.790, "dur": 3.821, + "args": { + "External id": 4057050,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 4057 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275330534.330, "dur": 3.216, + "args": { + "External id": 4057051,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 4058 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275330541.610, "dur": 3.850, + "args": { + "External id": 4057052,"Record function id": 0, "Ev Idx": 4059 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275330542.846, "dur": 2.225, + "args": { + "External id": 4057053,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 4060 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275330543.368, "dur": 1.311, + "args": { + "External id": 4057054,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 4061 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275330543.671, "dur": 0.940, + "args": { + "External id": 4057055,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 4062 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275330548.545, "dur": 3.521, + "args": { + "External id": 4057056,"Record function id": 0, "Ev Idx": 4063 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275330549.673, "dur": 1.970, + "args": { + "External id": 4057057,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 4064 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275330550.159, "dur": 1.074, + "args": { + "External id": 4057058,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 4065 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275330550.526, "dur": 0.643, + "args": { + "External id": 4057059,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 4066 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275330555.143, "dur": 3.701, + "args": { + "External id": 4057060,"Record function id": 0, "Ev Idx": 4067 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275330556.373, "dur": 2.077, + "args": { + "External id": 4057061,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 4068 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275330556.829, "dur": 1.229, + "args": { + "External id": 4057062,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 4069 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275330557.292, "dur": 0.659, + "args": { + "External id": 4057063,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 4070 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275330562.094, "dur": 3.258, + "args": { + "External id": 4057064,"Record function id": 0, "Ev Idx": 4071 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275330563.172, "dur": 1.797, + "args": { + "External id": 4057065,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 4072 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275330563.608, "dur": 0.967, + "args": { + "External id": 4057066,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 4073 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275330563.878, "dur": 0.595, + "args": { + "External id": 4057067,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 4074 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275330568.369, "dur": 4.159, + "args": { + "External id": 4057068,"Record function id": 0, "Ev Idx": 4075 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275330569.962, "dur": 2.166, + "args": { + "External id": 4057069,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 4076 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275330570.432, "dur": 1.277, + "args": { + "External id": 4057070,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 4077 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275330570.778, "dur": 0.856, + "args": { + "External id": 4057071,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 4078 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275330575.504, "dur": 3.938, + "args": { + "External id": 4057072,"Record function id": 0, "Ev Idx": 4079 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275330576.663, "dur": 2.373, + "args": { + "External id": 4057073,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 4080 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275330577.310, "dur": 1.307, + "args": { + "External id": 4057074,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 4081 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275330577.741, "dur": 0.789, + "args": { + "External id": 4057075,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 4082 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RegisterPostBackwardFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1655275330582.887, "dur": 36756.403, + "args": { + "External id": 4057076,"Record function id": 0, "Sequence number": 40618375, "Fwd thread id": 1, "Ev Idx": 4083 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1655275330583.969, "dur": 36747.061, + "args": { + "External id": 4057077,"Sequence number": 40618375, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 4084 + } + }, + { + "ph": "f", "id": 205, "pid": 1336756, "tid": 1381189, "ts": 1655275330583.969, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.11)", "pid": 1336756, "tid": 1381189, + "ts": 1655275330613.268, "dur": 38.469, + "args": { + "External id": 4057078,"Record function id": 0, "Ev Idx": 4085 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.11)", "pid": 1336756, "tid": 1381189, + "ts": 1655275330662.397, "dur": 63.085, + "args": { + "External id": 4057079,"Record function id": 0, "Ev Idx": 4086 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.11)", "pid": 1336756, "tid": 1381189, + "ts": 1655275330731.261, "dur": 36592.364, + "args": { + "External id": 4057080,"Record function id": 0, "Ev Idx": 4087 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655275330817.016, "dur": 6.188, + "args": { + "External id": 4057081,"Record function id": 0, "Concrete Inputs": ["[51384320]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4088 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275330833.101, "dur": 13.435, + "args": { + "External id": 4057082,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[51384320], []], "Ev Idx": 4089 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::chunk_cat", "pid": 1336756, "tid": 1381189, + "ts": 1655275330861.842, "dur": 35657.005, + "args": { + "External id": 4057083,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [2048, 1], [2048, 1], [2048, 1], [2048, 1], [1], [2048, 1], [2048, 1], [5632, 1]], [], [], [6423040, 1]], "Input Dims": [[[2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048], [5632, 2048], [5632, 2048], [2048, 5632]], [], [], [8, 6423040]], "Ev Idx": 4090 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_chunk_cat", "pid": 1336756, "tid": 1381189, + "ts": 1655275330876.287, "dur": 35633.701, + "args": { + "External id": 4057084,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [2048, 1], [2048, 1], [2048, 1], [2048, 1], [1], [2048, 1], [2048, 1], [5632, 1]], [], [], [6423040, 1]], "Input Dims": [[[2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048], [5632, 2048], [5632, 2048], [2048, 5632]], [], [], [8, 6423040]], "Ev Idx": 4091 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655275330948.549, "dur": 13.763, + "args": { + "External id": 4057085,"Record function id": 0, "Concrete Inputs": ["[12602]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4092 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1381189, + "ts": 1655275330968.505, "dur": 35502.008, + "args": { + "External id": 4057086,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[12602], [], [], [], [], [], [], []], "Ev Idx": 4093 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336756, "tid": 1381189, + "ts": 1655275330971.192, "dur": 35498.386, + "args": { + "External id": 4057087,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[12602], [], [], [], [], [], []], "Ev Idx": 4094 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275330975.322, "dur": 4.677, + "args": { + "External id": 4057088,"Record function id": 0, "Concrete Inputs": ["[12602]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4095 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1381189, + "ts": 1655275331046.482, "dur": 35419.285, + "args": { + "External id": 4057089,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[12602], [12602], []], "Ev Idx": 4096 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 1336756, "tid": 1381189, + "ts": 1655275366611.228, "dur": 9.679, + "args": { + "External id": 4057090,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "", "", "", "False"], "Input type": ["float", "ScalarList", "", "", "", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[51384320], [], [], [], [], []], "Ev Idx": 4097 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655275366614.649, "dur": 5.893, + "args": { + "External id": 4057091,"Record function id": 0, "Concrete Inputs": ["[6423040]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4098 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_reduce_scatter_base_", "pid": 1336756, "tid": 1381189, + "ts": 1655275366650.881, "dur": 371.130, + "args": { + "External id": 4057092,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "-1"], "Input type": ["float", "float", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], [], []], "Input Dims": [[6423040], [51384320], [], [], [], []], "Ev Idx": 4099 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336756, "tid": 1381189, + "ts": 1655275366677.307, "dur": 339.040, + "args": { + "External id": 4057093,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 3, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "3", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 6423040, "Process Group Name": "0", "Input type": ["float", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[51384320], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 4100, "In msg nelems": 51384320 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_reduce_scatter_base", "pid": 1336756, "tid": 1381189, + "ts": 1655275366688.505, "dur": 290.992, + "args": { + "External id": 4057094,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[51384320]], "Ev Idx": 4101 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336756, "tid": 1381189, + "ts": 1655275367044.466, "dur": 2.870, + "args": { + "External id": 4057095,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "3", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 4102, "In msg nelems": 0, "Rank": 3, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275367109.961, "dur": 7.250, + "args": { + "External id": 4057096,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4103 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275367162.647, "dur": 1.652, + "args": { + "External id": 4057097,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "256"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4104 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275367180.648, "dur": 3.011, + "args": { + "External id": 4057098,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "524544"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4105 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275367196.935, "dur": 1.006, + "args": { + "External id": 4057099,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "1048832"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4106 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275367208.497, "dur": 0.809, + "args": { + "External id": 4057100,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "1573120"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4107 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275367220.055, "dur": 1.059, + "args": { + "External id": 4057101,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4108 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275367236.484, "dur": 2.893, + "args": { + "External id": 4057102,"Record function id": 0, "Concrete Inputs": ["", "[704, 2048]", "[2048, 1]", "2097664"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4109 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275367251.490, "dur": 1.638, + "args": { + "External id": 4057103,"Record function id": 0, "Concrete Inputs": ["", "[704, 2048]", "[2048, 1]", "3539456"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4110 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275367263.168, "dur": 0.909, + "args": { + "External id": 4057104,"Record function id": 0, "Concrete Inputs": ["", "[256, 5632]", "[5632, 1]", "4981248"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4111 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: CompiledFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1655275367355.266, "dur": 2698.265, + "args": { + "External id": 4057105,"Record function id": 0, "Ev Idx": 4112 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.10)", "pid": 1336756, "tid": 1381189, + "ts": 1655275367374.187, "dur": 1008.149, + "args": { + "External id": 4057106,"Record function id": 0, "Ev Idx": 4113 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.10)", "pid": 1336756, "tid": 1381189, + "ts": 1655275367388.809, "dur": 332.735, + "args": { + "External id": 4057107,"Record function id": 0, "Ev Idx": 4114 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275367486.294, "dur": 4.843, + "args": { + "External id": 4057108,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[51384320], []], "Ev Idx": 4115 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275367494.226, "dur": 0.923, + "args": { + "External id": 4057109,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 4116 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275367496.865, "dur": 3.203, + "args": { + "External id": 4057110,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 4117 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275367501.451, "dur": 0.943, + "args": { + "External id": 4057111,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 4118 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275367503.757, "dur": 1.365, + "args": { + "External id": 4057112,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 4119 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275367507.036, "dur": 0.938, + "args": { + "External id": 4057113,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 4120 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275367509.436, "dur": 1.106, + "args": { + "External id": 4057114,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 4121 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275367511.697, "dur": 1.079, + "args": { + "External id": 4057115,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 4122 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275367513.946, "dur": 0.971, + "args": { + "External id": 4057116,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 4123 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275367516.088, "dur": 1.050, + "args": { + "External id": 4057117,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 4124 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 1336756, "tid": 1381189, + "ts": 1655275367535.300, "dur": 153.465, + "args": { + "External id": 4057118,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 4125 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 1336756, "tid": 1381189, + "ts": 1655275367551.377, "dur": 132.879, + "args": { + "External id": 4057119,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 4126 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655275367569.464, "dur": 15.501, + "args": { + "External id": 4057120,"Record function id": 0, "Concrete Inputs": ["[2133]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4127 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1381189, + "ts": 1655275367588.287, "dur": 68.063, + "args": { + "External id": 4057121,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], [], []], "Ev Idx": 4128 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336756, "tid": 1381189, + "ts": 1655275367590.871, "dur": 65.174, + "args": { + "External id": 4057122,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], []], "Ev Idx": 4129 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275367595.079, "dur": 5.546, + "args": { + "External id": 4057123,"Record function id": 0, "Concrete Inputs": ["[2133]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4130 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1381189, + "ts": 1655275367602.559, "dur": 52.766, + "args": { + "External id": 4057124,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[2133], [2133], []], "Ev Idx": 4131 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::backward_prefetch for model.layers.9", "pid": 1336756, "tid": 1381189, + "ts": 1655275367794.994, "dur": 578.986, + "args": { + "External id": 4057125,"Record function id": 0, "Ev Idx": 4132 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.9)", "pid": 1336756, "tid": 1381189, + "ts": 1655275367813.630, "dur": 547.250, + "args": { + "External id": 4057126,"Record function id": 0, "Ev Idx": 4133 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655275367868.912, "dur": 4.874, + "args": { + "External id": 4057127,"Record function id": 0, "Concrete Inputs": ["[6423040]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4134 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336756, "tid": 1381189, + "ts": 1655275367889.453, "dur": 32.827, + "args": { + "External id": 4057128,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 4135 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275367894.616, "dur": 1.485, + "args": { + "External id": 4057129,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4136 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275367897.995, "dur": 0.663, + "args": { + "External id": 4057130,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4137 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275367900.261, "dur": 0.502, + "args": { + "External id": 4057131,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4138 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275367902.541, "dur": 0.567, + "args": { + "External id": 4057132,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4139 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275367904.671, "dur": 0.435, + "args": { + "External id": 4057133,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4140 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275367906.572, "dur": 2.079, + "args": { + "External id": 4057134,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4141 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275367914.185, "dur": 0.389, + "args": { + "External id": 4057135,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4142 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275367915.874, "dur": 0.400, + "args": { + "External id": 4057136,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4143 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275367917.760, "dur": 0.518, + "args": { + "External id": 4057137,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4144 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336756, "tid": 1381189, + "ts": 1655275367931.292, "dur": 29.978, + "args": { + "External id": 4057138,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 4145 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 1336756, "tid": 1381189, + "ts": 1655275368031.321, "dur": 106.623, + "args": { + "External id": 4057139,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "6423040", "8", "3", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [], [], [], [], [], []], "Ev Idx": 4146 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655275368042.742, "dur": 4.531, + "args": { + "External id": 4057140,"Record function id": 0, "Concrete Inputs": ["[51384320]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4147 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 1336756, "tid": 1381189, + "ts": 1655275368052.782, "dur": 11.144, + "args": { + "External id": 4057141,"Record function id": 0, "Concrete Inputs": ["", "0", "19269120", "6423040"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 4148 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1381189, + "ts": 1655275368056.909, "dur": 6.489, + "args": { + "External id": 4057142,"Record function id": 0, "Concrete Inputs": ["", "0", "19269120", "25692160", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[51384320], [], [], [], []], "Ev Idx": 4149 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275368061.022, "dur": 0.786, + "args": { + "External id": 4057143,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "[1]", "19269120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 4150 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336756, "tid": 1381189, + "ts": 1655275368074.249, "dur": 23.247, + "args": { + "External id": 4057144,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 4151 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275368076.588, "dur": 0.510, + "args": { + "External id": 4057145,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "19269120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4152 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275368078.676, "dur": 0.480, + "args": { + "External id": 4057146,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "19269376"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4153 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275368080.785, "dur": 1.487, + "args": { + "External id": 4057147,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "19793664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4154 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275368083.715, "dur": 0.358, + "args": { + "External id": 4057148,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "20317952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4155 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275368085.327, "dur": 0.440, + "args": { + "External id": 4057149,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "20842240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4156 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275368087.105, "dur": 0.413, + "args": { + "External id": 4057150,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "21366528"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4157 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275368088.916, "dur": 0.417, + "args": { + "External id": 4057151,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "21366784"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4158 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275368090.738, "dur": 0.346, + "args": { + "External id": 4057152,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "22808576"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4159 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275368092.867, "dur": 0.321, + "args": { + "External id": 4057153,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "24250368"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4160 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336756, "tid": 1381189, + "ts": 1655275368107.677, "dur": 22.416, + "args": { + "External id": 4057154,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 4161 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 1336756, "tid": 1381189, + "ts": 1655275368185.495, "dur": 109.446, + "args": { + "External id": 4057155,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[51384320], [6423040], [], [], []], "Ev Idx": 4162 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336756, "tid": 1381189, + "ts": 1655275368207.563, "dur": 83.913, + "args": { + "External id": 4057156,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 3, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "3", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 51384320, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[6423040], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 4163, "In msg nelems": 6423040 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 1336756, "tid": 1381189, + "ts": 1655275368217.921, "dur": 69.391, + "args": { + "External id": 4057157,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[6423040]], "Ev Idx": 4164 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336756, "tid": 1381189, + "ts": 1655275368309.366, "dur": 1.948, + "args": { + "External id": 4057158,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "3", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 4165, "In msg nelems": 0, "Rank": 3, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1655275368389.128, "dur": 1643.953, + "args": { + "External id": 4057159,"Sequence number": 40618374, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 4166 + } + }, + { + "ph": "f", "id": 206, "pid": 1336756, "tid": 1381189, "ts": 1655275368389.128, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275368521.456, "dur": 106.160, + "args": { + "External id": 4057160,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [5632, 1], [5632, 1]], "Input Dims": [[65536, 2048], [2048, 5632], [65536, 5632]], "Ev Idx": 4167 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_add_mul_rsub_silu_0", "pid": 1336756, "tid": 1381189, + "ts": 1655275368665.144, "dur": 37.370, + "args": { + "External id": 4057161,"kernel_hash": "c2zszzsomz26dv2qwvmiurvgyrl5qxtyn6ocoqkdpzzhfzwqp5q6", "grid": "grid(369098752,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "369098752"], "kernel_file": "/tmp/torchinductor_cvm/2z/c2zszzsomz26dv2qwvmiurvgyrl5qxtyn6ocoqkdpzzhfzwqp5q6.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[5632, 1], [5632, 1], [5632, 1], [23068672, 5632, 1], [23068672, 5632, 1], [23068672, 5632, 1], []], "Input Dims": [[65536, 5632], [65536, 5632], [65536, 5632], [16, 4096, 5632], [16, 4096, 5632], [16, 4096, 5632], []], "Ev Idx": 4168 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 1336756, "tid": 1381189, + "ts": 1655275368718.658, "dur": 49.033, + "args": { + "External id": 4057162,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[0, 1, 2048], [0, 5632, 1], [11534336, 5632, 1]], "Input Dims": [[1, 2048, 65536], [1, 65536, 5632], [1, 2048, 5632]], "Ev Idx": 4169 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275368778.995, "dur": 33.225, + "args": { + "External id": 4057163,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 5632], [2048, 1], [2048, 1]], "Input Dims": [[5632, 65536], [65536, 2048], [5632, 2048]], "Ev Idx": 4170 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275368819.030, "dur": 45.646, + "args": { + "External id": 4057164,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 5632], [5632, 2048], [65536, 2048]], "Ev Idx": 4171 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275368872.213, "dur": 28.099, + "args": { + "External id": 4057165,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 5632], [2048, 1], [2048, 1]], "Input Dims": [[5632, 65536], [65536, 2048], [5632, 2048]], "Ev Idx": 4172 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275368906.925, "dur": 42.956, + "args": { + "External id": 4057166,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 5632], [5632, 2048], [65536, 2048]], "Ev Idx": 4173 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_1", "pid": 1336756, "tid": 1381189, + "ts": 1655275368971.245, "dur": 63.076, + "args": { + "External id": 4057167,"kernel_hash": "cjd6g3jfgntyoifzno6l2urmnhif7alxtw6zz7miov66vywxwv7d", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/jd/cjd6g3jfgntyoifzno6l2urmnhif7alxtw6zz7miov66vywxwv7d.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[65536, 2048], [65536, 2048], []], "Ev Idx": 4174 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 1336756, "tid": 1381189, + "ts": 1655275369066.598, "dur": 28.197, + "args": { + "External id": 4057168,"kernel_hash": "cxhg545cyph4gbk5vymzyh72vho7oogk3ycan2lp4cxntklp5hew", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "65536", "2048", "1", "497", "132", "True", "2048", "True", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/xh/cxhg545cyph4gbk5vymzyh72vho7oogk3ycan2lp4cxntklp5hew.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [1], [2048, 1], [2048, 1], [2048, 1], [2048, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [2048], [65536, 2048], [65536, 2048], [132, 2048], [65536, 2048], [65536], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 4175 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 1336756, "tid": 1381189, + "ts": 1655275369116.584, "dur": 18.756, + "args": { + "External id": 4057169,"kernel_hash": "cu42i6zmxtvs2i7cs6x4ixaexke3lhgdiaye5oxwm7s3u6em6co4", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "66"], "kernel_file": "/tmp/torchinductor_cvm/u4/cu42i6zmxtvs2i7cs6x4ixaexke3lhgdiaye5oxwm7s3u6em6co4.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [4096, 1, 2048], [], []], "Input Dims": [[132, 2048], [1, 2048, 2], [], []], "Ev Idx": 4176 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 1336756, "tid": 1381189, + "ts": 1655275369149.525, "dur": 14.886, + "args": { + "External id": 4057170,"kernel_hash": "ckihofrorhmzazt2wfn2dz2m5wfx3auisu2gvfo2jsepr4zyekmq", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "2"], "kernel_file": "/tmp/torchinductor_cvm/ki/ckihofrorhmzazt2wfn2dz2m5wfx3auisu2gvfo2jsepr4zyekmq.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1, 2048], [2048, 1], [], []], "Input Dims": [[1, 2048, 2], [1, 2048], [], []], "Ev Idx": 4177 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275369172.779, "dur": 35.027, + "args": { + "External id": 4057171,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 4178 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275369211.364, "dur": 34.035, + "args": { + "External id": 4057172,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 4179 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 1336756, "tid": 1381189, + "ts": 1655275369273.677, "dur": 188.053, + "args": { + "External id": 4057173,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.125", "True", "-1", "-1", "0.", "", "False", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar", "long int"], "Input Strides": [[8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [131072, 4096, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 32, 4096], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 4180 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655275369351.687, "dur": 5.592, + "args": { + "External id": 4057174,"Record function id": 0, "Concrete Inputs": ["[16, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4181 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655275369359.243, "dur": 2.210, + "args": { + "External id": 4057175,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4182 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336756, "tid": 1381189, + "ts": 1655275369498.169, "dur": 26.646, + "args": { + "External id": 4057176,"kernel_hash": "cb6oumcqb462ndf2ivcd2sc6qg6mfjahptjw4ih7cesqhfpziv3b", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/b6/cb6oumcqb462ndf2ivcd2sc6qg6mfjahptjw4ih7cesqhfpziv3b.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 4183 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336756, "tid": 1381189, + "ts": 1655275369536.809, "dur": 14.013, + "args": { + "External id": 4057177,"kernel_hash": "cb6oumcqb462ndf2ivcd2sc6qg6mfjahptjw4ih7cesqhfpziv3b", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/b6/cb6oumcqb462ndf2ivcd2sc6qg6mfjahptjw4ih7cesqhfpziv3b.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 4184 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275369560.559, "dur": 39.255, + "args": { + "External id": 4057178,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 4185 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275369606.351, "dur": 35.314, + "args": { + "External id": 4057179,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 4186 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275369649.908, "dur": 21.294, + "args": { + "External id": 4057180,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 4187 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275369676.096, "dur": 30.466, + "args": { + "External id": 4057181,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 4188 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275369713.093, "dur": 20.035, + "args": { + "External id": 4057182,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 4189 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275369740.416, "dur": 30.220, + "args": { + "External id": 4057183,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 4190 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_4", "pid": 1336756, "tid": 1381189, + "ts": 1655275369788.548, "dur": 36.165, + "args": { + "External id": 4057184,"kernel_hash": "c7pqhdjojzeazwsh5g3ibnyk4m2nfh3q73e3zc7hljz4yvhe7c4h", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/7p/c7pqhdjojzeazwsh5g3ibnyk4m2nfh3q73e3zc7hljz4yvhe7c4h.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1], []], "Input Dims": [[65536, 2048], [65536, 2048], [65536, 2048], []], "Ev Idx": 4191 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_2", "pid": 1336756, "tid": 1381189, + "ts": 1655275369848.047, "dur": 24.548, + "args": { + "External id": 4057185,"kernel_hash": "cvgvwkysjpcw75q5t3guce5bep2so25f7i5zxc6ipt5f56shof73", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "65536", "2048", "1", "497", "132", "True", "2048", "False", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/vg/cvgvwkysjpcw75q5t3guce5bep2so25f7i5zxc6ipt5f56shof73.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [1], [2048, 1], [2048, 1], [2048, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [2048], [65536, 2048], [65536, 2048], [132, 2048], [65536], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 4192 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 1336756, "tid": 1381189, + "ts": 1655275369886.650, "dur": 17.066, + "args": { + "External id": 4057186,"kernel_hash": "cu42i6zmxtvs2i7cs6x4ixaexke3lhgdiaye5oxwm7s3u6em6co4", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "66"], "kernel_file": "/tmp/torchinductor_cvm/u4/cu42i6zmxtvs2i7cs6x4ixaexke3lhgdiaye5oxwm7s3u6em6co4.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [4096, 1, 2048], [], []], "Input Dims": [[132, 2048], [1, 2048, 2], [], []], "Ev Idx": 4193 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 1336756, "tid": 1381189, + "ts": 1655275369917.904, "dur": 14.550, + "args": { + "External id": 4057187,"kernel_hash": "ckihofrorhmzazt2wfn2dz2m5wfx3auisu2gvfo2jsepr4zyekmq", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "2"], "kernel_file": "/tmp/torchinductor_cvm/ki/ckihofrorhmzazt2wfn2dz2m5wfx3auisu2gvfo2jsepr4zyekmq.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1, 2048], [2048, 1], [], []], "Input Dims": [[1, 2048, 2], [1, 2048], [], []], "Ev Idx": 4194 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_5", "pid": 1336756, "tid": 1381189, + "ts": 1655275369945.002, "dur": 15.371, + "args": { + "External id": 4057188,"kernel_hash": "cckrpn5uuxyvbancoio3sz2onrjto236n54xx4ycphq5p6r3jlfj", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/ck/cckrpn5uuxyvbancoio3sz2onrjto236n54xx4ycphq5p6r3jlfj.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [8388608, 2048, 1], []], "Input Dims": [[65536, 2048], [65536, 2048], [16, 4096, 2048], []], "Ev Idx": 4195 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275370076.650, "dur": 16.297, + "args": { + "External id": 4057189,"Record function id": 0, "Ev Idx": 4196 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275370080.027, "dur": 12.009, + "args": { + "External id": 4057190,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 4197 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275370084.439, "dur": 6.554, + "args": { + "External id": 4057191,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 4198 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275370086.386, "dur": 4.487, + "args": { + "External id": 4057192,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 4199 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275370096.982, "dur": 6.446, + "args": { + "External id": 4057193,"Record function id": 0, "Ev Idx": 4200 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275370098.208, "dur": 4.780, + "args": { + "External id": 4057194,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 4201 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275370098.909, "dur": 3.528, + "args": { + "External id": 4057195,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 4202 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275370100.104, "dur": 2.217, + "args": { + "External id": 4057196,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 4203 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275370106.670, "dur": 4.639, + "args": { + "External id": 4057197,"Record function id": 0, "Ev Idx": 4204 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275370107.965, "dur": 2.905, + "args": { + "External id": 4057198,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 4205 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275370108.619, "dur": 1.770, + "args": { + "External id": 4057199,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 4206 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275370109.215, "dur": 1.111, + "args": { + "External id": 4057200,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 4207 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275370114.378, "dur": 4.386, + "args": { + "External id": 4057201,"Record function id": 0, "Ev Idx": 4208 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275370115.331, "dur": 3.013, + "args": { + "External id": 4057202,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 4209 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275370115.873, "dur": 2.058, + "args": { + "External id": 4057203,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 4210 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275370116.783, "dur": 1.087, + "args": { + "External id": 4057204,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 4211 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275370121.779, "dur": 3.963, + "args": { + "External id": 4057205,"Record function id": 0, "Ev Idx": 4212 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275370123.188, "dur": 2.146, + "args": { + "External id": 4057206,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 4213 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275370123.911, "dur": 1.013, + "args": { + "External id": 4057207,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 4214 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275370124.189, "dur": 0.668, + "args": { + "External id": 4057208,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 4215 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275370128.831, "dur": 3.970, + "args": { + "External id": 4057209,"Record function id": 0, "Ev Idx": 4216 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275370129.973, "dur": 2.423, + "args": { + "External id": 4057210,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 4217 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275370130.437, "dur": 1.525, + "args": { + "External id": 4057211,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 4218 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275370131.148, "dur": 0.713, + "args": { + "External id": 4057212,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 4219 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275370136.021, "dur": 3.808, + "args": { + "External id": 4057213,"Record function id": 0, "Ev Idx": 4220 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275370137.083, "dur": 2.340, + "args": { + "External id": 4057214,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 4221 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275370137.928, "dur": 1.040, + "args": { + "External id": 4057215,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 4222 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275370138.206, "dur": 0.670, + "args": { + "External id": 4057216,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 4223 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275370142.852, "dur": 3.551, + "args": { + "External id": 4057217,"Record function id": 0, "Ev Idx": 4224 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275370143.977, "dur": 1.986, + "args": { + "External id": 4057218,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 4225 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275370144.430, "dur": 1.092, + "args": { + "External id": 4057219,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 4226 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275370144.829, "dur": 0.619, + "args": { + "External id": 4057220,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 4227 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275370149.327, "dur": 5.534, + "args": { + "External id": 4057221,"Record function id": 0, "Ev Idx": 4228 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275370150.203, "dur": 4.247, + "args": { + "External id": 4057222,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 4229 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275370151.070, "dur": 2.978, + "args": { + "External id": 4057223,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 4230 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275370151.583, "dur": 2.385, + "args": { + "External id": 4057224,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 4231 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RegisterPostBackwardFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1655275370158.729, "dur": 36424.634, + "args": { + "External id": 4057225,"Record function id": 0, "Sequence number": 40618373, "Fwd thread id": 1, "Ev Idx": 4232 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1655275370160.183, "dur": 36414.404, + "args": { + "External id": 4057226,"Sequence number": 40618373, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 4233 + } + }, + { + "ph": "f", "id": 207, "pid": 1336756, "tid": 1381189, "ts": 1655275370160.183, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.10)", "pid": 1336756, "tid": 1381189, + "ts": 1655275370188.422, "dur": 37.785, + "args": { + "External id": 4057227,"Record function id": 0, "Ev Idx": 4234 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.10)", "pid": 1336756, "tid": 1381189, + "ts": 1655275370233.943, "dur": 58.602, + "args": { + "External id": 4057228,"Record function id": 0, "Ev Idx": 4235 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.10)", "pid": 1336756, "tid": 1381189, + "ts": 1655275370298.836, "dur": 36267.865, + "args": { + "External id": 4057229,"Record function id": 0, "Ev Idx": 4236 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655275370383.770, "dur": 6.578, + "args": { + "External id": 4057230,"Record function id": 0, "Concrete Inputs": ["[51384320]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4237 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275370399.706, "dur": 5.183, + "args": { + "External id": 4057231,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[51384320], []], "Ev Idx": 4238 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::chunk_cat", "pid": 1336756, "tid": 1381189, + "ts": 1655275370435.993, "dur": 35259.854, + "args": { + "External id": 4057232,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [2048, 1], [2048, 1], [2048, 1], [2048, 1], [1], [2048, 1], [2048, 1], [5632, 1]], [], [], [6423040, 1]], "Input Dims": [[[2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048], [5632, 2048], [5632, 2048], [2048, 5632]], [], [], [8, 6423040]], "Ev Idx": 4239 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_chunk_cat", "pid": 1336756, "tid": 1381189, + "ts": 1655275370450.521, "dur": 35237.064, + "args": { + "External id": 4057233,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [2048, 1], [2048, 1], [2048, 1], [2048, 1], [1], [2048, 1], [2048, 1], [5632, 1]], [], [], [6423040, 1]], "Input Dims": [[[2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048], [5632, 2048], [5632, 2048], [2048, 5632]], [], [], [8, 6423040]], "Ev Idx": 4240 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655275370512.073, "dur": 16.725, + "args": { + "External id": 4057234,"Record function id": 0, "Concrete Inputs": ["[12602]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4241 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1381189, + "ts": 1655275370535.453, "dur": 35113.028, + "args": { + "External id": 4057235,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[12602], [], [], [], [], [], [], []], "Ev Idx": 4242 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336756, "tid": 1381189, + "ts": 1655275370538.315, "dur": 35109.628, + "args": { + "External id": 4057236,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[12602], [], [], [], [], [], []], "Ev Idx": 4243 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275370542.321, "dur": 5.619, + "args": { + "External id": 4057237,"Record function id": 0, "Concrete Inputs": ["[12602]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4244 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1381189, + "ts": 1655275370549.936, "dur": 35094.576, + "args": { + "External id": 4057238,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[12602], [12602], []], "Ev Idx": 4245 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 1336756, "tid": 1381189, + "ts": 1655275405781.533, "dur": 8.687, + "args": { + "External id": 4057239,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "", "", "", "False"], "Input type": ["float", "ScalarList", "", "", "", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[51384320], [], [], [], [], []], "Ev Idx": 4246 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655275405784.570, "dur": 5.289, + "args": { + "External id": 4057240,"Record function id": 0, "Concrete Inputs": ["[6423040]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4247 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_reduce_scatter_base_", "pid": 1336756, "tid": 1381189, + "ts": 1655275405819.797, "dur": 431.841, + "args": { + "External id": 4057241,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "-1"], "Input type": ["float", "float", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], [], []], "Input Dims": [[6423040], [51384320], [], [], [], []], "Ev Idx": 4248 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336756, "tid": 1381189, + "ts": 1655275405845.313, "dur": 400.770, + "args": { + "External id": 4057242,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 3, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "3", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 6423040, "Process Group Name": "0", "Input type": ["float", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[51384320], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 4249, "In msg nelems": 51384320 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_reduce_scatter_base", "pid": 1336756, "tid": 1381189, + "ts": 1655275405855.842, "dur": 384.288, + "args": { + "External id": 4057243,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[51384320]], "Ev Idx": 4250 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336756, "tid": 1381189, + "ts": 1655275406273.978, "dur": 2.703, + "args": { + "External id": 4057244,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "3", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 4251, "In msg nelems": 0, "Rank": 3, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275406340.160, "dur": 6.726, + "args": { + "External id": 4057245,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4252 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275406393.032, "dur": 2.831, + "args": { + "External id": 4057246,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "256"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4253 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275406411.566, "dur": 1.153, + "args": { + "External id": 4057247,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "524544"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4254 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275406444.604, "dur": 1.746, + "args": { + "External id": 4057248,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "1048832"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4255 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275406457.147, "dur": 1.021, + "args": { + "External id": 4057249,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "1573120"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4256 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275406467.827, "dur": 2.737, + "args": { + "External id": 4057250,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4257 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275406481.123, "dur": 0.998, + "args": { + "External id": 4057251,"Record function id": 0, "Concrete Inputs": ["", "[704, 2048]", "[2048, 1]", "2097664"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4258 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275406493.764, "dur": 1.033, + "args": { + "External id": 4057252,"Record function id": 0, "Concrete Inputs": ["", "[704, 2048]", "[2048, 1]", "3539456"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4259 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275406504.998, "dur": 1.179, + "args": { + "External id": 4057253,"Record function id": 0, "Concrete Inputs": ["", "[256, 5632]", "[5632, 1]", "4981248"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4260 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: CompiledFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1655275406600.259, "dur": 2614.829, + "args": { + "External id": 4057254,"Record function id": 0, "Ev Idx": 4261 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.9)", "pid": 1336756, "tid": 1381189, + "ts": 1655275406619.026, "dur": 976.750, + "args": { + "External id": 4057255,"Record function id": 0, "Ev Idx": 4262 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.9)", "pid": 1336756, "tid": 1381189, + "ts": 1655275406632.397, "dur": 307.055, + "args": { + "External id": 4057256,"Record function id": 0, "Ev Idx": 4263 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275406705.841, "dur": 5.170, + "args": { + "External id": 4057257,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[51384320], []], "Ev Idx": 4264 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275406713.973, "dur": 1.029, + "args": { + "External id": 4057258,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 4265 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275406716.621, "dur": 1.212, + "args": { + "External id": 4057259,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 4266 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275406719.305, "dur": 0.900, + "args": { + "External id": 4057260,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 4267 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275406721.562, "dur": 0.806, + "args": { + "External id": 4057261,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 4268 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275406723.979, "dur": 0.849, + "args": { + "External id": 4057262,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 4269 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275406726.437, "dur": 1.194, + "args": { + "External id": 4057263,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 4270 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275406729.067, "dur": 0.876, + "args": { + "External id": 4057264,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 4271 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275406731.624, "dur": 2.218, + "args": { + "External id": 4057265,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 4272 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275406735.330, "dur": 0.786, + "args": { + "External id": 4057266,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 4273 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 1336756, "tid": 1381189, + "ts": 1655275406754.832, "dur": 153.812, + "args": { + "External id": 4057267,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 4274 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 1336756, "tid": 1381189, + "ts": 1655275406770.577, "dur": 133.584, + "args": { + "External id": 4057268,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 4275 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655275406791.579, "dur": 12.609, + "args": { + "External id": 4057269,"Record function id": 0, "Concrete Inputs": ["[2133]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4276 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1381189, + "ts": 1655275406807.512, "dur": 68.984, + "args": { + "External id": 4057270,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], [], []], "Ev Idx": 4277 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336756, "tid": 1381189, + "ts": 1655275406810.366, "dur": 65.845, + "args": { + "External id": 4057271,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], []], "Ev Idx": 4278 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275406814.561, "dur": 5.845, + "args": { + "External id": 4057272,"Record function id": 0, "Concrete Inputs": ["[2133]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4279 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1381189, + "ts": 1655275406824.029, "dur": 51.587, + "args": { + "External id": 4057273,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[2133], [2133], []], "Ev Idx": 4280 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::backward_prefetch for model.layers.8", "pid": 1336756, "tid": 1381189, + "ts": 1655275407051.655, "dur": 536.792, + "args": { + "External id": 4057274,"Record function id": 0, "Ev Idx": 4281 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.8)", "pid": 1336756, "tid": 1381189, + "ts": 1655275407068.070, "dur": 507.959, + "args": { + "External id": 4057275,"Record function id": 0, "Ev Idx": 4282 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655275407123.648, "dur": 5.863, + "args": { + "External id": 4057276,"Record function id": 0, "Concrete Inputs": ["[6423040]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4283 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336756, "tid": 1381189, + "ts": 1655275407144.859, "dur": 29.750, + "args": { + "External id": 4057277,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 4284 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275407149.925, "dur": 1.429, + "args": { + "External id": 4057278,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4285 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275407153.761, "dur": 0.889, + "args": { + "External id": 4057279,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4286 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275407156.037, "dur": 0.602, + "args": { + "External id": 4057280,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4287 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275407158.399, "dur": 1.533, + "args": { + "External id": 4057281,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4288 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275407161.661, "dur": 0.416, + "args": { + "External id": 4057282,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4289 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275407163.757, "dur": 0.420, + "args": { + "External id": 4057283,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4290 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275407166.063, "dur": 0.360, + "args": { + "External id": 4057284,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4291 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275407168.043, "dur": 0.466, + "args": { + "External id": 4057285,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4292 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275407169.913, "dur": 0.558, + "args": { + "External id": 4057286,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4293 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336756, "tid": 1381189, + "ts": 1655275407183.831, "dur": 30.785, + "args": { + "External id": 4057287,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 4294 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 1336756, "tid": 1381189, + "ts": 1655275407244.820, "dur": 94.816, + "args": { + "External id": 4057288,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "6423040", "8", "3", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [], [], [], [], [], []], "Ev Idx": 4295 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655275407254.893, "dur": 2.930, + "args": { + "External id": 4057289,"Record function id": 0, "Concrete Inputs": ["[51384320]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4296 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 1336756, "tid": 1381189, + "ts": 1655275407262.938, "dur": 10.326, + "args": { + "External id": 4057290,"Record function id": 0, "Concrete Inputs": ["", "0", "19269120", "6423040"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 4297 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1381189, + "ts": 1655275407267.152, "dur": 5.679, + "args": { + "External id": 4057291,"Record function id": 0, "Concrete Inputs": ["", "0", "19269120", "25692160", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[51384320], [], [], [], []], "Ev Idx": 4298 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275407270.991, "dur": 0.421, + "args": { + "External id": 4057292,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "[1]", "19269120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 4299 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336756, "tid": 1381189, + "ts": 1655275407280.779, "dur": 24.288, + "args": { + "External id": 4057293,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 4300 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275407283.067, "dur": 2.170, + "args": { + "External id": 4057294,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "19269120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4301 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275407286.970, "dur": 0.592, + "args": { + "External id": 4057295,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "19269376"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4302 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275407289.090, "dur": 0.429, + "args": { + "External id": 4057296,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "19793664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4303 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275407291.109, "dur": 0.429, + "args": { + "External id": 4057297,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "20317952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4304 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275407293.156, "dur": 0.380, + "args": { + "External id": 4057298,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "20842240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4305 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275407295.200, "dur": 0.432, + "args": { + "External id": 4057299,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "21366528"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4306 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275407297.279, "dur": 0.376, + "args": { + "External id": 4057300,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "21366784"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4307 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275407298.873, "dur": 0.409, + "args": { + "External id": 4057301,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "22808576"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4308 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275407300.684, "dur": 1.775, + "args": { + "External id": 4057302,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "24250368"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4309 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336756, "tid": 1381189, + "ts": 1655275407313.182, "dur": 19.551, + "args": { + "External id": 4057303,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 4310 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 1336756, "tid": 1381189, + "ts": 1655275407382.567, "dur": 125.669, + "args": { + "External id": 4057304,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[51384320], [6423040], [], [], []], "Ev Idx": 4311 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336756, "tid": 1381189, + "ts": 1655275407403.612, "dur": 100.780, + "args": { + "External id": 4057305,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 3, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "3", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 51384320, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[6423040], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 4312, "In msg nelems": 6423040 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 1336756, "tid": 1381189, + "ts": 1655275407413.032, "dur": 87.083, + "args": { + "External id": 4057306,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[6423040]], "Ev Idx": 4313 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336756, "tid": 1381189, + "ts": 1655275407522.686, "dur": 1.945, + "args": { + "External id": 4057307,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "3", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 4314, "In msg nelems": 0, "Rank": 3, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1655275407602.326, "dur": 1589.870, + "args": { + "External id": 4057308,"Sequence number": 40618372, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 4315 + } + }, + { + "ph": "f", "id": 208, "pid": 1336756, "tid": 1381189, "ts": 1655275407602.326, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275407705.646, "dur": 101.714, + "args": { + "External id": 4057309,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [5632, 1], [5632, 1]], "Input Dims": [[65536, 2048], [2048, 5632], [65536, 5632]], "Ev Idx": 4316 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_add_mul_rsub_silu_0", "pid": 1336756, "tid": 1381189, + "ts": 1655275407841.947, "dur": 34.564, + "args": { + "External id": 4057310,"kernel_hash": "c2zszzsomz26dv2qwvmiurvgyrl5qxtyn6ocoqkdpzzhfzwqp5q6", "grid": "grid(369098752,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "369098752"], "kernel_file": "/tmp/torchinductor_cvm/2z/c2zszzsomz26dv2qwvmiurvgyrl5qxtyn6ocoqkdpzzhfzwqp5q6.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[5632, 1], [5632, 1], [5632, 1], [23068672, 5632, 1], [23068672, 5632, 1], [23068672, 5632, 1], []], "Input Dims": [[65536, 5632], [65536, 5632], [65536, 5632], [16, 4096, 5632], [16, 4096, 5632], [16, 4096, 5632], []], "Ev Idx": 4317 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 1336756, "tid": 1381189, + "ts": 1655275407894.396, "dur": 49.222, + "args": { + "External id": 4057311,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[0, 1, 2048], [0, 5632, 1], [11534336, 5632, 1]], "Input Dims": [[1, 2048, 65536], [1, 65536, 5632], [1, 2048, 5632]], "Ev Idx": 4318 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275407952.940, "dur": 75.297, + "args": { + "External id": 4057312,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 5632], [2048, 1], [2048, 1]], "Input Dims": [[5632, 65536], [65536, 2048], [5632, 2048]], "Ev Idx": 4319 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275408040.457, "dur": 51.147, + "args": { + "External id": 4057313,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 5632], [5632, 2048], [65536, 2048]], "Ev Idx": 4320 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275408099.555, "dur": 28.464, + "args": { + "External id": 4057314,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 5632], [2048, 1], [2048, 1]], "Input Dims": [[5632, 65536], [65536, 2048], [5632, 2048]], "Ev Idx": 4321 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275408136.618, "dur": 43.124, + "args": { + "External id": 4057315,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 5632], [5632, 2048], [65536, 2048]], "Ev Idx": 4322 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_1", "pid": 1336756, "tid": 1381189, + "ts": 1655275408203.591, "dur": 22.364, + "args": { + "External id": 4057316,"kernel_hash": "cjd6g3jfgntyoifzno6l2urmnhif7alxtw6zz7miov66vywxwv7d", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/jd/cjd6g3jfgntyoifzno6l2urmnhif7alxtw6zz7miov66vywxwv7d.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[65536, 2048], [65536, 2048], []], "Ev Idx": 4323 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 1336756, "tid": 1381189, + "ts": 1655275408242.757, "dur": 25.466, + "args": { + "External id": 4057317,"kernel_hash": "cxhg545cyph4gbk5vymzyh72vho7oogk3ycan2lp4cxntklp5hew", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "65536", "2048", "1", "497", "132", "True", "2048", "True", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/xh/cxhg545cyph4gbk5vymzyh72vho7oogk3ycan2lp4cxntklp5hew.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [1], [2048, 1], [2048, 1], [2048, 1], [2048, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [2048], [65536, 2048], [65536, 2048], [132, 2048], [65536, 2048], [65536], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 4324 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 1336756, "tid": 1381189, + "ts": 1655275408286.437, "dur": 17.237, + "args": { + "External id": 4057318,"kernel_hash": "cu42i6zmxtvs2i7cs6x4ixaexke3lhgdiaye5oxwm7s3u6em6co4", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "66"], "kernel_file": "/tmp/torchinductor_cvm/u4/cu42i6zmxtvs2i7cs6x4ixaexke3lhgdiaye5oxwm7s3u6em6co4.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [4096, 1, 2048], [], []], "Input Dims": [[132, 2048], [1, 2048, 2], [], []], "Ev Idx": 4325 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 1336756, "tid": 1381189, + "ts": 1655275408315.561, "dur": 13.962, + "args": { + "External id": 4057319,"kernel_hash": "ckihofrorhmzazt2wfn2dz2m5wfx3auisu2gvfo2jsepr4zyekmq", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "2"], "kernel_file": "/tmp/torchinductor_cvm/ki/ckihofrorhmzazt2wfn2dz2m5wfx3auisu2gvfo2jsepr4zyekmq.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1, 2048], [2048, 1], [], []], "Input Dims": [[1, 2048, 2], [1, 2048], [], []], "Ev Idx": 4326 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275408339.334, "dur": 28.246, + "args": { + "External id": 4057320,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 4327 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275408370.575, "dur": 32.719, + "args": { + "External id": 4057321,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 4328 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 1336756, "tid": 1381189, + "ts": 1655275408447.019, "dur": 170.265, + "args": { + "External id": 4057322,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.125", "True", "-1", "-1", "0.", "", "False", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar", "long int"], "Input Strides": [[8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [131072, 4096, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 32, 4096], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 4329 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655275408523.513, "dur": 6.266, + "args": { + "External id": 4057323,"Record function id": 0, "Concrete Inputs": ["[16, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4330 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655275408532.344, "dur": 2.409, + "args": { + "External id": 4057324,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4331 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336756, "tid": 1381189, + "ts": 1655275408647.555, "dur": 23.215, + "args": { + "External id": 4057325,"kernel_hash": "cb6oumcqb462ndf2ivcd2sc6qg6mfjahptjw4ih7cesqhfpziv3b", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/b6/cb6oumcqb462ndf2ivcd2sc6qg6mfjahptjw4ih7cesqhfpziv3b.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 4332 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336756, "tid": 1381189, + "ts": 1655275408682.190, "dur": 13.584, + "args": { + "External id": 4057326,"kernel_hash": "cb6oumcqb462ndf2ivcd2sc6qg6mfjahptjw4ih7cesqhfpziv3b", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/b6/cb6oumcqb462ndf2ivcd2sc6qg6mfjahptjw4ih7cesqhfpziv3b.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 4333 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275408704.106, "dur": 37.362, + "args": { + "External id": 4057327,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 4334 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275408749.866, "dur": 34.865, + "args": { + "External id": 4057328,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 4335 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275408791.472, "dur": 20.999, + "args": { + "External id": 4057329,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 4336 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275408833.279, "dur": 32.090, + "args": { + "External id": 4057330,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 4337 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275408872.040, "dur": 20.767, + "args": { + "External id": 4057331,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 4338 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275408901.676, "dur": 30.634, + "args": { + "External id": 4057332,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 4339 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_4", "pid": 1336756, "tid": 1381189, + "ts": 1655275408948.049, "dur": 20.872, + "args": { + "External id": 4057333,"kernel_hash": "c7pqhdjojzeazwsh5g3ibnyk4m2nfh3q73e3zc7hljz4yvhe7c4h", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/7p/c7pqhdjojzeazwsh5g3ibnyk4m2nfh3q73e3zc7hljz4yvhe7c4h.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1], []], "Input Dims": [[65536, 2048], [65536, 2048], [65536, 2048], []], "Ev Idx": 4340 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_2", "pid": 1336756, "tid": 1381189, + "ts": 1655275409018.887, "dur": 41.249, + "args": { + "External id": 4057334,"kernel_hash": "cvgvwkysjpcw75q5t3guce5bep2so25f7i5zxc6ipt5f56shof73", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "65536", "2048", "1", "497", "132", "True", "2048", "False", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/vg/cvgvwkysjpcw75q5t3guce5bep2so25f7i5zxc6ipt5f56shof73.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [1], [2048, 1], [2048, 1], [2048, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [2048], [65536, 2048], [65536, 2048], [132, 2048], [65536], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 4341 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 1336756, "tid": 1381189, + "ts": 1655275409085.679, "dur": 16.942, + "args": { + "External id": 4057335,"kernel_hash": "cu42i6zmxtvs2i7cs6x4ixaexke3lhgdiaye5oxwm7s3u6em6co4", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "66"], "kernel_file": "/tmp/torchinductor_cvm/u4/cu42i6zmxtvs2i7cs6x4ixaexke3lhgdiaye5oxwm7s3u6em6co4.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [4096, 1, 2048], [], []], "Input Dims": [[132, 2048], [1, 2048, 2], [], []], "Ev Idx": 4342 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 1336756, "tid": 1381189, + "ts": 1655275409120.593, "dur": 14.114, + "args": { + "External id": 4057336,"kernel_hash": "ckihofrorhmzazt2wfn2dz2m5wfx3auisu2gvfo2jsepr4zyekmq", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "2"], "kernel_file": "/tmp/torchinductor_cvm/ki/ckihofrorhmzazt2wfn2dz2m5wfx3auisu2gvfo2jsepr4zyekmq.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1, 2048], [2048, 1], [], []], "Input Dims": [[1, 2048, 2], [1, 2048], [], []], "Ev Idx": 4343 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_5", "pid": 1336756, "tid": 1381189, + "ts": 1655275409147.143, "dur": 17.493, + "args": { + "External id": 4057337,"kernel_hash": "cckrpn5uuxyvbancoio3sz2onrjto236n54xx4ycphq5p6r3jlfj", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/ck/cckrpn5uuxyvbancoio3sz2onrjto236n54xx4ycphq5p6r3jlfj.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [8388608, 2048, 1], []], "Input Dims": [[65536, 2048], [65536, 2048], [16, 4096, 2048], []], "Ev Idx": 4344 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275409237.622, "dur": 16.276, + "args": { + "External id": 4057338,"Record function id": 0, "Ev Idx": 4345 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275409241.242, "dur": 11.654, + "args": { + "External id": 4057339,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 4346 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275409245.653, "dur": 6.452, + "args": { + "External id": 4057340,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 4347 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275409247.695, "dur": 4.280, + "args": { + "External id": 4057341,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 4348 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275409257.582, "dur": 7.251, + "args": { + "External id": 4057342,"Record function id": 0, "Ev Idx": 4349 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275409259.206, "dur": 5.154, + "args": { + "External id": 4057343,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 4350 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275409260.206, "dur": 3.705, + "args": { + "External id": 4057344,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 4351 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275409261.029, "dur": 2.788, + "args": { + "External id": 4057345,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 4352 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275409268.023, "dur": 7.795, + "args": { + "External id": 4057346,"Record function id": 0, "Ev Idx": 4353 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275409272.320, "dur": 3.087, + "args": { + "External id": 4057347,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 4354 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275409273.158, "dur": 1.839, + "args": { + "External id": 4057348,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 4355 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275409273.735, "dur": 1.183, + "args": { + "External id": 4057349,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 4356 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275409279.218, "dur": 4.761, + "args": { + "External id": 4057350,"Record function id": 0, "Ev Idx": 4357 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275409280.792, "dur": 2.768, + "args": { + "External id": 4057351,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 4358 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275409281.639, "dur": 1.528, + "args": { + "External id": 4057352,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 4359 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275409282.365, "dur": 0.719, + "args": { + "External id": 4057353,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 4360 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275409287.081, "dur": 3.814, + "args": { + "External id": 4057354,"Record function id": 0, "Ev Idx": 4361 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275409288.443, "dur": 2.048, + "args": { + "External id": 4057355,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 4362 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275409288.924, "dur": 1.154, + "args": { + "External id": 4057356,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 4363 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275409289.311, "dur": 0.705, + "args": { + "External id": 4057357,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 4364 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275409294.056, "dur": 3.735, + "args": { + "External id": 4057358,"Record function id": 0, "Ev Idx": 4365 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275409295.245, "dur": 2.111, + "args": { + "External id": 4057359,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 4366 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275409295.728, "dur": 1.220, + "args": { + "External id": 4057360,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 4367 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275409296.159, "dur": 0.673, + "args": { + "External id": 4057361,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 4368 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275409300.969, "dur": 3.251, + "args": { + "External id": 4057362,"Record function id": 0, "Ev Idx": 4369 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275409302.090, "dur": 1.730, + "args": { + "External id": 4057363,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 4370 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275409302.539, "dur": 0.862, + "args": { + "External id": 4057364,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 4371 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275409302.820, "dur": 0.486, + "args": { + "External id": 4057365,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 4372 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275409307.217, "dur": 3.169, + "args": { + "External id": 4057366,"Record function id": 0, "Ev Idx": 4373 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275409308.108, "dur": 1.873, + "args": { + "External id": 4057367,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 4374 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275409308.689, "dur": 0.906, + "args": { + "External id": 4057368,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 4375 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275409309.070, "dur": 0.460, + "args": { + "External id": 4057369,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 4376 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275409313.318, "dur": 5.285, + "args": { + "External id": 4057370,"Record function id": 0, "Ev Idx": 4377 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275409314.373, "dur": 3.816, + "args": { + "External id": 4057371,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 4378 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275409314.852, "dur": 2.933, + "args": { + "External id": 4057372,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 4379 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275409315.604, "dur": 2.088, + "args": { + "External id": 4057373,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 4380 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RegisterPostBackwardFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1655275409322.046, "dur": 36333.678, + "args": { + "External id": 4057374,"Record function id": 0, "Sequence number": 40618371, "Fwd thread id": 1, "Ev Idx": 4381 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1655275409323.570, "dur": 36323.571, + "args": { + "External id": 4057375,"Sequence number": 40618371, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 4382 + } + }, + { + "ph": "f", "id": 209, "pid": 1336756, "tid": 1381189, "ts": 1655275409323.570, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.9)", "pid": 1336756, "tid": 1381189, + "ts": 1655275409354.799, "dur": 37.533, + "args": { + "External id": 4057376,"Record function id": 0, "Ev Idx": 4383 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.9)", "pid": 1336756, "tid": 1381189, + "ts": 1655275409399.953, "dur": 75.636, + "args": { + "External id": 4057377,"Record function id": 0, "Ev Idx": 4384 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.9)", "pid": 1336756, "tid": 1381189, + "ts": 1655275409484.163, "dur": 36154.785, + "args": { + "External id": 4057378,"Record function id": 0, "Ev Idx": 4385 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655275409571.124, "dur": 6.289, + "args": { + "External id": 4057379,"Record function id": 0, "Concrete Inputs": ["[51384320]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4386 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275409588.121, "dur": 5.171, + "args": { + "External id": 4057380,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[51384320], []], "Ev Idx": 4387 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::chunk_cat", "pid": 1336756, "tid": 1381189, + "ts": 1655275409607.187, "dur": 35206.778, + "args": { + "External id": 4057381,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [2048, 1], [2048, 1], [2048, 1], [2048, 1], [1], [2048, 1], [2048, 1], [5632, 1]], [], [], [6423040, 1]], "Input Dims": [[[2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048], [5632, 2048], [5632, 2048], [2048, 5632]], [], [], [8, 6423040]], "Ev Idx": 4388 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_chunk_cat", "pid": 1336756, "tid": 1381189, + "ts": 1655275409620.440, "dur": 35184.715, + "args": { + "External id": 4057382,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [2048, 1], [2048, 1], [2048, 1], [2048, 1], [1], [2048, 1], [2048, 1], [5632, 1]], [], [], [6423040, 1]], "Input Dims": [[[2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048], [5632, 2048], [5632, 2048], [2048, 5632]], [], [], [8, 6423040]], "Ev Idx": 4389 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655275409667.130, "dur": 13.896, + "args": { + "External id": 4057383,"Record function id": 0, "Concrete Inputs": ["[12602]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4390 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1381189, + "ts": 1655275409687.510, "dur": 35077.398, + "args": { + "External id": 4057384,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[12602], [], [], [], [], [], [], []], "Ev Idx": 4391 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336756, "tid": 1381189, + "ts": 1655275409690.406, "dur": 35073.838, + "args": { + "External id": 4057385,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[12602], [], [], [], [], [], []], "Ev Idx": 4392 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275409694.423, "dur": 4.605, + "args": { + "External id": 4057386,"Record function id": 0, "Concrete Inputs": ["[12602]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4393 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1381189, + "ts": 1655275409700.683, "dur": 35059.813, + "args": { + "External id": 4057387,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[12602], [12602], []], "Ev Idx": 4394 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 1336756, "tid": 1381189, + "ts": 1655275444904.965, "dur": 9.388, + "args": { + "External id": 4057388,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "", "", "", "False"], "Input type": ["float", "ScalarList", "", "", "", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[51384320], [], [], [], [], []], "Ev Idx": 4395 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655275444908.287, "dur": 5.695, + "args": { + "External id": 4057389,"Record function id": 0, "Concrete Inputs": ["[6423040]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4396 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_reduce_scatter_base_", "pid": 1336756, "tid": 1381189, + "ts": 1655275444945.646, "dur": 386.822, + "args": { + "External id": 4057390,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "-1"], "Input type": ["float", "float", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], [], []], "Input Dims": [[6423040], [51384320], [], [], [], []], "Ev Idx": 4397 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336756, "tid": 1381189, + "ts": 1655275444971.088, "dur": 356.221, + "args": { + "External id": 4057391,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 3, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "3", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 6423040, "Process Group Name": "0", "Input type": ["float", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[51384320], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 4398, "In msg nelems": 51384320 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_reduce_scatter_base", "pid": 1336756, "tid": 1381189, + "ts": 1655275445007.348, "dur": 313.995, + "args": { + "External id": 4057392,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[51384320]], "Ev Idx": 4399 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336756, "tid": 1381189, + "ts": 1655275445353.955, "dur": 2.744, + "args": { + "External id": 4057393,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "3", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 4400, "In msg nelems": 0, "Rank": 3, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275445434.284, "dur": 7.189, + "args": { + "External id": 4057394,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4401 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275445489.448, "dur": 3.197, + "args": { + "External id": 4057395,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "256"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4402 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275445507.203, "dur": 0.732, + "args": { + "External id": 4057396,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "524544"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4403 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275445518.733, "dur": 1.006, + "args": { + "External id": 4057397,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "1048832"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4404 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275445530.745, "dur": 1.075, + "args": { + "External id": 4057398,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "1573120"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4405 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275445542.000, "dur": 2.504, + "args": { + "External id": 4057399,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4406 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275445554.509, "dur": 1.025, + "args": { + "External id": 4057400,"Record function id": 0, "Concrete Inputs": ["", "[704, 2048]", "[2048, 1]", "2097664"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4407 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275445565.986, "dur": 0.824, + "args": { + "External id": 4057401,"Record function id": 0, "Concrete Inputs": ["", "[704, 2048]", "[2048, 1]", "3539456"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4408 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275445576.363, "dur": 1.093, + "args": { + "External id": 4057402,"Record function id": 0, "Concrete Inputs": ["", "[256, 5632]", "[5632, 1]", "4981248"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4409 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: CompiledFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1655275445671.564, "dur": 2645.190, + "args": { + "External id": 4057403,"Record function id": 0, "Ev Idx": 4410 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.8)", "pid": 1336756, "tid": 1381189, + "ts": 1655275445690.414, "dur": 997.770, + "args": { + "External id": 4057404,"Record function id": 0, "Ev Idx": 4411 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.8)", "pid": 1336756, "tid": 1381189, + "ts": 1655275445705.543, "dur": 349.847, + "args": { + "External id": 4057405,"Record function id": 0, "Ev Idx": 4412 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275445783.305, "dur": 4.044, + "args": { + "External id": 4057406,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[51384320], []], "Ev Idx": 4413 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275445790.569, "dur": 2.421, + "args": { + "External id": 4057407,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 4414 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275445794.458, "dur": 1.058, + "args": { + "External id": 4057408,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 4415 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275445797.540, "dur": 0.778, + "args": { + "External id": 4057409,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 4416 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275445799.821, "dur": 0.933, + "args": { + "External id": 4057410,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 4417 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275445802.226, "dur": 0.827, + "args": { + "External id": 4057411,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 4418 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275445804.601, "dur": 0.890, + "args": { + "External id": 4057412,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 4419 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275445806.794, "dur": 0.964, + "args": { + "External id": 4057413,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 4420 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275445809.424, "dur": 0.925, + "args": { + "External id": 4057414,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 4421 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275445811.709, "dur": 2.887, + "args": { + "External id": 4057415,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 4422 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 1336756, "tid": 1381189, + "ts": 1655275445831.699, "dur": 189.487, + "args": { + "External id": 4057416,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 4423 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 1336756, "tid": 1381189, + "ts": 1655275445847.446, "dur": 131.022, + "args": { + "External id": 4057417,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 4424 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655275445867.258, "dur": 11.780, + "args": { + "External id": 4057418,"Record function id": 0, "Concrete Inputs": ["[2133]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4425 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1381189, + "ts": 1655275445882.244, "dur": 69.004, + "args": { + "External id": 4057419,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], [], []], "Ev Idx": 4426 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336756, "tid": 1381189, + "ts": 1655275445884.668, "dur": 66.298, + "args": { + "External id": 4057420,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], []], "Ev Idx": 4427 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275445888.692, "dur": 5.941, + "args": { + "External id": 4057421,"Record function id": 0, "Concrete Inputs": ["[2133]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4428 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1381189, + "ts": 1655275445898.051, "dur": 52.141, + "args": { + "External id": 4057422,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[2133], [2133], []], "Ev Idx": 4429 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::backward_prefetch for model.layers.7", "pid": 1336756, "tid": 1381189, + "ts": 1655275446132.200, "dur": 548.037, + "args": { + "External id": 4057423,"Record function id": 0, "Ev Idx": 4430 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.7)", "pid": 1336756, "tid": 1381189, + "ts": 1655275446148.622, "dur": 519.444, + "args": { + "External id": 4057424,"Record function id": 0, "Ev Idx": 4431 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655275446207.897, "dur": 5.212, + "args": { + "External id": 4057425,"Record function id": 0, "Concrete Inputs": ["[6423040]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4432 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336756, "tid": 1381189, + "ts": 1655275446228.842, "dur": 26.413, + "args": { + "External id": 4057426,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 4433 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275446234.267, "dur": 1.646, + "args": { + "External id": 4057427,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4434 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275446237.714, "dur": 0.783, + "args": { + "External id": 4057428,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4435 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275446239.868, "dur": 0.397, + "args": { + "External id": 4057429,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4436 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275446241.632, "dur": 0.439, + "args": { + "External id": 4057430,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4437 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275446243.233, "dur": 1.706, + "args": { + "External id": 4057431,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4438 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275446246.140, "dur": 0.266, + "args": { + "External id": 4057432,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4439 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275446247.961, "dur": 0.382, + "args": { + "External id": 4057433,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4440 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275446249.901, "dur": 0.360, + "args": { + "External id": 4057434,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4441 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275446251.572, "dur": 0.359, + "args": { + "External id": 4057435,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4442 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336756, "tid": 1381189, + "ts": 1655275446264.133, "dur": 32.382, + "args": { + "External id": 4057436,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 4443 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 1336756, "tid": 1381189, + "ts": 1655275446327.140, "dur": 113.574, + "args": { + "External id": 4057437,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "6423040", "8", "3", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [], [], [], [], [], []], "Ev Idx": 4444 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655275446337.267, "dur": 2.736, + "args": { + "External id": 4057438,"Record function id": 0, "Concrete Inputs": ["[51384320]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4445 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 1336756, "tid": 1381189, + "ts": 1655275446345.273, "dur": 9.889, + "args": { + "External id": 4057439,"Record function id": 0, "Concrete Inputs": ["", "0", "19269120", "6423040"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 4446 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1381189, + "ts": 1655275446349.527, "dur": 5.212, + "args": { + "External id": 4057440,"Record function id": 0, "Concrete Inputs": ["", "0", "19269120", "25692160", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[51384320], [], [], [], []], "Ev Idx": 4447 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275446352.915, "dur": 0.626, + "args": { + "External id": 4057441,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "[1]", "19269120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 4448 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336756, "tid": 1381189, + "ts": 1655275446361.975, "dur": 22.696, + "args": { + "External id": 4057442,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 4449 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275446364.488, "dur": 0.660, + "args": { + "External id": 4057443,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "19269120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4450 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275446366.609, "dur": 1.493, + "args": { + "External id": 4057444,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "19269376"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4451 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275446369.830, "dur": 0.438, + "args": { + "External id": 4057445,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "19793664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4452 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275446371.362, "dur": 0.379, + "args": { + "External id": 4057446,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "20317952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4453 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275446373.065, "dur": 0.644, + "args": { + "External id": 4057447,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "20842240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4454 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275446375.212, "dur": 0.387, + "args": { + "External id": 4057448,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "21366528"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4455 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275446377.557, "dur": 0.337, + "args": { + "External id": 4057449,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "21366784"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4456 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275446379.440, "dur": 0.255, + "args": { + "External id": 4057450,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "22808576"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4457 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275446381.476, "dur": 0.360, + "args": { + "External id": 4057451,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "24250368"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4458 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336756, "tid": 1381189, + "ts": 1655275446397.405, "dur": 33.395, + "args": { + "External id": 4057452,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 4459 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 1336756, "tid": 1381189, + "ts": 1655275446487.545, "dur": 115.045, + "args": { + "External id": 4057453,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[51384320], [6423040], [], [], []], "Ev Idx": 4460 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336756, "tid": 1381189, + "ts": 1655275446515.080, "dur": 83.983, + "args": { + "External id": 4057454,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 3, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "3", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 51384320, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[6423040], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 4461, "In msg nelems": 6423040 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 1336756, "tid": 1381189, + "ts": 1655275446524.500, "dur": 69.476, + "args": { + "External id": 4057455,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[6423040]], "Ev Idx": 4462 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336756, "tid": 1381189, + "ts": 1655275446618.354, "dur": 1.887, + "args": { + "External id": 4057456,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "3", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 4463, "In msg nelems": 0, "Rank": 3, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1655275446694.872, "dur": 1604.135, + "args": { + "External id": 4057457,"Sequence number": 40618370, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 4464 + } + }, + { + "ph": "f", "id": 210, "pid": 1336756, "tid": 1381189, "ts": 1655275446694.872, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275446798.830, "dur": 102.605, + "args": { + "External id": 4057458,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [5632, 1], [5632, 1]], "Input Dims": [[65536, 2048], [2048, 5632], [65536, 5632]], "Ev Idx": 4465 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_add_mul_rsub_silu_0", "pid": 1336756, "tid": 1381189, + "ts": 1655275446941.670, "dur": 34.901, + "args": { + "External id": 4057459,"kernel_hash": "c2zszzsomz26dv2qwvmiurvgyrl5qxtyn6ocoqkdpzzhfzwqp5q6", "grid": "grid(369098752,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "369098752"], "kernel_file": "/tmp/torchinductor_cvm/2z/c2zszzsomz26dv2qwvmiurvgyrl5qxtyn6ocoqkdpzzhfzwqp5q6.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[5632, 1], [5632, 1], [5632, 1], [23068672, 5632, 1], [23068672, 5632, 1], [23068672, 5632, 1], []], "Input Dims": [[65536, 5632], [65536, 5632], [65536, 5632], [16, 4096, 5632], [16, 4096, 5632], [16, 4096, 5632], []], "Ev Idx": 4466 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 1336756, "tid": 1381189, + "ts": 1655275447035.831, "dur": 56.633, + "args": { + "External id": 4057460,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[0, 1, 2048], [0, 5632, 1], [11534336, 5632, 1]], "Input Dims": [[1, 2048, 65536], [1, 65536, 5632], [1, 2048, 5632]], "Ev Idx": 4467 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275447103.442, "dur": 33.136, + "args": { + "External id": 4057461,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 5632], [2048, 1], [2048, 1]], "Input Dims": [[5632, 65536], [65536, 2048], [5632, 2048]], "Ev Idx": 4468 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275447142.553, "dur": 45.279, + "args": { + "External id": 4057462,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 5632], [5632, 2048], [65536, 2048]], "Ev Idx": 4469 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275447194.113, "dur": 27.589, + "args": { + "External id": 4057463,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 5632], [2048, 1], [2048, 1]], "Input Dims": [[5632, 65536], [65536, 2048], [5632, 2048]], "Ev Idx": 4470 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275447228.406, "dur": 41.674, + "args": { + "External id": 4057464,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 5632], [5632, 2048], [65536, 2048]], "Ev Idx": 4471 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_1", "pid": 1336756, "tid": 1381189, + "ts": 1655275447297.339, "dur": 23.699, + "args": { + "External id": 4057465,"kernel_hash": "cjd6g3jfgntyoifzno6l2urmnhif7alxtw6zz7miov66vywxwv7d", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/jd/cjd6g3jfgntyoifzno6l2urmnhif7alxtw6zz7miov66vywxwv7d.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[65536, 2048], [65536, 2048], []], "Ev Idx": 4472 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 1336756, "tid": 1381189, + "ts": 1655275447339.638, "dur": 25.391, + "args": { + "External id": 4057466,"kernel_hash": "cxhg545cyph4gbk5vymzyh72vho7oogk3ycan2lp4cxntklp5hew", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "65536", "2048", "1", "497", "132", "True", "2048", "True", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/xh/cxhg545cyph4gbk5vymzyh72vho7oogk3ycan2lp4cxntklp5hew.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [1], [2048, 1], [2048, 1], [2048, 1], [2048, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [2048], [65536, 2048], [65536, 2048], [132, 2048], [65536, 2048], [65536], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 4473 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 1336756, "tid": 1381189, + "ts": 1655275447384.121, "dur": 17.606, + "args": { + "External id": 4057467,"kernel_hash": "cu42i6zmxtvs2i7cs6x4ixaexke3lhgdiaye5oxwm7s3u6em6co4", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "66"], "kernel_file": "/tmp/torchinductor_cvm/u4/cu42i6zmxtvs2i7cs6x4ixaexke3lhgdiaye5oxwm7s3u6em6co4.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [4096, 1, 2048], [], []], "Input Dims": [[132, 2048], [1, 2048, 2], [], []], "Ev Idx": 4474 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 1336756, "tid": 1381189, + "ts": 1655275447430.589, "dur": 18.021, + "args": { + "External id": 4057468,"kernel_hash": "ckihofrorhmzazt2wfn2dz2m5wfx3auisu2gvfo2jsepr4zyekmq", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "2"], "kernel_file": "/tmp/torchinductor_cvm/ki/ckihofrorhmzazt2wfn2dz2m5wfx3auisu2gvfo2jsepr4zyekmq.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1, 2048], [2048, 1], [], []], "Input Dims": [[1, 2048, 2], [1, 2048], [], []], "Ev Idx": 4475 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275447458.878, "dur": 31.666, + "args": { + "External id": 4057469,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 4476 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275447493.656, "dur": 32.999, + "args": { + "External id": 4057470,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 4477 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 1336756, "tid": 1381189, + "ts": 1655275447555.423, "dur": 168.111, + "args": { + "External id": 4057471,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.125", "True", "-1", "-1", "0.", "", "False", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar", "long int"], "Input Strides": [[8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [131072, 4096, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 32, 4096], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 4478 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655275447631.433, "dur": 5.976, + "args": { + "External id": 4057472,"Record function id": 0, "Concrete Inputs": ["[16, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4479 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655275447639.537, "dur": 2.079, + "args": { + "External id": 4057473,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4480 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336756, "tid": 1381189, + "ts": 1655275447755.295, "dur": 25.093, + "args": { + "External id": 4057474,"kernel_hash": "cb6oumcqb462ndf2ivcd2sc6qg6mfjahptjw4ih7cesqhfpziv3b", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/b6/cb6oumcqb462ndf2ivcd2sc6qg6mfjahptjw4ih7cesqhfpziv3b.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 4481 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336756, "tid": 1381189, + "ts": 1655275447791.875, "dur": 14.147, + "args": { + "External id": 4057475,"kernel_hash": "cb6oumcqb462ndf2ivcd2sc6qg6mfjahptjw4ih7cesqhfpziv3b", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/b6/cb6oumcqb462ndf2ivcd2sc6qg6mfjahptjw4ih7cesqhfpziv3b.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 4482 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275447814.086, "dur": 44.917, + "args": { + "External id": 4057476,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 4483 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275447866.300, "dur": 36.653, + "args": { + "External id": 4057477,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 4484 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275447909.476, "dur": 21.023, + "args": { + "External id": 4057478,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 4485 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275447935.559, "dur": 30.287, + "args": { + "External id": 4057479,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 4486 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275447971.204, "dur": 58.381, + "args": { + "External id": 4057480,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 4487 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275448041.085, "dur": 35.129, + "args": { + "External id": 4057481,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 4488 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_4", "pid": 1336756, "tid": 1381189, + "ts": 1655275448094.829, "dur": 35.682, + "args": { + "External id": 4057482,"kernel_hash": "c7pqhdjojzeazwsh5g3ibnyk4m2nfh3q73e3zc7hljz4yvhe7c4h", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/7p/c7pqhdjojzeazwsh5g3ibnyk4m2nfh3q73e3zc7hljz4yvhe7c4h.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1], []], "Input Dims": [[65536, 2048], [65536, 2048], [65536, 2048], []], "Ev Idx": 4489 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_2", "pid": 1336756, "tid": 1381189, + "ts": 1655275448153.882, "dur": 25.077, + "args": { + "External id": 4057483,"kernel_hash": "cvgvwkysjpcw75q5t3guce5bep2so25f7i5zxc6ipt5f56shof73", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "65536", "2048", "1", "497", "132", "True", "2048", "False", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/vg/cvgvwkysjpcw75q5t3guce5bep2so25f7i5zxc6ipt5f56shof73.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [1], [2048, 1], [2048, 1], [2048, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [2048], [65536, 2048], [65536, 2048], [132, 2048], [65536], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 4490 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 1336756, "tid": 1381189, + "ts": 1655275448191.559, "dur": 17.088, + "args": { + "External id": 4057484,"kernel_hash": "cu42i6zmxtvs2i7cs6x4ixaexke3lhgdiaye5oxwm7s3u6em6co4", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "66"], "kernel_file": "/tmp/torchinductor_cvm/u4/cu42i6zmxtvs2i7cs6x4ixaexke3lhgdiaye5oxwm7s3u6em6co4.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [4096, 1, 2048], [], []], "Input Dims": [[132, 2048], [1, 2048, 2], [], []], "Ev Idx": 4491 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 1336756, "tid": 1381189, + "ts": 1655275448223.077, "dur": 17.472, + "args": { + "External id": 4057485,"kernel_hash": "ckihofrorhmzazt2wfn2dz2m5wfx3auisu2gvfo2jsepr4zyekmq", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "2"], "kernel_file": "/tmp/torchinductor_cvm/ki/ckihofrorhmzazt2wfn2dz2m5wfx3auisu2gvfo2jsepr4zyekmq.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1, 2048], [2048, 1], [], []], "Input Dims": [[1, 2048, 2], [1, 2048], [], []], "Ev Idx": 4492 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_5", "pid": 1336756, "tid": 1381189, + "ts": 1655275448252.217, "dur": 14.421, + "args": { + "External id": 4057486,"kernel_hash": "cckrpn5uuxyvbancoio3sz2onrjto236n54xx4ycphq5p6r3jlfj", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/ck/cckrpn5uuxyvbancoio3sz2onrjto236n54xx4ycphq5p6r3jlfj.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [8388608, 2048, 1], []], "Input Dims": [[65536, 2048], [65536, 2048], [16, 4096, 2048], []], "Ev Idx": 4493 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275448338.812, "dur": 18.761, + "args": { + "External id": 4057487,"Record function id": 0, "Ev Idx": 4494 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275448342.151, "dur": 14.432, + "args": { + "External id": 4057488,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 4495 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275448346.312, "dur": 9.335, + "args": { + "External id": 4057489,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 4496 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275448348.044, "dur": 7.480, + "args": { + "External id": 4057490,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 4497 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275448361.623, "dur": 5.269, + "args": { + "External id": 4057491,"Record function id": 0, "Ev Idx": 4498 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275448362.980, "dur": 3.456, + "args": { + "External id": 4057492,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 4499 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275448363.701, "dur": 2.233, + "args": { + "External id": 4057493,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 4500 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275448364.640, "dur": 1.192, + "args": { + "External id": 4057494,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 4501 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275448370.005, "dur": 5.537, + "args": { + "External id": 4057495,"Record function id": 0, "Ev Idx": 4502 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275448371.501, "dur": 3.627, + "args": { + "External id": 4057496,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 4503 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275448372.083, "dur": 2.548, + "args": { + "External id": 4057497,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 4504 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275448372.472, "dur": 2.088, + "args": { + "External id": 4057498,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 4505 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275448378.683, "dur": 4.195, + "args": { + "External id": 4057499,"Record function id": 0, "Ev Idx": 4506 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275448380.041, "dur": 2.414, + "args": { + "External id": 4057500,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 4507 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275448380.841, "dur": 1.179, + "args": { + "External id": 4057501,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 4508 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275448381.345, "dur": 0.606, + "args": { + "External id": 4057502,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 4509 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275448386.045, "dur": 4.022, + "args": { + "External id": 4057503,"Record function id": 0, "Ev Idx": 4510 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275448387.311, "dur": 2.340, + "args": { + "External id": 4057504,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 4511 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275448388.053, "dur": 1.174, + "args": { + "External id": 4057505,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 4512 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275448388.338, "dur": 0.821, + "args": { + "External id": 4057506,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 4513 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275448393.158, "dur": 4.537, + "args": { + "External id": 4057507,"Record function id": 0, "Ev Idx": 4514 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275448394.422, "dur": 2.839, + "args": { + "External id": 4057508,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 4515 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275448395.027, "dur": 1.783, + "args": { + "External id": 4057509,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 4516 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275448395.581, "dur": 1.100, + "args": { + "External id": 4057510,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 4517 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275448400.948, "dur": 3.838, + "args": { + "External id": 4057511,"Record function id": 0, "Ev Idx": 4518 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275448402.183, "dur": 2.186, + "args": { + "External id": 4057512,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 4519 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275448402.693, "dur": 1.276, + "args": { + "External id": 4057513,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 4520 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275448402.947, "dur": 0.955, + "args": { + "External id": 4057514,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 4521 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275448407.918, "dur": 25.099, + "args": { + "External id": 4057515,"Record function id": 0, "Ev Idx": 4522 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275448412.427, "dur": 19.144, + "args": { + "External id": 4057516,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 4523 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275448413.145, "dur": 1.351, + "args": { + "External id": 4057517,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 4524 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275448413.642, "dur": 0.763, + "args": { + "External id": 4057518,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 4525 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275448438.434, "dur": 5.601, + "args": { + "External id": 4057519,"Record function id": 0, "Ev Idx": 4526 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275448440.001, "dur": 3.637, + "args": { + "External id": 4057520,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 4527 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275448441.300, "dur": 1.905, + "args": { + "External id": 4057521,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 4528 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275448441.885, "dur": 1.197, + "args": { + "External id": 4057522,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 4529 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RegisterPostBackwardFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1655275448447.467, "dur": 37885.609, + "args": { + "External id": 4057523,"Record function id": 0, "Sequence number": 40618369, "Fwd thread id": 1, "Ev Idx": 4530 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1655275448448.601, "dur": 37876.008, + "args": { + "External id": 4057524,"Sequence number": 40618369, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 4531 + } + }, + { + "ph": "f", "id": 211, "pid": 1336756, "tid": 1381189, "ts": 1655275448448.601, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.8)", "pid": 1336756, "tid": 1381189, + "ts": 1655275448478.286, "dur": 38.575, + "args": { + "External id": 4057525,"Record function id": 0, "Ev Idx": 4532 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.8)", "pid": 1336756, "tid": 1381189, + "ts": 1655275448525.303, "dur": 59.709, + "args": { + "External id": 4057526,"Record function id": 0, "Ev Idx": 4533 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.8)", "pid": 1336756, "tid": 1381189, + "ts": 1655275448590.568, "dur": 37725.812, + "args": { + "External id": 4057527,"Record function id": 0, "Ev Idx": 4534 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655275448678.490, "dur": 6.188, + "args": { + "External id": 4057528,"Record function id": 0, "Concrete Inputs": ["[51384320]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4535 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275448694.181, "dur": 5.563, + "args": { + "External id": 4057529,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[51384320], []], "Ev Idx": 4536 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::chunk_cat", "pid": 1336756, "tid": 1381189, + "ts": 1655275448713.140, "dur": 36758.368, + "args": { + "External id": 4057530,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [2048, 1], [2048, 1], [2048, 1], [2048, 1], [1], [2048, 1], [2048, 1], [5632, 1]], [], [], [6423040, 1]], "Input Dims": [[[2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048], [5632, 2048], [5632, 2048], [2048, 5632]], [], [], [8, 6423040]], "Ev Idx": 4537 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_chunk_cat", "pid": 1336756, "tid": 1381189, + "ts": 1655275448726.293, "dur": 36736.499, + "args": { + "External id": 4057531,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [2048, 1], [2048, 1], [2048, 1], [2048, 1], [1], [2048, 1], [2048, 1], [5632, 1]], [], [], [6423040, 1]], "Input Dims": [[[2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048], [5632, 2048], [5632, 2048], [2048, 5632]], [], [], [8, 6423040]], "Ev Idx": 4538 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655275448777.574, "dur": 13.228, + "args": { + "External id": 4057532,"Record function id": 0, "Concrete Inputs": ["[12602]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4539 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1381189, + "ts": 1655275448796.858, "dur": 36628.022, + "args": { + "External id": 4057533,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[12602], [], [], [], [], [], [], []], "Ev Idx": 4540 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336756, "tid": 1381189, + "ts": 1655275448799.653, "dur": 36614.280, + "args": { + "External id": 4057534,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[12602], [], [], [], [], [], []], "Ev Idx": 4541 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275448803.619, "dur": 5.250, + "args": { + "External id": 4057535,"Record function id": 0, "Concrete Inputs": ["[12602]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4542 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1381189, + "ts": 1655275448810.468, "dur": 36599.789, + "args": { + "External id": 4057536,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[12602], [12602], []], "Ev Idx": 4543 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 1336756, "tid": 1381189, + "ts": 1655275485555.881, "dur": 10.550, + "args": { + "External id": 4057537,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "", "", "", "False"], "Input type": ["float", "ScalarList", "", "", "", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[51384320], [], [], [], [], []], "Ev Idx": 4544 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655275485560.567, "dur": 5.492, + "args": { + "External id": 4057538,"Record function id": 0, "Concrete Inputs": ["[6423040]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4545 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_reduce_scatter_base_", "pid": 1336756, "tid": 1381189, + "ts": 1655275485595.047, "dur": 432.028, + "args": { + "External id": 4057539,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "-1"], "Input type": ["float", "float", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], [], []], "Input Dims": [[6423040], [51384320], [], [], [], []], "Ev Idx": 4546 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336756, "tid": 1381189, + "ts": 1655275485622.329, "dur": 398.820, + "args": { + "External id": 4057540,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 3, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "3", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 6423040, "Process Group Name": "0", "Input type": ["float", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[51384320], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 4547, "In msg nelems": 51384320 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_reduce_scatter_base", "pid": 1336756, "tid": 1381189, + "ts": 1655275485633.461, "dur": 380.411, + "args": { + "External id": 4057541,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[51384320]], "Ev Idx": 4548 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336756, "tid": 1381189, + "ts": 1655275486051.643, "dur": 3.109, + "args": { + "External id": 4057542,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "3", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 4549, "In msg nelems": 0, "Rank": 3, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275486118.797, "dur": 7.272, + "args": { + "External id": 4057543,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4550 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275486169.140, "dur": 1.739, + "args": { + "External id": 4057544,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "256"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4551 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275486185.227, "dur": 1.094, + "args": { + "External id": 4057545,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "524544"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4552 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275486198.640, "dur": 1.017, + "args": { + "External id": 4057546,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "1048832"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4553 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275486215.179, "dur": 1.300, + "args": { + "External id": 4057547,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "1573120"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4554 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275486226.343, "dur": 0.949, + "args": { + "External id": 4057548,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4555 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275486236.923, "dur": 0.921, + "args": { + "External id": 4057549,"Record function id": 0, "Concrete Inputs": ["", "[704, 2048]", "[2048, 1]", "2097664"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4556 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275486248.251, "dur": 0.792, + "args": { + "External id": 4057550,"Record function id": 0, "Concrete Inputs": ["", "[704, 2048]", "[2048, 1]", "3539456"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4557 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275486258.101, "dur": 0.781, + "args": { + "External id": 4057551,"Record function id": 0, "Concrete Inputs": ["", "[256, 5632]", "[5632, 1]", "4981248"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4558 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: CompiledFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1655275486347.238, "dur": 2608.141, + "args": { + "External id": 4057552,"Record function id": 0, "Ev Idx": 4559 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.7)", "pid": 1336756, "tid": 1381189, + "ts": 1655275486366.528, "dur": 1004.452, + "args": { + "External id": 4057553,"Record function id": 0, "Ev Idx": 4560 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.7)", "pid": 1336756, "tid": 1381189, + "ts": 1655275486380.404, "dur": 316.780, + "args": { + "External id": 4057554,"Record function id": 0, "Ev Idx": 4561 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275486473.350, "dur": 4.743, + "args": { + "External id": 4057555,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[51384320], []], "Ev Idx": 4562 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275486481.384, "dur": 0.863, + "args": { + "External id": 4057556,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 4563 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275486485.777, "dur": 0.927, + "args": { + "External id": 4057557,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 4564 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275486488.412, "dur": 1.019, + "args": { + "External id": 4057558,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 4565 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275486491.078, "dur": 2.190, + "args": { + "External id": 4057559,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 4566 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275486494.917, "dur": 0.715, + "args": { + "External id": 4057560,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 4567 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275486499.244, "dur": 0.834, + "args": { + "External id": 4057561,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 4568 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275486501.608, "dur": 0.806, + "args": { + "External id": 4057562,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 4569 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275486504.165, "dur": 0.732, + "args": { + "External id": 4057563,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 4570 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275486506.345, "dur": 0.837, + "args": { + "External id": 4057564,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 4571 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 1336756, "tid": 1381189, + "ts": 1655275486527.262, "dur": 143.248, + "args": { + "External id": 4057565,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 4572 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 1336756, "tid": 1381189, + "ts": 1655275486543.525, "dur": 122.854, + "args": { + "External id": 4057566,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 4573 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655275486558.256, "dur": 12.046, + "args": { + "External id": 4057567,"Record function id": 0, "Concrete Inputs": ["[2133]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4574 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1381189, + "ts": 1655275486573.303, "dur": 66.597, + "args": { + "External id": 4057568,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], [], []], "Ev Idx": 4575 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336756, "tid": 1381189, + "ts": 1655275486575.786, "dur": 63.757, + "args": { + "External id": 4057569,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], []], "Ev Idx": 4576 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275486579.729, "dur": 6.238, + "args": { + "External id": 4057570,"Record function id": 0, "Concrete Inputs": ["[2133]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4577 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1381189, + "ts": 1655275486587.748, "dur": 51.088, + "args": { + "External id": 4057571,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[2133], [2133], []], "Ev Idx": 4578 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::backward_prefetch for model.layers.6", "pid": 1336756, "tid": 1381189, + "ts": 1655275486769.711, "dur": 593.577, + "args": { + "External id": 4057572,"Record function id": 0, "Ev Idx": 4579 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.6)", "pid": 1336756, "tid": 1381189, + "ts": 1655275486785.346, "dur": 566.046, + "args": { + "External id": 4057573,"Record function id": 0, "Ev Idx": 4580 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655275486838.240, "dur": 6.046, + "args": { + "External id": 4057574,"Record function id": 0, "Concrete Inputs": ["[6423040]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4581 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336756, "tid": 1381189, + "ts": 1655275486863.528, "dur": 28.262, + "args": { + "External id": 4057575,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 4582 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275486868.318, "dur": 1.977, + "args": { + "External id": 4057576,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4583 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275486872.460, "dur": 0.377, + "args": { + "External id": 4057577,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4584 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275486874.145, "dur": 0.184, + "args": { + "External id": 4057578,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4585 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275486877.152, "dur": 0.266, + "args": { + "External id": 4057579,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4586 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275486879.085, "dur": 0.557, + "args": { + "External id": 4057580,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4587 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275486881.317, "dur": 0.621, + "args": { + "External id": 4057581,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4588 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275486883.224, "dur": 0.211, + "args": { + "External id": 4057582,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4589 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275486885.560, "dur": 1.834, + "args": { + "External id": 4057583,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4590 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275486888.778, "dur": 0.585, + "args": { + "External id": 4057584,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4591 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336756, "tid": 1381189, + "ts": 1655275486900.655, "dur": 27.355, + "args": { + "External id": 4057585,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 4592 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 1336756, "tid": 1381189, + "ts": 1655275486956.378, "dur": 165.107, + "args": { + "External id": 4057586,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "6423040", "8", "3", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [], [], [], [], [], []], "Ev Idx": 4593 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655275486965.982, "dur": 3.174, + "args": { + "External id": 4057587,"Record function id": 0, "Concrete Inputs": ["[51384320]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4594 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 1336756, "tid": 1381189, + "ts": 1655275486974.056, "dur": 50.958, + "args": { + "External id": 4057588,"Record function id": 0, "Concrete Inputs": ["", "0", "19269120", "6423040"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 4595 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1381189, + "ts": 1655275486978.354, "dur": 46.179, + "args": { + "External id": 4057589,"Record function id": 0, "Concrete Inputs": ["", "0", "19269120", "25692160", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[51384320], [], [], [], []], "Ev Idx": 4596 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275487021.400, "dur": 0.943, + "args": { + "External id": 4057590,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "[1]", "19269120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 4597 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336756, "tid": 1381189, + "ts": 1655275487034.166, "dur": 24.851, + "args": { + "External id": 4057591,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 4598 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275487036.662, "dur": 0.907, + "args": { + "External id": 4057592,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "19269120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4599 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275487039.257, "dur": 0.657, + "args": { + "External id": 4057593,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "19269376"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4600 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275487041.145, "dur": 0.657, + "args": { + "External id": 4057594,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "19793664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4601 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275487043.595, "dur": 0.302, + "args": { + "External id": 4057595,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "20317952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4602 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275487045.140, "dur": 1.715, + "args": { + "External id": 4057596,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "20842240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4603 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275487048.480, "dur": 0.493, + "args": { + "External id": 4057597,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "21366528"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4604 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275487050.244, "dur": 0.762, + "args": { + "External id": 4057598,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "21366784"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4605 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275487052.384, "dur": 0.558, + "args": { + "External id": 4057599,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "22808576"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4606 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275487054.205, "dur": 0.485, + "args": { + "External id": 4057600,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "24250368"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4607 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336756, "tid": 1381189, + "ts": 1655275487090.860, "dur": 23.046, + "args": { + "External id": 4057601,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 4608 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 1336756, "tid": 1381189, + "ts": 1655275487170.038, "dur": 112.996, + "args": { + "External id": 4057602,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[51384320], [6423040], [], [], []], "Ev Idx": 4609 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336756, "tid": 1381189, + "ts": 1655275487197.805, "dur": 81.607, + "args": { + "External id": 4057603,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 3, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "3", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 51384320, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[6423040], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 4610, "In msg nelems": 6423040 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 1336756, "tid": 1381189, + "ts": 1655275487207.507, "dur": 67.800, + "args": { + "External id": 4057604,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[6423040]], "Ev Idx": 4611 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336756, "tid": 1381189, + "ts": 1655275487298.102, "dur": 2.231, + "args": { + "External id": 4057605,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "3", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 4612, "In msg nelems": 0, "Rank": 3, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1655275487378.214, "dur": 1559.276, + "args": { + "External id": 4057606,"Sequence number": 40618368, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 4613 + } + }, + { + "ph": "f", "id": 212, "pid": 1336756, "tid": 1381189, "ts": 1655275487378.214, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275487503.290, "dur": 105.829, + "args": { + "External id": 4057607,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [5632, 1], [5632, 1]], "Input Dims": [[65536, 2048], [2048, 5632], [65536, 5632]], "Ev Idx": 4614 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_add_mul_rsub_silu_0", "pid": 1336756, "tid": 1381189, + "ts": 1655275487650.357, "dur": 36.758, + "args": { + "External id": 4057608,"kernel_hash": "c2zszzsomz26dv2qwvmiurvgyrl5qxtyn6ocoqkdpzzhfzwqp5q6", "grid": "grid(369098752,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "369098752"], "kernel_file": "/tmp/torchinductor_cvm/2z/c2zszzsomz26dv2qwvmiurvgyrl5qxtyn6ocoqkdpzzhfzwqp5q6.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[5632, 1], [5632, 1], [5632, 1], [23068672, 5632, 1], [23068672, 5632, 1], [23068672, 5632, 1], []], "Input Dims": [[65536, 5632], [65536, 5632], [65536, 5632], [16, 4096, 5632], [16, 4096, 5632], [16, 4096, 5632], []], "Ev Idx": 4615 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 1336756, "tid": 1381189, + "ts": 1655275487701.709, "dur": 47.800, + "args": { + "External id": 4057609,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[0, 1, 2048], [0, 5632, 1], [11534336, 5632, 1]], "Input Dims": [[1, 2048, 65536], [1, 65536, 5632], [1, 2048, 5632]], "Ev Idx": 4616 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275487759.283, "dur": 31.777, + "args": { + "External id": 4057610,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 5632], [2048, 1], [2048, 1]], "Input Dims": [[5632, 65536], [65536, 2048], [5632, 2048]], "Ev Idx": 4617 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275487801.882, "dur": 46.370, + "args": { + "External id": 4057611,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 5632], [5632, 2048], [65536, 2048]], "Ev Idx": 4618 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275487856.830, "dur": 27.972, + "args": { + "External id": 4057612,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 5632], [2048, 1], [2048, 1]], "Input Dims": [[5632, 65536], [65536, 2048], [5632, 2048]], "Ev Idx": 4619 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275487892.867, "dur": 44.028, + "args": { + "External id": 4057613,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 5632], [5632, 2048], [65536, 2048]], "Ev Idx": 4620 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_1", "pid": 1336756, "tid": 1381189, + "ts": 1655275487959.857, "dur": 20.199, + "args": { + "External id": 4057614,"kernel_hash": "cjd6g3jfgntyoifzno6l2urmnhif7alxtw6zz7miov66vywxwv7d", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/jd/cjd6g3jfgntyoifzno6l2urmnhif7alxtw6zz7miov66vywxwv7d.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[65536, 2048], [65536, 2048], []], "Ev Idx": 4621 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 1336756, "tid": 1381189, + "ts": 1655275488044.529, "dur": 28.628, + "args": { + "External id": 4057615,"kernel_hash": "cxhg545cyph4gbk5vymzyh72vho7oogk3ycan2lp4cxntklp5hew", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "65536", "2048", "1", "497", "132", "True", "2048", "True", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/xh/cxhg545cyph4gbk5vymzyh72vho7oogk3ycan2lp4cxntklp5hew.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [1], [2048, 1], [2048, 1], [2048, 1], [2048, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [2048], [65536, 2048], [65536, 2048], [132, 2048], [65536, 2048], [65536], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 4622 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 1336756, "tid": 1381189, + "ts": 1655275488094.806, "dur": 19.027, + "args": { + "External id": 4057616,"kernel_hash": "cu42i6zmxtvs2i7cs6x4ixaexke3lhgdiaye5oxwm7s3u6em6co4", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "66"], "kernel_file": "/tmp/torchinductor_cvm/u4/cu42i6zmxtvs2i7cs6x4ixaexke3lhgdiaye5oxwm7s3u6em6co4.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [4096, 1, 2048], [], []], "Input Dims": [[132, 2048], [1, 2048, 2], [], []], "Ev Idx": 4623 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 1336756, "tid": 1381189, + "ts": 1655275488129.448, "dur": 14.000, + "args": { + "External id": 4057617,"kernel_hash": "ckihofrorhmzazt2wfn2dz2m5wfx3auisu2gvfo2jsepr4zyekmq", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "2"], "kernel_file": "/tmp/torchinductor_cvm/ki/ckihofrorhmzazt2wfn2dz2m5wfx3auisu2gvfo2jsepr4zyekmq.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1, 2048], [2048, 1], [], []], "Input Dims": [[1, 2048, 2], [1, 2048], [], []], "Ev Idx": 4624 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275488152.072, "dur": 32.313, + "args": { + "External id": 4057618,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 4625 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275488187.505, "dur": 33.213, + "args": { + "External id": 4057619,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 4626 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 1336756, "tid": 1381189, + "ts": 1655275488247.150, "dur": 163.580, + "args": { + "External id": 4057620,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.125", "True", "-1", "-1", "0.", "", "False", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar", "long int"], "Input Strides": [[8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [131072, 4096, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 32, 4096], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 4627 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655275488322.206, "dur": 7.523, + "args": { + "External id": 4057621,"Record function id": 0, "Concrete Inputs": ["[16, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4628 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655275488331.626, "dur": 2.270, + "args": { + "External id": 4057622,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4629 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336756, "tid": 1381189, + "ts": 1655275488461.142, "dur": 25.881, + "args": { + "External id": 4057623,"kernel_hash": "cb6oumcqb462ndf2ivcd2sc6qg6mfjahptjw4ih7cesqhfpziv3b", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/b6/cb6oumcqb462ndf2ivcd2sc6qg6mfjahptjw4ih7cesqhfpziv3b.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 4630 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336756, "tid": 1381189, + "ts": 1655275488498.813, "dur": 13.605, + "args": { + "External id": 4057624,"kernel_hash": "cb6oumcqb462ndf2ivcd2sc6qg6mfjahptjw4ih7cesqhfpziv3b", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/b6/cb6oumcqb462ndf2ivcd2sc6qg6mfjahptjw4ih7cesqhfpziv3b.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 4631 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275488520.556, "dur": 37.355, + "args": { + "External id": 4057625,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 4632 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275488563.634, "dur": 33.491, + "args": { + "External id": 4057626,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 4633 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275488602.738, "dur": 20.327, + "args": { + "External id": 4057627,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 4634 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275488628.998, "dur": 29.322, + "args": { + "External id": 4057628,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 4635 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275488663.204, "dur": 19.369, + "args": { + "External id": 4057629,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 4636 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275488689.795, "dur": 29.568, + "args": { + "External id": 4057630,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 4637 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_4", "pid": 1336756, "tid": 1381189, + "ts": 1655275488739.229, "dur": 20.547, + "args": { + "External id": 4057631,"kernel_hash": "c7pqhdjojzeazwsh5g3ibnyk4m2nfh3q73e3zc7hljz4yvhe7c4h", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/7p/c7pqhdjojzeazwsh5g3ibnyk4m2nfh3q73e3zc7hljz4yvhe7c4h.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1], []], "Input Dims": [[65536, 2048], [65536, 2048], [65536, 2048], []], "Ev Idx": 4638 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_2", "pid": 1336756, "tid": 1381189, + "ts": 1655275488775.504, "dur": 33.471, + "args": { + "External id": 4057632,"kernel_hash": "cvgvwkysjpcw75q5t3guce5bep2so25f7i5zxc6ipt5f56shof73", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "65536", "2048", "1", "497", "132", "True", "2048", "False", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/vg/cvgvwkysjpcw75q5t3guce5bep2so25f7i5zxc6ipt5f56shof73.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [1], [2048, 1], [2048, 1], [2048, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [2048], [65536, 2048], [65536, 2048], [132, 2048], [65536], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 4639 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 1336756, "tid": 1381189, + "ts": 1655275488832.529, "dur": 18.923, + "args": { + "External id": 4057633,"kernel_hash": "cu42i6zmxtvs2i7cs6x4ixaexke3lhgdiaye5oxwm7s3u6em6co4", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "66"], "kernel_file": "/tmp/torchinductor_cvm/u4/cu42i6zmxtvs2i7cs6x4ixaexke3lhgdiaye5oxwm7s3u6em6co4.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [4096, 1, 2048], [], []], "Input Dims": [[132, 2048], [1, 2048, 2], [], []], "Ev Idx": 4640 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 1336756, "tid": 1381189, + "ts": 1655275488867.068, "dur": 13.005, + "args": { + "External id": 4057634,"kernel_hash": "ckihofrorhmzazt2wfn2dz2m5wfx3auisu2gvfo2jsepr4zyekmq", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "2"], "kernel_file": "/tmp/torchinductor_cvm/ki/ckihofrorhmzazt2wfn2dz2m5wfx3auisu2gvfo2jsepr4zyekmq.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1, 2048], [2048, 1], [], []], "Input Dims": [[1, 2048, 2], [1, 2048], [], []], "Ev Idx": 4641 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_5", "pid": 1336756, "tid": 1381189, + "ts": 1655275488892.965, "dur": 14.973, + "args": { + "External id": 4057635,"kernel_hash": "cckrpn5uuxyvbancoio3sz2onrjto236n54xx4ycphq5p6r3jlfj", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/ck/cckrpn5uuxyvbancoio3sz2onrjto236n54xx4ycphq5p6r3jlfj.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [8388608, 2048, 1], []], "Input Dims": [[65536, 2048], [65536, 2048], [16, 4096, 2048], []], "Ev Idx": 4642 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275488980.916, "dur": 55.095, + "args": { + "External id": 4057636,"Record function id": 0, "Ev Idx": 4643 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275489017.726, "dur": 16.705, + "args": { + "External id": 4057637,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 4644 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275489023.265, "dur": 6.539, + "args": { + "External id": 4057638,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 4645 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275489024.784, "dur": 4.707, + "args": { + "External id": 4057639,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 4646 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275489042.048, "dur": 4.889, + "args": { + "External id": 4057640,"Record function id": 0, "Ev Idx": 4647 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275489043.668, "dur": 2.834, + "args": { + "External id": 4057641,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 4648 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275489044.554, "dur": 1.438, + "args": { + "External id": 4057642,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 4649 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275489044.855, "dur": 1.028, + "args": { + "External id": 4057643,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 4650 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275489050.120, "dur": 3.950, + "args": { + "External id": 4057644,"Record function id": 0, "Ev Idx": 4651 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275489051.262, "dur": 2.411, + "args": { + "External id": 4057645,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 4652 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275489051.942, "dur": 1.314, + "args": { + "External id": 4057646,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 4653 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275489052.581, "dur": 0.605, + "args": { + "External id": 4057647,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 4654 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275489057.237, "dur": 3.902, + "args": { + "External id": 4057648,"Record function id": 0, "Ev Idx": 4655 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275489058.381, "dur": 2.287, + "args": { + "External id": 4057649,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 4656 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275489058.948, "dur": 1.321, + "args": { + "External id": 4057650,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 4657 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275489059.556, "dur": 0.568, + "args": { + "External id": 4057651,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 4658 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275489064.170, "dur": 5.190, + "args": { + "External id": 4057652,"Record function id": 0, "Ev Idx": 4659 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275489065.216, "dur": 3.715, + "args": { + "External id": 4057653,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 4660 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275489065.717, "dur": 2.783, + "args": { + "External id": 4057654,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 4661 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275489066.028, "dur": 2.406, + "args": { + "External id": 4057655,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 4662 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275489072.366, "dur": 3.536, + "args": { + "External id": 4057656,"Record function id": 0, "Ev Idx": 4663 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275489073.456, "dur": 1.998, + "args": { + "External id": 4057657,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 4664 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275489073.987, "dur": 1.059, + "args": { + "External id": 4057658,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 4665 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275489074.243, "dur": 0.705, + "args": { + "External id": 4057659,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 4666 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275489079.051, "dur": 3.401, + "args": { + "External id": 4057660,"Record function id": 0, "Ev Idx": 4667 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275489079.961, "dur": 2.065, + "args": { + "External id": 4057661,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 4668 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275489080.483, "dur": 1.148, + "args": { + "External id": 4057662,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 4669 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275489080.902, "dur": 0.660, + "args": { + "External id": 4057663,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 4670 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275489085.430, "dur": 3.172, + "args": { + "External id": 4057664,"Record function id": 0, "Ev Idx": 4671 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275489086.348, "dur": 1.843, + "args": { + "External id": 4057665,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 4672 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275489087.035, "dur": 0.765, + "args": { + "External id": 4057666,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 4673 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275489087.288, "dur": 0.438, + "args": { + "External id": 4057667,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 4674 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275489091.546, "dur": 4.809, + "args": { + "External id": 4057668,"Record function id": 0, "Ev Idx": 4675 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275489092.455, "dur": 3.463, + "args": { + "External id": 4057669,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 4676 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275489092.979, "dur": 2.510, + "args": { + "External id": 4057670,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 4677 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275489094.717, "dur": 0.700, + "args": { + "External id": 4057671,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 4678 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RegisterPostBackwardFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1655275489103.180, "dur": 36420.353, + "args": { + "External id": 4057672,"Record function id": 0, "Sequence number": 40618367, "Fwd thread id": 1, "Ev Idx": 4679 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1655275489104.436, "dur": 36410.916, + "args": { + "External id": 4057673,"Sequence number": 40618367, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 4680 + } + }, + { + "ph": "f", "id": 213, "pid": 1336756, "tid": 1381189, "ts": 1655275489104.436, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.7)", "pid": 1336756, "tid": 1381189, + "ts": 1655275489132.898, "dur": 35.433, + "args": { + "External id": 4057674,"Record function id": 0, "Ev Idx": 4681 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.7)", "pid": 1336756, "tid": 1381189, + "ts": 1655275489175.879, "dur": 58.629, + "args": { + "External id": 4057675,"Record function id": 0, "Ev Idx": 4682 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.7)", "pid": 1336756, "tid": 1381189, + "ts": 1655275489239.869, "dur": 36266.800, + "args": { + "External id": 4057676,"Record function id": 0, "Ev Idx": 4683 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655275489325.809, "dur": 6.713, + "args": { + "External id": 4057677,"Record function id": 0, "Concrete Inputs": ["[51384320]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4684 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275489341.900, "dur": 4.825, + "args": { + "External id": 4057678,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[51384320], []], "Ev Idx": 4685 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::chunk_cat", "pid": 1336756, "tid": 1381189, + "ts": 1655275489360.243, "dur": 35356.124, + "args": { + "External id": 4057679,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [2048, 1], [2048, 1], [2048, 1], [2048, 1], [1], [2048, 1], [2048, 1], [5632, 1]], [], [], [6423040, 1]], "Input Dims": [[[2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048], [5632, 2048], [5632, 2048], [2048, 5632]], [], [], [8, 6423040]], "Ev Idx": 4686 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_chunk_cat", "pid": 1336756, "tid": 1381189, + "ts": 1655275489373.319, "dur": 35334.085, + "args": { + "External id": 4057680,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [2048, 1], [2048, 1], [2048, 1], [2048, 1], [1], [2048, 1], [2048, 1], [5632, 1]], [], [], [6423040, 1]], "Input Dims": [[[2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048], [5632, 2048], [5632, 2048], [2048, 5632]], [], [], [8, 6423040]], "Ev Idx": 4687 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655275489436.725, "dur": 13.892, + "args": { + "External id": 4057681,"Record function id": 0, "Concrete Inputs": ["[12602]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4688 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1381189, + "ts": 1655275489457.460, "dur": 35211.537, + "args": { + "External id": 4057682,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[12602], [], [], [], [], [], [], []], "Ev Idx": 4689 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336756, "tid": 1381189, + "ts": 1655275489460.023, "dur": 35208.259, + "args": { + "External id": 4057683,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[12602], [], [], [], [], [], []], "Ev Idx": 4690 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275489463.864, "dur": 7.650, + "args": { + "External id": 4057684,"Record function id": 0, "Concrete Inputs": ["[12602]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4691 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1381189, + "ts": 1655275489473.192, "dur": 35191.389, + "args": { + "External id": 4057685,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[12602], [12602], []], "Ev Idx": 4692 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 1336756, "tid": 1381189, + "ts": 1655275524800.509, "dur": 9.720, + "args": { + "External id": 4057686,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "", "", "", "False"], "Input type": ["float", "ScalarList", "", "", "", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[51384320], [], [], [], [], []], "Ev Idx": 4693 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655275524803.212, "dur": 6.643, + "args": { + "External id": 4057687,"Record function id": 0, "Concrete Inputs": ["[6423040]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4694 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_reduce_scatter_base_", "pid": 1336756, "tid": 1381189, + "ts": 1655275524839.287, "dur": 369.775, + "args": { + "External id": 4057688,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "-1"], "Input type": ["float", "float", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], [], []], "Input Dims": [[6423040], [51384320], [], [], [], []], "Ev Idx": 4695 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336756, "tid": 1381189, + "ts": 1655275524866.620, "dur": 336.959, + "args": { + "External id": 4057689,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 3, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "3", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 6423040, "Process Group Name": "0", "Input type": ["float", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[51384320], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 4696, "In msg nelems": 51384320 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_reduce_scatter_base", "pid": 1336756, "tid": 1381189, + "ts": 1655275524877.360, "dur": 320.422, + "args": { + "External id": 4057690,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[51384320]], "Ev Idx": 4697 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336756, "tid": 1381189, + "ts": 1655275525231.654, "dur": 2.126, + "args": { + "External id": 4057691,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "3", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 4698, "In msg nelems": 0, "Rank": 3, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275525291.924, "dur": 6.758, + "args": { + "External id": 4057692,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4699 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275525342.598, "dur": 1.159, + "args": { + "External id": 4057693,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "256"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4700 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275525358.251, "dur": 1.219, + "args": { + "External id": 4057694,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "524544"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4701 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275525370.543, "dur": 2.780, + "args": { + "External id": 4057695,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "1048832"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4702 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275525384.622, "dur": 0.717, + "args": { + "External id": 4057696,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "1573120"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4703 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275525394.642, "dur": 0.757, + "args": { + "External id": 4057697,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4704 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275525404.615, "dur": 0.716, + "args": { + "External id": 4057698,"Record function id": 0, "Concrete Inputs": ["", "[704, 2048]", "[2048, 1]", "2097664"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4705 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275525429.978, "dur": 2.886, + "args": { + "External id": 4057699,"Record function id": 0, "Concrete Inputs": ["", "[704, 2048]", "[2048, 1]", "3539456"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4706 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275525446.748, "dur": 1.165, + "args": { + "External id": 4057700,"Record function id": 0, "Concrete Inputs": ["", "[256, 5632]", "[5632, 1]", "4981248"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4707 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: CompiledFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1655275525538.942, "dur": 2583.386, + "args": { + "External id": 4057701,"Record function id": 0, "Ev Idx": 4708 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.6)", "pid": 1336756, "tid": 1381189, + "ts": 1655275525557.206, "dur": 974.239, + "args": { + "External id": 4057702,"Record function id": 0, "Ev Idx": 4709 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.6)", "pid": 1336756, "tid": 1381189, + "ts": 1655275525570.773, "dur": 294.180, + "args": { + "External id": 4057703,"Record function id": 0, "Ev Idx": 4710 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275525643.645, "dur": 3.898, + "args": { + "External id": 4057704,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[51384320], []], "Ev Idx": 4711 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275525650.449, "dur": 0.928, + "args": { + "External id": 4057705,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 4712 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275525654.166, "dur": 0.817, + "args": { + "External id": 4057706,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 4713 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275525656.647, "dur": 0.771, + "args": { + "External id": 4057707,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 4714 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275525658.839, "dur": 0.886, + "args": { + "External id": 4057708,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 4715 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275525661.212, "dur": 2.219, + "args": { + "External id": 4057709,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 4716 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275525666.451, "dur": 1.020, + "args": { + "External id": 4057710,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 4717 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275525668.784, "dur": 0.493, + "args": { + "External id": 4057711,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 4718 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275525670.662, "dur": 0.884, + "args": { + "External id": 4057712,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 4719 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275525673.061, "dur": 0.703, + "args": { + "External id": 4057713,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 4720 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 1336756, "tid": 1381189, + "ts": 1655275525693.876, "dur": 144.950, + "args": { + "External id": 4057714,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 4721 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 1336756, "tid": 1381189, + "ts": 1655275525709.633, "dur": 124.669, + "args": { + "External id": 4057715,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 4722 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655275525725.620, "dur": 11.967, + "args": { + "External id": 4057716,"Record function id": 0, "Concrete Inputs": ["[2133]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4723 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1381189, + "ts": 1655275525740.572, "dur": 66.911, + "args": { + "External id": 4057717,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], [], []], "Ev Idx": 4724 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336756, "tid": 1381189, + "ts": 1655275525742.871, "dur": 64.355, + "args": { + "External id": 4057718,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], []], "Ev Idx": 4725 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275525749.120, "dur": 5.780, + "args": { + "External id": 4057719,"Record function id": 0, "Concrete Inputs": ["[2133]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4726 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1381189, + "ts": 1655275525756.658, "dur": 49.942, + "args": { + "External id": 4057720,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[2133], [2133], []], "Ev Idx": 4727 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::backward_prefetch for model.layers.5", "pid": 1336756, "tid": 1381189, + "ts": 1655275525932.554, "dur": 591.644, + "args": { + "External id": 4057721,"Record function id": 0, "Ev Idx": 4728 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.5)", "pid": 1336756, "tid": 1381189, + "ts": 1655275525946.462, "dur": 565.955, + "args": { + "External id": 4057722,"Record function id": 0, "Ev Idx": 4729 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655275526035.357, "dur": 6.404, + "args": { + "External id": 4057723,"Record function id": 0, "Concrete Inputs": ["[6423040]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4730 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336756, "tid": 1381189, + "ts": 1655275526062.642, "dur": 28.901, + "args": { + "External id": 4057724,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 4731 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275526067.234, "dur": 3.177, + "args": { + "External id": 4057725,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4732 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275526072.421, "dur": 0.655, + "args": { + "External id": 4057726,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4733 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275526075.972, "dur": 0.410, + "args": { + "External id": 4057727,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4734 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275526077.814, "dur": 0.176, + "args": { + "External id": 4057728,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4735 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275526079.528, "dur": 0.780, + "args": { + "External id": 4057729,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4736 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275526081.486, "dur": 0.192, + "args": { + "External id": 4057730,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4737 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275526082.909, "dur": 0.305, + "args": { + "External id": 4057731,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4738 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275526085.356, "dur": 0.276, + "args": { + "External id": 4057732,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4739 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275526087.083, "dur": 1.632, + "args": { + "External id": 4057733,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4740 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336756, "tid": 1381189, + "ts": 1655275526101.148, "dur": 31.736, + "args": { + "External id": 4057734,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 4741 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 1336756, "tid": 1381189, + "ts": 1655275526163.865, "dur": 104.581, + "args": { + "External id": 4057735,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "6423040", "8", "3", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [], [], [], [], [], []], "Ev Idx": 4742 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655275526173.764, "dur": 3.616, + "args": { + "External id": 4057736,"Record function id": 0, "Concrete Inputs": ["[51384320]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4743 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 1336756, "tid": 1381189, + "ts": 1655275526182.390, "dur": 9.487, + "args": { + "External id": 4057737,"Record function id": 0, "Concrete Inputs": ["", "0", "19269120", "6423040"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 4744 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1381189, + "ts": 1655275526186.369, "dur": 5.114, + "args": { + "External id": 4057738,"Record function id": 0, "Concrete Inputs": ["", "0", "19269120", "25692160", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[51384320], [], [], [], []], "Ev Idx": 4745 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275526189.725, "dur": 0.439, + "args": { + "External id": 4057739,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "[1]", "19269120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 4746 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336756, "tid": 1381189, + "ts": 1655275526198.500, "dur": 24.934, + "args": { + "External id": 4057740,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 4747 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275526200.628, "dur": 0.504, + "args": { + "External id": 4057741,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "19269120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4748 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275526203.423, "dur": 0.691, + "args": { + "External id": 4057742,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "19269376"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4749 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275526207.553, "dur": 0.372, + "args": { + "External id": 4057743,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "19793664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4750 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275526209.418, "dur": 0.464, + "args": { + "External id": 4057744,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "20317952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4751 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275526211.352, "dur": 0.290, + "args": { + "External id": 4057745,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "20842240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4752 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275526212.831, "dur": 1.451, + "args": { + "External id": 4057746,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "21366528"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4753 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275526215.619, "dur": 0.535, + "args": { + "External id": 4057747,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "21366784"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4754 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275526217.443, "dur": 0.329, + "args": { + "External id": 4057748,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "22808576"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4755 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275526218.815, "dur": 0.354, + "args": { + "External id": 4057749,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "24250368"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4756 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336756, "tid": 1381189, + "ts": 1655275526238.797, "dur": 22.239, + "args": { + "External id": 4057750,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 4757 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 1336756, "tid": 1381189, + "ts": 1655275526312.624, "dur": 129.488, + "args": { + "External id": 4057751,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[51384320], [6423040], [], [], []], "Ev Idx": 4758 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336756, "tid": 1381189, + "ts": 1655275526338.836, "dur": 99.035, + "args": { + "External id": 4057752,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 3, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "3", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 51384320, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[6423040], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 4759, "In msg nelems": 6423040 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 1336756, "tid": 1381189, + "ts": 1655275526348.503, "dur": 83.834, + "args": { + "External id": 4057753,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[6423040]], "Ev Idx": 4760 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336756, "tid": 1381189, + "ts": 1655275526459.244, "dur": 2.299, + "args": { + "External id": 4057754,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "3", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 4761, "In msg nelems": 0, "Rank": 3, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1655275526538.391, "dur": 1564.373, + "args": { + "External id": 4057755,"Sequence number": 40618366, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 4762 + } + }, + { + "ph": "f", "id": 214, "pid": 1336756, "tid": 1381189, "ts": 1655275526538.391, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275526643.262, "dur": 104.635, + "args": { + "External id": 4057756,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [5632, 1], [5632, 1]], "Input Dims": [[65536, 2048], [2048, 5632], [65536, 5632]], "Ev Idx": 4763 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_add_mul_rsub_silu_0", "pid": 1336756, "tid": 1381189, + "ts": 1655275526787.767, "dur": 36.680, + "args": { + "External id": 4057757,"kernel_hash": "c2zszzsomz26dv2qwvmiurvgyrl5qxtyn6ocoqkdpzzhfzwqp5q6", "grid": "grid(369098752,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "369098752"], "kernel_file": "/tmp/torchinductor_cvm/2z/c2zszzsomz26dv2qwvmiurvgyrl5qxtyn6ocoqkdpzzhfzwqp5q6.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[5632, 1], [5632, 1], [5632, 1], [23068672, 5632, 1], [23068672, 5632, 1], [23068672, 5632, 1], []], "Input Dims": [[65536, 5632], [65536, 5632], [65536, 5632], [16, 4096, 5632], [16, 4096, 5632], [16, 4096, 5632], []], "Ev Idx": 4764 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 1336756, "tid": 1381189, + "ts": 1655275526838.972, "dur": 49.041, + "args": { + "External id": 4057758,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[0, 1, 2048], [0, 5632, 1], [11534336, 5632, 1]], "Input Dims": [[1, 2048, 65536], [1, 65536, 5632], [1, 2048, 5632]], "Ev Idx": 4765 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275526897.206, "dur": 32.502, + "args": { + "External id": 4057759,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 5632], [2048, 1], [2048, 1]], "Input Dims": [[5632, 65536], [65536, 2048], [5632, 2048]], "Ev Idx": 4766 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275526935.575, "dur": 87.088, + "args": { + "External id": 4057760,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 5632], [5632, 2048], [65536, 2048]], "Ev Idx": 4767 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275527035.216, "dur": 33.305, + "args": { + "External id": 4057761,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 5632], [2048, 1], [2048, 1]], "Input Dims": [[5632, 65536], [65536, 2048], [5632, 2048]], "Ev Idx": 4768 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275527075.847, "dur": 42.313, + "args": { + "External id": 4057762,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 5632], [5632, 2048], [65536, 2048]], "Ev Idx": 4769 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_1", "pid": 1336756, "tid": 1381189, + "ts": 1655275527144.413, "dur": 24.502, + "args": { + "External id": 4057763,"kernel_hash": "cjd6g3jfgntyoifzno6l2urmnhif7alxtw6zz7miov66vywxwv7d", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/jd/cjd6g3jfgntyoifzno6l2urmnhif7alxtw6zz7miov66vywxwv7d.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[65536, 2048], [65536, 2048], []], "Ev Idx": 4770 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 1336756, "tid": 1381189, + "ts": 1655275527187.816, "dur": 25.737, + "args": { + "External id": 4057764,"kernel_hash": "cxhg545cyph4gbk5vymzyh72vho7oogk3ycan2lp4cxntklp5hew", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "65536", "2048", "1", "497", "132", "True", "2048", "True", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/xh/cxhg545cyph4gbk5vymzyh72vho7oogk3ycan2lp4cxntklp5hew.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [1], [2048, 1], [2048, 1], [2048, 1], [2048, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [2048], [65536, 2048], [65536, 2048], [132, 2048], [65536, 2048], [65536], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 4771 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 1336756, "tid": 1381189, + "ts": 1655275527230.967, "dur": 17.457, + "args": { + "External id": 4057765,"kernel_hash": "cu42i6zmxtvs2i7cs6x4ixaexke3lhgdiaye5oxwm7s3u6em6co4", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "66"], "kernel_file": "/tmp/torchinductor_cvm/u4/cu42i6zmxtvs2i7cs6x4ixaexke3lhgdiaye5oxwm7s3u6em6co4.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [4096, 1, 2048], [], []], "Input Dims": [[132, 2048], [1, 2048, 2], [], []], "Ev Idx": 4772 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 1336756, "tid": 1381189, + "ts": 1655275527264.529, "dur": 14.471, + "args": { + "External id": 4057766,"kernel_hash": "ckihofrorhmzazt2wfn2dz2m5wfx3auisu2gvfo2jsepr4zyekmq", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "2"], "kernel_file": "/tmp/torchinductor_cvm/ki/ckihofrorhmzazt2wfn2dz2m5wfx3auisu2gvfo2jsepr4zyekmq.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1, 2048], [2048, 1], [], []], "Input Dims": [[1, 2048, 2], [1, 2048], [], []], "Ev Idx": 4773 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275527287.031, "dur": 26.878, + "args": { + "External id": 4057767,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 4774 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275527316.775, "dur": 31.841, + "args": { + "External id": 4057768,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 4775 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 1336756, "tid": 1381189, + "ts": 1655275527378.254, "dur": 187.590, + "args": { + "External id": 4057769,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.125", "True", "-1", "-1", "0.", "", "False", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar", "long int"], "Input Strides": [[8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [131072, 4096, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 32, 4096], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 4776 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655275527473.876, "dur": 7.766, + "args": { + "External id": 4057770,"Record function id": 0, "Concrete Inputs": ["[16, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4777 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655275527483.707, "dur": 2.240, + "args": { + "External id": 4057771,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4778 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336756, "tid": 1381189, + "ts": 1655275527597.603, "dur": 22.816, + "args": { + "External id": 4057772,"kernel_hash": "cb6oumcqb462ndf2ivcd2sc6qg6mfjahptjw4ih7cesqhfpziv3b", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/b6/cb6oumcqb462ndf2ivcd2sc6qg6mfjahptjw4ih7cesqhfpziv3b.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 4779 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336756, "tid": 1381189, + "ts": 1655275527631.547, "dur": 13.047, + "args": { + "External id": 4057773,"kernel_hash": "cb6oumcqb462ndf2ivcd2sc6qg6mfjahptjw4ih7cesqhfpziv3b", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/b6/cb6oumcqb462ndf2ivcd2sc6qg6mfjahptjw4ih7cesqhfpziv3b.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 4780 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275527652.309, "dur": 38.152, + "args": { + "External id": 4057774,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 4781 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275527695.454, "dur": 34.148, + "args": { + "External id": 4057775,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 4782 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275527735.962, "dur": 19.945, + "args": { + "External id": 4057776,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 4783 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275527761.635, "dur": 29.754, + "args": { + "External id": 4057777,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 4784 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275527796.622, "dur": 19.609, + "args": { + "External id": 4057778,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 4785 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275527822.917, "dur": 29.499, + "args": { + "External id": 4057779,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 4786 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_4", "pid": 1336756, "tid": 1381189, + "ts": 1655275527872.082, "dur": 20.838, + "args": { + "External id": 4057780,"kernel_hash": "c7pqhdjojzeazwsh5g3ibnyk4m2nfh3q73e3zc7hljz4yvhe7c4h", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/7p/c7pqhdjojzeazwsh5g3ibnyk4m2nfh3q73e3zc7hljz4yvhe7c4h.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1], []], "Input Dims": [[65536, 2048], [65536, 2048], [65536, 2048], []], "Ev Idx": 4787 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_2", "pid": 1336756, "tid": 1381189, + "ts": 1655275527911.131, "dur": 21.993, + "args": { + "External id": 4057781,"kernel_hash": "cvgvwkysjpcw75q5t3guce5bep2so25f7i5zxc6ipt5f56shof73", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "65536", "2048", "1", "497", "132", "True", "2048", "False", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/vg/cvgvwkysjpcw75q5t3guce5bep2so25f7i5zxc6ipt5f56shof73.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [1], [2048, 1], [2048, 1], [2048, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [2048], [65536, 2048], [65536, 2048], [132, 2048], [65536], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 4788 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 1336756, "tid": 1381189, + "ts": 1655275527945.850, "dur": 15.078, + "args": { + "External id": 4057782,"kernel_hash": "cu42i6zmxtvs2i7cs6x4ixaexke3lhgdiaye5oxwm7s3u6em6co4", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "66"], "kernel_file": "/tmp/torchinductor_cvm/u4/cu42i6zmxtvs2i7cs6x4ixaexke3lhgdiaye5oxwm7s3u6em6co4.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [4096, 1, 2048], [], []], "Input Dims": [[132, 2048], [1, 2048, 2], [], []], "Ev Idx": 4789 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 1336756, "tid": 1381189, + "ts": 1655275527975.956, "dur": 50.117, + "args": { + "External id": 4057783,"kernel_hash": "ckihofrorhmzazt2wfn2dz2m5wfx3auisu2gvfo2jsepr4zyekmq", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "2"], "kernel_file": "/tmp/torchinductor_cvm/ki/ckihofrorhmzazt2wfn2dz2m5wfx3auisu2gvfo2jsepr4zyekmq.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1, 2048], [2048, 1], [], []], "Input Dims": [[1, 2048, 2], [1, 2048], [], []], "Ev Idx": 4790 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_5", "pid": 1336756, "tid": 1381189, + "ts": 1655275528044.149, "dur": 16.611, + "args": { + "External id": 4057784,"kernel_hash": "cckrpn5uuxyvbancoio3sz2onrjto236n54xx4ycphq5p6r3jlfj", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/ck/cckrpn5uuxyvbancoio3sz2onrjto236n54xx4ycphq5p6r3jlfj.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [8388608, 2048, 1], []], "Input Dims": [[65536, 2048], [65536, 2048], [16, 4096, 2048], []], "Ev Idx": 4791 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275528145.305, "dur": 14.072, + "args": { + "External id": 4057785,"Record function id": 0, "Ev Idx": 4792 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275528148.320, "dur": 10.183, + "args": { + "External id": 4057786,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 4793 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275528152.349, "dur": 5.255, + "args": { + "External id": 4057787,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 4794 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275528153.622, "dur": 3.901, + "args": { + "External id": 4057788,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 4795 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275528163.072, "dur": 4.254, + "args": { + "External id": 4057789,"Record function id": 0, "Ev Idx": 4796 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275528164.698, "dur": 2.221, + "args": { + "External id": 4057790,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 4797 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275528165.413, "dur": 1.057, + "args": { + "External id": 4057791,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 4798 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275528165.702, "dur": 0.672, + "args": { + "External id": 4057792,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 4799 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275528170.454, "dur": 4.353, + "args": { + "External id": 4057793,"Record function id": 0, "Ev Idx": 4800 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275528171.633, "dur": 2.796, + "args": { + "External id": 4057794,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 4801 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275528172.239, "dur": 1.747, + "args": { + "External id": 4057795,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 4802 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275528173.172, "dur": 0.739, + "args": { + "External id": 4057796,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 4803 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275528181.194, "dur": 3.901, + "args": { + "External id": 4057797,"Record function id": 0, "Ev Idx": 4804 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275528182.542, "dur": 2.147, + "args": { + "External id": 4057798,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 4805 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275528183.355, "dur": 0.941, + "args": { + "External id": 4057799,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 4806 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275528183.644, "dur": 0.585, + "args": { + "External id": 4057800,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 4807 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275528188.134, "dur": 4.985, + "args": { + "External id": 4057801,"Record function id": 0, "Ev Idx": 4808 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275528189.313, "dur": 3.405, + "args": { + "External id": 4057802,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 4809 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275528189.752, "dur": 2.559, + "args": { + "External id": 4057803,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 4810 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275528190.023, "dur": 2.221, + "args": { + "External id": 4057804,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 4811 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275528196.091, "dur": 5.445, + "args": { + "External id": 4057805,"Record function id": 0, "Ev Idx": 4812 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275528197.135, "dur": 4.014, + "args": { + "External id": 4057806,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 4813 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275528197.558, "dur": 3.192, + "args": { + "External id": 4057807,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 4814 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275528199.942, "dur": 0.682, + "args": { + "External id": 4057808,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 4815 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275528204.659, "dur": 2.994, + "args": { + "External id": 4057809,"Record function id": 0, "Ev Idx": 4816 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275528205.624, "dur": 1.647, + "args": { + "External id": 4057810,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 4817 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275528206.051, "dur": 0.820, + "args": { + "External id": 4057811,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 4818 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275528206.342, "dur": 0.438, + "args": { + "External id": 4057812,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 4819 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275528210.607, "dur": 3.601, + "args": { + "External id": 4057813,"Record function id": 0, "Ev Idx": 4820 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275528211.524, "dur": 2.294, + "args": { + "External id": 4057814,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 4821 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275528212.090, "dur": 1.287, + "args": { + "External id": 4057815,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 4822 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275528212.476, "dur": 0.836, + "args": { + "External id": 4057816,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 4823 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275528217.129, "dur": 3.651, + "args": { + "External id": 4057817,"Record function id": 0, "Ev Idx": 4824 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275528218.199, "dur": 2.184, + "args": { + "External id": 4057818,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 4825 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275528218.606, "dur": 1.377, + "args": { + "External id": 4057819,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 4826 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275528219.299, "dur": 0.618, + "args": { + "External id": 4057820,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 4827 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RegisterPostBackwardFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1655275528224.183, "dur": 36568.455, + "args": { + "External id": 4057821,"Record function id": 0, "Sequence number": 40618365, "Fwd thread id": 1, "Ev Idx": 4828 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1655275528225.283, "dur": 36559.024, + "args": { + "External id": 4057822,"Sequence number": 40618365, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 4829 + } + }, + { + "ph": "f", "id": 215, "pid": 1336756, "tid": 1381189, "ts": 1655275528225.283, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.6)", "pid": 1336756, "tid": 1381189, + "ts": 1655275528257.830, "dur": 36.809, + "args": { + "External id": 4057823,"Record function id": 0, "Ev Idx": 4830 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.6)", "pid": 1336756, "tid": 1381189, + "ts": 1655275528302.199, "dur": 59.921, + "args": { + "External id": 4057824,"Record function id": 0, "Ev Idx": 4831 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.6)", "pid": 1336756, "tid": 1381189, + "ts": 1655275528367.480, "dur": 36409.181, + "args": { + "External id": 4057825,"Record function id": 0, "Ev Idx": 4832 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655275528476.332, "dur": 8.272, + "args": { + "External id": 4057826,"Record function id": 0, "Concrete Inputs": ["[51384320]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4833 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275528495.060, "dur": 5.022, + "args": { + "External id": 4057827,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[51384320], []], "Ev Idx": 4834 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::chunk_cat", "pid": 1336756, "tid": 1381189, + "ts": 1655275528514.350, "dur": 35435.607, + "args": { + "External id": 4057828,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [2048, 1], [2048, 1], [2048, 1], [2048, 1], [1], [2048, 1], [2048, 1], [5632, 1]], [], [], [6423040, 1]], "Input Dims": [[[2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048], [5632, 2048], [5632, 2048], [2048, 5632]], [], [], [8, 6423040]], "Ev Idx": 4835 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_chunk_cat", "pid": 1336756, "tid": 1381189, + "ts": 1655275528530.940, "dur": 35410.181, + "args": { + "External id": 4057829,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [2048, 1], [2048, 1], [2048, 1], [2048, 1], [1], [2048, 1], [2048, 1], [5632, 1]], [], [], [6423040, 1]], "Input Dims": [[[2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048], [5632, 2048], [5632, 2048], [2048, 5632]], [], [], [8, 6423040]], "Ev Idx": 4836 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655275528570.538, "dur": 16.898, + "args": { + "External id": 4057830,"Record function id": 0, "Concrete Inputs": ["[12602]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4837 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1381189, + "ts": 1655275528593.753, "dur": 35309.115, + "args": { + "External id": 4057831,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[12602], [], [], [], [], [], [], []], "Ev Idx": 4838 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336756, "tid": 1381189, + "ts": 1655275528596.249, "dur": 35305.839, + "args": { + "External id": 4057832,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[12602], [], [], [], [], [], []], "Ev Idx": 4839 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275528600.274, "dur": 5.252, + "args": { + "External id": 4057833,"Record function id": 0, "Concrete Inputs": ["[12602]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4840 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1381189, + "ts": 1655275528607.199, "dur": 35291.286, + "args": { + "External id": 4057834,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[12602], [12602], []], "Ev Idx": 4841 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 1336756, "tid": 1381189, + "ts": 1655275564063.182, "dur": 8.575, + "args": { + "External id": 4057835,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "", "", "", "False"], "Input type": ["float", "ScalarList", "", "", "", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[51384320], [], [], [], [], []], "Ev Idx": 4842 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655275564065.785, "dur": 5.419, + "args": { + "External id": 4057836,"Record function id": 0, "Concrete Inputs": ["[6423040]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4843 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_reduce_scatter_base_", "pid": 1336756, "tid": 1381189, + "ts": 1655275564101.659, "dur": 392.245, + "args": { + "External id": 4057837,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "-1"], "Input type": ["float", "float", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], [], []], "Input Dims": [[6423040], [51384320], [], [], [], []], "Ev Idx": 4844 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336756, "tid": 1381189, + "ts": 1655275564132.442, "dur": 356.014, + "args": { + "External id": 4057838,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 3, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "3", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 6423040, "Process Group Name": "0", "Input type": ["float", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[51384320], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 4845, "In msg nelems": 51384320 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_reduce_scatter_base", "pid": 1336756, "tid": 1381189, + "ts": 1655275564143.213, "dur": 338.881, + "args": { + "External id": 4057839,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[51384320]], "Ev Idx": 4846 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336756, "tid": 1381189, + "ts": 1655275564517.141, "dur": 2.219, + "args": { + "External id": 4057840,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "3", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 4847, "In msg nelems": 0, "Rank": 3, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275564579.723, "dur": 7.931, + "args": { + "External id": 4057841,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4848 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275564631.508, "dur": 1.529, + "args": { + "External id": 4057842,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "256"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4849 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275564647.921, "dur": 1.301, + "args": { + "External id": 4057843,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "524544"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4850 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275564659.791, "dur": 1.139, + "args": { + "External id": 4057844,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "1048832"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4851 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275564671.540, "dur": 2.663, + "args": { + "External id": 4057845,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "1573120"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4852 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275564683.986, "dur": 1.054, + "args": { + "External id": 4057846,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4853 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275564695.664, "dur": 0.670, + "args": { + "External id": 4057847,"Record function id": 0, "Concrete Inputs": ["", "[704, 2048]", "[2048, 1]", "2097664"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4854 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275564706.234, "dur": 1.090, + "args": { + "External id": 4057848,"Record function id": 0, "Concrete Inputs": ["", "[704, 2048]", "[2048, 1]", "3539456"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4855 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275564716.407, "dur": 2.929, + "args": { + "External id": 4057849,"Record function id": 0, "Concrete Inputs": ["", "[256, 5632]", "[5632, 1]", "4981248"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4856 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: CompiledFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1655275564806.494, "dur": 2650.420, + "args": { + "External id": 4057850,"Record function id": 0, "Ev Idx": 4857 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.5)", "pid": 1336756, "tid": 1381189, + "ts": 1655275564825.245, "dur": 986.308, + "args": { + "External id": 4057851,"Record function id": 0, "Ev Idx": 4858 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.5)", "pid": 1336756, "tid": 1381189, + "ts": 1655275564838.252, "dur": 339.238, + "args": { + "External id": 4057852,"Record function id": 0, "Ev Idx": 4859 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275564911.179, "dur": 4.074, + "args": { + "External id": 4057853,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[51384320], []], "Ev Idx": 4860 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275564918.648, "dur": 1.018, + "args": { + "External id": 4057854,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 4861 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275564922.664, "dur": 0.742, + "args": { + "External id": 4057855,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 4862 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275564925.187, "dur": 0.946, + "args": { + "External id": 4057856,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 4863 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275564927.707, "dur": 0.519, + "args": { + "External id": 4057857,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 4864 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275564929.721, "dur": 0.755, + "args": { + "External id": 4057858,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 4865 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275564933.273, "dur": 0.659, + "args": { + "External id": 4057859,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 4866 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275564935.540, "dur": 2.226, + "args": { + "External id": 4057860,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 4867 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275564939.170, "dur": 1.089, + "args": { + "External id": 4057861,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 4868 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275564941.676, "dur": 0.717, + "args": { + "External id": 4057862,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 4869 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 1336756, "tid": 1381189, + "ts": 1655275564960.222, "dur": 184.316, + "args": { + "External id": 4057863,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 4870 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 1336756, "tid": 1381189, + "ts": 1655275564976.315, "dur": 163.258, + "args": { + "External id": 4057864,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 4871 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655275565031.181, "dur": 12.442, + "args": { + "External id": 4057865,"Record function id": 0, "Concrete Inputs": ["[2133]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4872 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1381189, + "ts": 1655275565046.849, "dur": 66.442, + "args": { + "External id": 4057866,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], [], []], "Ev Idx": 4873 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336756, "tid": 1381189, + "ts": 1655275565049.301, "dur": 63.725, + "args": { + "External id": 4057867,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], []], "Ev Idx": 4874 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275565053.325, "dur": 6.188, + "args": { + "External id": 4057868,"Record function id": 0, "Concrete Inputs": ["[2133]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4875 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1381189, + "ts": 1655275565061.123, "dur": 51.403, + "args": { + "External id": 4057869,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[2133], [2133], []], "Ev Idx": 4876 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::backward_prefetch for model.layers.4", "pid": 1336756, "tid": 1381189, + "ts": 1655275565253.349, "dur": 550.804, + "args": { + "External id": 4057870,"Record function id": 0, "Ev Idx": 4877 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.4)", "pid": 1336756, "tid": 1381189, + "ts": 1655275565269.681, "dur": 522.797, + "args": { + "External id": 4057871,"Record function id": 0, "Ev Idx": 4878 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655275565323.129, "dur": 4.279, + "args": { + "External id": 4057872,"Record function id": 0, "Concrete Inputs": ["[6423040]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4879 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336756, "tid": 1381189, + "ts": 1655275565347.411, "dur": 29.338, + "args": { + "External id": 4057873,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 4880 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275565352.350, "dur": 2.364, + "args": { + "External id": 4057874,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4881 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275565356.640, "dur": 0.415, + "args": { + "External id": 4057875,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4882 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275565358.517, "dur": 2.418, + "args": { + "External id": 4057876,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4883 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275565363.088, "dur": 0.341, + "args": { + "External id": 4057877,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4884 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275565364.975, "dur": 0.454, + "args": { + "External id": 4057878,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4885 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275565367.010, "dur": 0.339, + "args": { + "External id": 4057879,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4886 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275565369.309, "dur": 0.242, + "args": { + "External id": 4057880,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4887 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275565370.811, "dur": 0.678, + "args": { + "External id": 4057881,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4888 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275565373.069, "dur": 0.873, + "args": { + "External id": 4057882,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4889 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336756, "tid": 1381189, + "ts": 1655275565386.572, "dur": 43.394, + "args": { + "External id": 4057883,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 4890 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 1336756, "tid": 1381189, + "ts": 1655275565464.444, "dur": 105.356, + "args": { + "External id": 4057884,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "6423040", "8", "3", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [], [], [], [], [], []], "Ev Idx": 4891 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655275565475.079, "dur": 4.458, + "args": { + "External id": 4057885,"Record function id": 0, "Concrete Inputs": ["[51384320]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4892 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 1336756, "tid": 1381189, + "ts": 1655275565484.857, "dur": 12.617, + "args": { + "External id": 4057886,"Record function id": 0, "Concrete Inputs": ["", "0", "19269120", "6423040"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 4893 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1381189, + "ts": 1655275565488.991, "dur": 8.060, + "args": { + "External id": 4057887,"Record function id": 0, "Concrete Inputs": ["", "0", "19269120", "25692160", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[51384320], [], [], [], []], "Ev Idx": 4894 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275565492.899, "dur": 2.630, + "args": { + "External id": 4057888,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "[1]", "19269120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 4895 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336756, "tid": 1381189, + "ts": 1655275565505.573, "dur": 23.766, + "args": { + "External id": 4057889,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 4896 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275565507.874, "dur": 0.575, + "args": { + "External id": 4057890,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "19269120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4897 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275565510.019, "dur": 0.411, + "args": { + "External id": 4057891,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "19269376"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4898 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275565511.766, "dur": 0.763, + "args": { + "External id": 4057892,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "19793664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4899 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275565513.827, "dur": 0.693, + "args": { + "External id": 4057893,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "20317952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4900 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275565516.210, "dur": 0.598, + "args": { + "External id": 4057894,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "20842240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4901 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275565518.206, "dur": 0.222, + "args": { + "External id": 4057895,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "21366528"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4902 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275565519.906, "dur": 0.322, + "args": { + "External id": 4057896,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "21366784"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4903 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275565521.415, "dur": 1.451, + "args": { + "External id": 4057897,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "22808576"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4904 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275565524.138, "dur": 0.343, + "args": { + "External id": 4057898,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "24250368"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4905 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336756, "tid": 1381189, + "ts": 1655275565540.495, "dur": 22.552, + "args": { + "External id": 4057899,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 4906 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 1336756, "tid": 1381189, + "ts": 1655275565615.419, "dur": 112.196, + "args": { + "External id": 4057900,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[51384320], [6423040], [], [], []], "Ev Idx": 4907 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336756, "tid": 1381189, + "ts": 1655275565640.745, "dur": 83.355, + "args": { + "External id": 4057901,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 3, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "3", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 51384320, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[6423040], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 4908, "In msg nelems": 6423040 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 1336756, "tid": 1381189, + "ts": 1655275565650.288, "dur": 69.520, + "args": { + "External id": 4057902,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[6423040]], "Ev Idx": 4909 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336756, "tid": 1381189, + "ts": 1655275565743.836, "dur": 1.602, + "args": { + "External id": 4057903,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "3", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 4910, "In msg nelems": 0, "Rank": 3, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1655275565817.569, "dur": 1615.537, + "args": { + "External id": 4057904,"Sequence number": 40618364, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 4911 + } + }, + { + "ph": "f", "id": 216, "pid": 1336756, "tid": 1381189, "ts": 1655275565817.569, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275565920.752, "dur": 146.436, + "args": { + "External id": 4057905,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [5632, 1], [5632, 1]], "Input Dims": [[65536, 2048], [2048, 5632], [65536, 5632]], "Ev Idx": 4912 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_add_mul_rsub_silu_0", "pid": 1336756, "tid": 1381189, + "ts": 1655275566112.533, "dur": 37.634, + "args": { + "External id": 4057906,"kernel_hash": "c2zszzsomz26dv2qwvmiurvgyrl5qxtyn6ocoqkdpzzhfzwqp5q6", "grid": "grid(369098752,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "369098752"], "kernel_file": "/tmp/torchinductor_cvm/2z/c2zszzsomz26dv2qwvmiurvgyrl5qxtyn6ocoqkdpzzhfzwqp5q6.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[5632, 1], [5632, 1], [5632, 1], [23068672, 5632, 1], [23068672, 5632, 1], [23068672, 5632, 1], []], "Input Dims": [[65536, 5632], [65536, 5632], [65536, 5632], [16, 4096, 5632], [16, 4096, 5632], [16, 4096, 5632], []], "Ev Idx": 4913 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 1336756, "tid": 1381189, + "ts": 1655275566167.658, "dur": 53.400, + "args": { + "External id": 4057907,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[0, 1, 2048], [0, 5632, 1], [11534336, 5632, 1]], "Input Dims": [[1, 2048, 65536], [1, 65536, 5632], [1, 2048, 5632]], "Ev Idx": 4914 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275566230.401, "dur": 32.866, + "args": { + "External id": 4057908,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 5632], [2048, 1], [2048, 1]], "Input Dims": [[5632, 65536], [65536, 2048], [5632, 2048]], "Ev Idx": 4915 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275566269.445, "dur": 44.705, + "args": { + "External id": 4057909,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 5632], [5632, 2048], [65536, 2048]], "Ev Idx": 4916 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275566320.422, "dur": 27.376, + "args": { + "External id": 4057910,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 5632], [2048, 1], [2048, 1]], "Input Dims": [[5632, 65536], [65536, 2048], [5632, 2048]], "Ev Idx": 4917 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275566356.491, "dur": 43.042, + "args": { + "External id": 4057911,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 5632], [5632, 2048], [65536, 2048]], "Ev Idx": 4918 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_1", "pid": 1336756, "tid": 1381189, + "ts": 1655275566437.644, "dur": 24.222, + "args": { + "External id": 4057912,"kernel_hash": "cjd6g3jfgntyoifzno6l2urmnhif7alxtw6zz7miov66vywxwv7d", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/jd/cjd6g3jfgntyoifzno6l2urmnhif7alxtw6zz7miov66vywxwv7d.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[65536, 2048], [65536, 2048], []], "Ev Idx": 4919 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 1336756, "tid": 1381189, + "ts": 1655275566483.219, "dur": 28.740, + "args": { + "External id": 4057913,"kernel_hash": "cxhg545cyph4gbk5vymzyh72vho7oogk3ycan2lp4cxntklp5hew", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "65536", "2048", "1", "497", "132", "True", "2048", "True", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/xh/cxhg545cyph4gbk5vymzyh72vho7oogk3ycan2lp4cxntklp5hew.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [1], [2048, 1], [2048, 1], [2048, 1], [2048, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [2048], [65536, 2048], [65536, 2048], [132, 2048], [65536, 2048], [65536], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 4920 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 1336756, "tid": 1381189, + "ts": 1655275566532.655, "dur": 17.775, + "args": { + "External id": 4057914,"kernel_hash": "cu42i6zmxtvs2i7cs6x4ixaexke3lhgdiaye5oxwm7s3u6em6co4", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "66"], "kernel_file": "/tmp/torchinductor_cvm/u4/cu42i6zmxtvs2i7cs6x4ixaexke3lhgdiaye5oxwm7s3u6em6co4.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [4096, 1, 2048], [], []], "Input Dims": [[132, 2048], [1, 2048, 2], [], []], "Ev Idx": 4921 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 1336756, "tid": 1381189, + "ts": 1655275566566.155, "dur": 14.517, + "args": { + "External id": 4057915,"kernel_hash": "ckihofrorhmzazt2wfn2dz2m5wfx3auisu2gvfo2jsepr4zyekmq", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "2"], "kernel_file": "/tmp/torchinductor_cvm/ki/ckihofrorhmzazt2wfn2dz2m5wfx3auisu2gvfo2jsepr4zyekmq.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1, 2048], [2048, 1], [], []], "Input Dims": [[1, 2048, 2], [1, 2048], [], []], "Ev Idx": 4922 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275566590.763, "dur": 32.047, + "args": { + "External id": 4057916,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 4923 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275566626.205, "dur": 33.263, + "args": { + "External id": 4057917,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 4924 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 1336756, "tid": 1381189, + "ts": 1655275566687.065, "dur": 166.275, + "args": { + "External id": 4057918,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.125", "True", "-1", "-1", "0.", "", "False", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar", "long int"], "Input Strides": [[8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [131072, 4096, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 32, 4096], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 4925 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655275566764.510, "dur": 6.046, + "args": { + "External id": 4057919,"Record function id": 0, "Concrete Inputs": ["[16, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4926 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655275566772.469, "dur": 3.013, + "args": { + "External id": 4057920,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4927 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336756, "tid": 1381189, + "ts": 1655275566885.498, "dur": 23.155, + "args": { + "External id": 4057921,"kernel_hash": "cb6oumcqb462ndf2ivcd2sc6qg6mfjahptjw4ih7cesqhfpziv3b", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/b6/cb6oumcqb462ndf2ivcd2sc6qg6mfjahptjw4ih7cesqhfpziv3b.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 4928 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336756, "tid": 1381189, + "ts": 1655275566926.403, "dur": 13.564, + "args": { + "External id": 4057922,"kernel_hash": "cb6oumcqb462ndf2ivcd2sc6qg6mfjahptjw4ih7cesqhfpziv3b", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/b6/cb6oumcqb462ndf2ivcd2sc6qg6mfjahptjw4ih7cesqhfpziv3b.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 4929 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275566947.285, "dur": 32.884, + "args": { + "External id": 4057923,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 4930 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275567025.591, "dur": 40.836, + "args": { + "External id": 4057924,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 4931 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275567074.702, "dur": 21.051, + "args": { + "External id": 4057925,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 4932 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275567100.276, "dur": 29.936, + "args": { + "External id": 4057926,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 4933 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275567136.113, "dur": 19.369, + "args": { + "External id": 4057927,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 4934 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275567162.783, "dur": 29.584, + "args": { + "External id": 4057928,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 4935 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_4", "pid": 1336756, "tid": 1381189, + "ts": 1655275567213.713, "dur": 24.203, + "args": { + "External id": 4057929,"kernel_hash": "c7pqhdjojzeazwsh5g3ibnyk4m2nfh3q73e3zc7hljz4yvhe7c4h", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/7p/c7pqhdjojzeazwsh5g3ibnyk4m2nfh3q73e3zc7hljz4yvhe7c4h.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1], []], "Input Dims": [[65536, 2048], [65536, 2048], [65536, 2048], []], "Ev Idx": 4936 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_2", "pid": 1336756, "tid": 1381189, + "ts": 1655275567257.285, "dur": 37.316, + "args": { + "External id": 4057930,"kernel_hash": "cvgvwkysjpcw75q5t3guce5bep2so25f7i5zxc6ipt5f56shof73", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "65536", "2048", "1", "497", "132", "True", "2048", "False", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/vg/cvgvwkysjpcw75q5t3guce5bep2so25f7i5zxc6ipt5f56shof73.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [1], [2048, 1], [2048, 1], [2048, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [2048], [65536, 2048], [65536, 2048], [132, 2048], [65536], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 4937 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 1336756, "tid": 1381189, + "ts": 1655275567315.719, "dur": 19.501, + "args": { + "External id": 4057931,"kernel_hash": "cu42i6zmxtvs2i7cs6x4ixaexke3lhgdiaye5oxwm7s3u6em6co4", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "66"], "kernel_file": "/tmp/torchinductor_cvm/u4/cu42i6zmxtvs2i7cs6x4ixaexke3lhgdiaye5oxwm7s3u6em6co4.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [4096, 1, 2048], [], []], "Input Dims": [[132, 2048], [1, 2048, 2], [], []], "Ev Idx": 4938 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 1336756, "tid": 1381189, + "ts": 1655275567351.940, "dur": 13.543, + "args": { + "External id": 4057932,"kernel_hash": "ckihofrorhmzazt2wfn2dz2m5wfx3auisu2gvfo2jsepr4zyekmq", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "2"], "kernel_file": "/tmp/torchinductor_cvm/ki/ckihofrorhmzazt2wfn2dz2m5wfx3auisu2gvfo2jsepr4zyekmq.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1, 2048], [2048, 1], [], []], "Input Dims": [[1, 2048, 2], [1, 2048], [], []], "Ev Idx": 4939 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_5", "pid": 1336756, "tid": 1381189, + "ts": 1655275567377.204, "dur": 13.759, + "args": { + "External id": 4057933,"kernel_hash": "cckrpn5uuxyvbancoio3sz2onrjto236n54xx4ycphq5p6r3jlfj", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/ck/cckrpn5uuxyvbancoio3sz2onrjto236n54xx4ycphq5p6r3jlfj.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [8388608, 2048, 1], []], "Input Dims": [[65536, 2048], [65536, 2048], [16, 4096, 2048], []], "Ev Idx": 4940 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275567479.303, "dur": 15.561, + "args": { + "External id": 4057934,"Record function id": 0, "Ev Idx": 4941 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275567482.666, "dur": 11.255, + "args": { + "External id": 4057935,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 4942 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275567486.985, "dur": 6.072, + "args": { + "External id": 4057936,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 4943 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275567488.578, "dur": 4.386, + "args": { + "External id": 4057937,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 4944 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275567498.643, "dur": 5.848, + "args": { + "External id": 4057938,"Record function id": 0, "Ev Idx": 4945 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275567499.880, "dur": 4.154, + "args": { + "External id": 4057939,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 4946 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275567500.639, "dur": 2.929, + "args": { + "External id": 4057940,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 4947 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275567501.424, "dur": 2.057, + "args": { + "External id": 4057941,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 4948 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275567507.701, "dur": 7.667, + "args": { + "External id": 4057942,"Record function id": 0, "Ev Idx": 4949 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275567508.941, "dur": 6.028, + "args": { + "External id": 4057943,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 4950 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275567509.648, "dur": 4.897, + "args": { + "External id": 4057944,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 4951 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275567513.439, "dur": 1.019, + "args": { + "External id": 4057945,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 4952 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275567518.490, "dur": 3.993, + "args": { + "External id": 4057946,"Record function id": 0, "Ev Idx": 4953 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275567519.688, "dur": 2.406, + "args": { + "External id": 4057947,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 4954 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275567520.325, "dur": 1.358, + "args": { + "External id": 4057948,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 4955 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275567520.828, "dur": 0.722, + "args": { + "External id": 4057949,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 4956 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275567525.596, "dur": 3.416, + "args": { + "External id": 4057950,"Record function id": 0, "Ev Idx": 4957 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275567526.769, "dur": 1.849, + "args": { + "External id": 4057951,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 4958 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275567527.304, "dur": 0.902, + "args": { + "External id": 4057952,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 4959 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275567527.589, "dur": 0.553, + "args": { + "External id": 4057953,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 4960 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275567532.087, "dur": 3.398, + "args": { + "External id": 4057954,"Record function id": 0, "Ev Idx": 4961 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275567533.042, "dur": 2.051, + "args": { + "External id": 4057955,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 4962 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275567533.561, "dur": 1.093, + "args": { + "External id": 4057956,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 4963 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275567533.899, "dur": 0.682, + "args": { + "External id": 4057957,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 4964 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275567538.615, "dur": 5.144, + "args": { + "External id": 4057958,"Record function id": 0, "Ev Idx": 4965 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275567539.549, "dur": 3.823, + "args": { + "External id": 4057959,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 4966 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275567540.188, "dur": 2.682, + "args": { + "External id": 4057960,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 4967 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275567542.314, "dur": 0.491, + "args": { + "External id": 4057961,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 4968 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275567546.868, "dur": 3.549, + "args": { + "External id": 4057962,"Record function id": 0, "Ev Idx": 4969 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275567547.985, "dur": 2.000, + "args": { + "External id": 4057963,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 4970 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275567548.500, "dur": 1.075, + "args": { + "External id": 4057964,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 4971 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275567548.825, "dur": 0.682, + "args": { + "External id": 4057965,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 4972 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275567553.409, "dur": 4.304, + "args": { + "External id": 4057966,"Record function id": 0, "Ev Idx": 4973 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275567554.335, "dur": 2.994, + "args": { + "External id": 4057967,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 4974 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275567554.805, "dur": 2.137, + "args": { + "External id": 4057968,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 4975 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275567555.083, "dur": 1.798, + "args": { + "External id": 4057969,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 4976 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RegisterPostBackwardFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1655275567561.052, "dur": 36214.911, + "args": { + "External id": 4057970,"Record function id": 0, "Sequence number": 40618363, "Fwd thread id": 1, "Ev Idx": 4977 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1655275567562.268, "dur": 36205.500, + "args": { + "External id": 4057971,"Sequence number": 40618363, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 4978 + } + }, + { + "ph": "f", "id": 217, "pid": 1336756, "tid": 1381189, "ts": 1655275567562.268, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.5)", "pid": 1336756, "tid": 1381189, + "ts": 1655275567594.242, "dur": 38.935, + "args": { + "External id": 4057972,"Record function id": 0, "Ev Idx": 4979 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.5)", "pid": 1336756, "tid": 1381189, + "ts": 1655275567640.213, "dur": 62.062, + "args": { + "External id": 4057973,"Record function id": 0, "Ev Idx": 4980 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.5)", "pid": 1336756, "tid": 1381189, + "ts": 1655275567709.429, "dur": 36050.756, + "args": { + "External id": 4057974,"Record function id": 0, "Ev Idx": 4981 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655275567797.588, "dur": 6.869, + "args": { + "External id": 4057975,"Record function id": 0, "Concrete Inputs": ["[51384320]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4982 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275567814.134, "dur": 4.693, + "args": { + "External id": 4057976,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[51384320], []], "Ev Idx": 4983 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::chunk_cat", "pid": 1336756, "tid": 1381189, + "ts": 1655275567832.505, "dur": 35079.697, + "args": { + "External id": 4057977,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [2048, 1], [2048, 1], [2048, 1], [2048, 1], [1], [2048, 1], [2048, 1], [5632, 1]], [], [], [6423040, 1]], "Input Dims": [[[2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048], [5632, 2048], [5632, 2048], [2048, 5632]], [], [], [8, 6423040]], "Ev Idx": 4984 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_chunk_cat", "pid": 1336756, "tid": 1381189, + "ts": 1655275567846.143, "dur": 35057.586, + "args": { + "External id": 4057978,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [2048, 1], [2048, 1], [2048, 1], [2048, 1], [1], [2048, 1], [2048, 1], [5632, 1]], [], [], [6423040, 1]], "Input Dims": [[[2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048], [5632, 2048], [5632, 2048], [2048, 5632]], [], [], [8, 6423040]], "Ev Idx": 4985 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655275567884.278, "dur": 13.273, + "args": { + "External id": 4057979,"Record function id": 0, "Concrete Inputs": ["[12602]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4986 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1381189, + "ts": 1655275567903.574, "dur": 34963.577, + "args": { + "External id": 4057980,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[12602], [], [], [], [], [], [], []], "Ev Idx": 4987 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336756, "tid": 1381189, + "ts": 1655275567906.043, "dur": 34960.480, + "args": { + "External id": 4057981,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[12602], [], [], [], [], [], []], "Ev Idx": 4988 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275567910.235, "dur": 5.311, + "args": { + "External id": 4057982,"Record function id": 0, "Concrete Inputs": ["[12602]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4989 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1381189, + "ts": 1655275567917.022, "dur": 34945.949, + "args": { + "External id": 4057983,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[12602], [12602], []], "Ev Idx": 4990 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 1336756, "tid": 1381189, + "ts": 1655275603021.383, "dur": 8.850, + "args": { + "External id": 4057984,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "", "", "", "False"], "Input type": ["float", "ScalarList", "", "", "", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[51384320], [], [], [], [], []], "Ev Idx": 4991 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655275603024.176, "dur": 5.501, + "args": { + "External id": 4057985,"Record function id": 0, "Concrete Inputs": ["[6423040]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 4992 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_reduce_scatter_base_", "pid": 1336756, "tid": 1381189, + "ts": 1655275603059.588, "dur": 415.107, + "args": { + "External id": 4057986,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "-1"], "Input type": ["float", "float", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], [], []], "Input Dims": [[6423040], [51384320], [], [], [], []], "Ev Idx": 4993 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336756, "tid": 1381189, + "ts": 1655275603087.264, "dur": 381.717, + "args": { + "External id": 4057987,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 3, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "3", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 6423040, "Process Group Name": "0", "Input type": ["float", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[51384320], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 4994, "In msg nelems": 51384320 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_reduce_scatter_base", "pid": 1336756, "tid": 1381189, + "ts": 1655275603098.301, "dur": 364.767, + "args": { + "External id": 4057988,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[51384320]], "Ev Idx": 4995 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336756, "tid": 1381189, + "ts": 1655275603498.352, "dur": 2.759, + "args": { + "External id": 4057989,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "3", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 4996, "In msg nelems": 0, "Rank": 3, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275603563.954, "dur": 6.724, + "args": { + "External id": 4057990,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4997 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275603615.057, "dur": 1.394, + "args": { + "External id": 4057991,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "256"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4998 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275603632.616, "dur": 1.305, + "args": { + "External id": 4057992,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "524544"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 4999 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275603645.110, "dur": 0.719, + "args": { + "External id": 4057993,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "1048832"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5000 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275603656.335, "dur": 1.097, + "args": { + "External id": 4057994,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "1573120"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5001 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275603666.796, "dur": 1.051, + "args": { + "External id": 4057995,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5002 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275603681.100, "dur": 0.907, + "args": { + "External id": 4057996,"Record function id": 0, "Concrete Inputs": ["", "[704, 2048]", "[2048, 1]", "2097664"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5003 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275603692.266, "dur": 1.354, + "args": { + "External id": 4057997,"Record function id": 0, "Concrete Inputs": ["", "[704, 2048]", "[2048, 1]", "3539456"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5004 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275603702.634, "dur": 1.132, + "args": { + "External id": 4057998,"Record function id": 0, "Concrete Inputs": ["", "[256, 5632]", "[5632, 1]", "4981248"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5005 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: CompiledFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1655275603789.812, "dur": 2606.060, + "args": { + "External id": 4057999,"Record function id": 0, "Ev Idx": 5006 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.4)", "pid": 1336756, "tid": 1381189, + "ts": 1655275603807.318, "dur": 971.040, + "args": { + "External id": 4058000,"Record function id": 0, "Ev Idx": 5007 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.4)", "pid": 1336756, "tid": 1381189, + "ts": 1655275603820.326, "dur": 339.807, + "args": { + "External id": 4058001,"Record function id": 0, "Ev Idx": 5008 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275603890.643, "dur": 3.666, + "args": { + "External id": 4058002,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[51384320], []], "Ev Idx": 5009 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275603897.077, "dur": 1.582, + "args": { + "External id": 4058003,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 5010 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275603902.247, "dur": 2.330, + "args": { + "External id": 4058004,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 5011 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275603906.131, "dur": 1.187, + "args": { + "External id": 4058005,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 5012 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275603908.691, "dur": 0.863, + "args": { + "External id": 4058006,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 5013 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275603911.066, "dur": 0.543, + "args": { + "External id": 4058007,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 5014 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275603914.620, "dur": 0.774, + "args": { + "External id": 4058008,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 5015 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275603916.689, "dur": 0.520, + "args": { + "External id": 4058009,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 5016 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275603918.545, "dur": 0.828, + "args": { + "External id": 4058010,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 5017 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275603920.982, "dur": 0.887, + "args": { + "External id": 4058011,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 5018 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 1336756, "tid": 1381189, + "ts": 1655275603941.308, "dur": 188.280, + "args": { + "External id": 4058012,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 5019 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 1336756, "tid": 1381189, + "ts": 1655275603957.214, "dur": 167.266, + "args": { + "External id": 4058013,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 5020 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655275603973.981, "dur": 50.601, + "args": { + "External id": 4058014,"Record function id": 0, "Concrete Inputs": ["[2133]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5021 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1381189, + "ts": 1655275604028.693, "dur": 67.914, + "args": { + "External id": 4058015,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], [], []], "Ev Idx": 5022 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336756, "tid": 1381189, + "ts": 1655275604031.086, "dur": 65.213, + "args": { + "External id": 4058016,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], []], "Ev Idx": 5023 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275604035.677, "dur": 6.556, + "args": { + "External id": 4058017,"Record function id": 0, "Concrete Inputs": ["[2133]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5024 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1381189, + "ts": 1655275604043.909, "dur": 51.790, + "args": { + "External id": 4058018,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[2133], [2133], []], "Ev Idx": 5025 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::backward_prefetch for model.layers.3", "pid": 1336756, "tid": 1381189, + "ts": 1655275604234.820, "dur": 536.473, + "args": { + "External id": 4058019,"Record function id": 0, "Ev Idx": 5026 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.3)", "pid": 1336756, "tid": 1381189, + "ts": 1655275604250.283, "dur": 509.717, + "args": { + "External id": 4058020,"Record function id": 0, "Ev Idx": 5027 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655275604301.998, "dur": 4.506, + "args": { + "External id": 4058021,"Record function id": 0, "Concrete Inputs": ["[6423040]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5028 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336756, "tid": 1381189, + "ts": 1655275604325.508, "dur": 28.763, + "args": { + "External id": 4058022,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 5029 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275604330.701, "dur": 2.429, + "args": { + "External id": 4058023,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5030 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275604335.242, "dur": 0.561, + "args": { + "External id": 4058024,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5031 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275604337.027, "dur": 0.387, + "args": { + "External id": 4058025,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5032 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275604339.550, "dur": 0.157, + "args": { + "External id": 4058026,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5033 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275604341.320, "dur": 0.573, + "args": { + "External id": 4058027,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5034 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275604343.381, "dur": 1.965, + "args": { + "External id": 4058028,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5035 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275604347.293, "dur": 0.346, + "args": { + "External id": 4058029,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5036 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275604349.060, "dur": 0.453, + "args": { + "External id": 4058030,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5037 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275604350.798, "dur": 0.644, + "args": { + "External id": 4058031,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5038 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336756, "tid": 1381189, + "ts": 1655275604364.510, "dur": 28.225, + "args": { + "External id": 4058032,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 5039 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 1336756, "tid": 1381189, + "ts": 1655275604440.503, "dur": 102.850, + "args": { + "External id": 4058033,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "6423040", "8", "3", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [], [], [], [], [], []], "Ev Idx": 5040 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655275604451.809, "dur": 4.485, + "args": { + "External id": 4058034,"Record function id": 0, "Concrete Inputs": ["[51384320]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5041 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 1336756, "tid": 1381189, + "ts": 1655275604462.071, "dur": 10.781, + "args": { + "External id": 4058035,"Record function id": 0, "Concrete Inputs": ["", "0", "19269120", "6423040"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 5042 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1381189, + "ts": 1655275604466.094, "dur": 6.337, + "args": { + "External id": 4058036,"Record function id": 0, "Concrete Inputs": ["", "0", "19269120", "25692160", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[51384320], [], [], [], []], "Ev Idx": 5043 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275604470.187, "dur": 0.568, + "args": { + "External id": 4058037,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "[1]", "19269120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 5044 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336756, "tid": 1381189, + "ts": 1655275604480.596, "dur": 23.131, + "args": { + "External id": 4058038,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 5045 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275604482.939, "dur": 0.328, + "args": { + "External id": 4058039,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "19269120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5046 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275604484.841, "dur": 0.309, + "args": { + "External id": 4058040,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "19269376"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5047 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275604486.592, "dur": 2.303, + "args": { + "External id": 4058041,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "19793664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5048 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275604490.239, "dur": 0.700, + "args": { + "External id": 4058042,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "20317952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5049 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275604492.107, "dur": 0.175, + "args": { + "External id": 4058043,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "20842240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5050 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275604494.094, "dur": 0.431, + "args": { + "External id": 4058044,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "21366528"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5051 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275604495.812, "dur": 0.428, + "args": { + "External id": 4058045,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "21366784"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5052 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275604497.712, "dur": 0.256, + "args": { + "External id": 4058046,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "22808576"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5053 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275604499.352, "dur": 0.279, + "args": { + "External id": 4058047,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "24250368"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5054 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336756, "tid": 1381189, + "ts": 1655275604515.291, "dur": 20.925, + "args": { + "External id": 4058048,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 5055 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 1336756, "tid": 1381189, + "ts": 1655275604585.885, "dur": 109.919, + "args": { + "External id": 4058049,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[51384320], [6423040], [], [], []], "Ev Idx": 5056 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336756, "tid": 1381189, + "ts": 1655275604610.568, "dur": 81.855, + "args": { + "External id": 4058050,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 3, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "3", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 51384320, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[6423040], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 5057, "In msg nelems": 6423040 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 1336756, "tid": 1381189, + "ts": 1655275604619.197, "dur": 68.955, + "args": { + "External id": 4058051,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[6423040]], "Ev Idx": 5058 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336756, "tid": 1381189, + "ts": 1655275604711.053, "dur": 2.173, + "args": { + "External id": 4058052,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "3", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 5059, "In msg nelems": 0, "Rank": 3, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1655275604784.388, "dur": 1594.682, + "args": { + "External id": 4058053,"Sequence number": 40618362, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 5060 + } + }, + { + "ph": "f", "id": 218, "pid": 1336756, "tid": 1381189, "ts": 1655275604784.388, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275604887.771, "dur": 144.781, + "args": { + "External id": 4058054,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [5632, 1], [5632, 1]], "Input Dims": [[65536, 2048], [2048, 5632], [65536, 5632]], "Ev Idx": 5061 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_add_mul_rsub_silu_0", "pid": 1336756, "tid": 1381189, + "ts": 1655275605077.636, "dur": 37.643, + "args": { + "External id": 4058055,"kernel_hash": "c2zszzsomz26dv2qwvmiurvgyrl5qxtyn6ocoqkdpzzhfzwqp5q6", "grid": "grid(369098752,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "369098752"], "kernel_file": "/tmp/torchinductor_cvm/2z/c2zszzsomz26dv2qwvmiurvgyrl5qxtyn6ocoqkdpzzhfzwqp5q6.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[5632, 1], [5632, 1], [5632, 1], [23068672, 5632, 1], [23068672, 5632, 1], [23068672, 5632, 1], []], "Input Dims": [[65536, 5632], [65536, 5632], [65536, 5632], [16, 4096, 5632], [16, 4096, 5632], [16, 4096, 5632], []], "Ev Idx": 5062 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 1336756, "tid": 1381189, + "ts": 1655275605131.896, "dur": 55.688, + "args": { + "External id": 4058056,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[0, 1, 2048], [0, 5632, 1], [11534336, 5632, 1]], "Input Dims": [[1, 2048, 65536], [1, 65536, 5632], [1, 2048, 5632]], "Ev Idx": 5063 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275605198.050, "dur": 33.065, + "args": { + "External id": 4058057,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 5632], [2048, 1], [2048, 1]], "Input Dims": [[5632, 65536], [65536, 2048], [5632, 2048]], "Ev Idx": 5064 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275605239.166, "dur": 47.076, + "args": { + "External id": 4058058,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 5632], [5632, 2048], [65536, 2048]], "Ev Idx": 5065 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275605292.429, "dur": 27.761, + "args": { + "External id": 4058059,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 5632], [2048, 1], [2048, 1]], "Input Dims": [[5632, 65536], [65536, 2048], [5632, 2048]], "Ev Idx": 5066 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275605326.928, "dur": 42.645, + "args": { + "External id": 4058060,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 5632], [5632, 2048], [65536, 2048]], "Ev Idx": 5067 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_1", "pid": 1336756, "tid": 1381189, + "ts": 1655275605391.084, "dur": 22.189, + "args": { + "External id": 4058061,"kernel_hash": "cjd6g3jfgntyoifzno6l2urmnhif7alxtw6zz7miov66vywxwv7d", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/jd/cjd6g3jfgntyoifzno6l2urmnhif7alxtw6zz7miov66vywxwv7d.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[65536, 2048], [65536, 2048], []], "Ev Idx": 5068 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 1336756, "tid": 1381189, + "ts": 1655275605451.503, "dur": 28.277, + "args": { + "External id": 4058062,"kernel_hash": "cxhg545cyph4gbk5vymzyh72vho7oogk3ycan2lp4cxntklp5hew", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "65536", "2048", "1", "497", "132", "True", "2048", "True", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/xh/cxhg545cyph4gbk5vymzyh72vho7oogk3ycan2lp4cxntklp5hew.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [1], [2048, 1], [2048, 1], [2048, 1], [2048, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [2048], [65536, 2048], [65536, 2048], [132, 2048], [65536, 2048], [65536], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 5069 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 1336756, "tid": 1381189, + "ts": 1655275605502.208, "dur": 17.863, + "args": { + "External id": 4058063,"kernel_hash": "cu42i6zmxtvs2i7cs6x4ixaexke3lhgdiaye5oxwm7s3u6em6co4", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "66"], "kernel_file": "/tmp/torchinductor_cvm/u4/cu42i6zmxtvs2i7cs6x4ixaexke3lhgdiaye5oxwm7s3u6em6co4.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [4096, 1, 2048], [], []], "Input Dims": [[132, 2048], [1, 2048, 2], [], []], "Ev Idx": 5070 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 1336756, "tid": 1381189, + "ts": 1655275605534.792, "dur": 14.012, + "args": { + "External id": 4058064,"kernel_hash": "ckihofrorhmzazt2wfn2dz2m5wfx3auisu2gvfo2jsepr4zyekmq", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "2"], "kernel_file": "/tmp/torchinductor_cvm/ki/ckihofrorhmzazt2wfn2dz2m5wfx3auisu2gvfo2jsepr4zyekmq.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1, 2048], [2048, 1], [], []], "Input Dims": [[1, 2048, 2], [1, 2048], [], []], "Ev Idx": 5071 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275605557.016, "dur": 33.999, + "args": { + "External id": 4058065,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 5072 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275605594.630, "dur": 34.569, + "args": { + "External id": 4058066,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 5073 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 1336756, "tid": 1381189, + "ts": 1655275605658.415, "dur": 164.473, + "args": { + "External id": 4058067,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.125", "True", "-1", "-1", "0.", "", "False", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar", "long int"], "Input Strides": [[8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [131072, 4096, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 32, 4096], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 5074 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655275605735.112, "dur": 6.242, + "args": { + "External id": 4058068,"Record function id": 0, "Concrete Inputs": ["[16, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5075 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655275605743.086, "dur": 2.319, + "args": { + "External id": 4058069,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5076 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336756, "tid": 1381189, + "ts": 1655275605853.634, "dur": 23.566, + "args": { + "External id": 4058070,"kernel_hash": "cb6oumcqb462ndf2ivcd2sc6qg6mfjahptjw4ih7cesqhfpziv3b", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/b6/cb6oumcqb462ndf2ivcd2sc6qg6mfjahptjw4ih7cesqhfpziv3b.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 5077 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336756, "tid": 1381189, + "ts": 1655275605889.270, "dur": 13.129, + "args": { + "External id": 4058071,"kernel_hash": "cb6oumcqb462ndf2ivcd2sc6qg6mfjahptjw4ih7cesqhfpziv3b", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/b6/cb6oumcqb462ndf2ivcd2sc6qg6mfjahptjw4ih7cesqhfpziv3b.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 5078 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275605909.791, "dur": 32.685, + "args": { + "External id": 4058072,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 5079 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275605947.557, "dur": 34.014, + "args": { + "External id": 4058073,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 5080 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275606027.848, "dur": 26.664, + "args": { + "External id": 4058074,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 5081 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275606060.876, "dur": 31.013, + "args": { + "External id": 4058075,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 5082 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275606098.194, "dur": 19.266, + "args": { + "External id": 4058076,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 5083 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275606123.567, "dur": 29.246, + "args": { + "External id": 4058077,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 5084 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_4", "pid": 1336756, "tid": 1381189, + "ts": 1655275606174.910, "dur": 22.270, + "args": { + "External id": 4058078,"kernel_hash": "c7pqhdjojzeazwsh5g3ibnyk4m2nfh3q73e3zc7hljz4yvhe7c4h", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/7p/c7pqhdjojzeazwsh5g3ibnyk4m2nfh3q73e3zc7hljz4yvhe7c4h.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1], []], "Input Dims": [[65536, 2048], [65536, 2048], [65536, 2048], []], "Ev Idx": 5085 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_2", "pid": 1336756, "tid": 1381189, + "ts": 1655275606213.803, "dur": 21.661, + "args": { + "External id": 4058079,"kernel_hash": "cvgvwkysjpcw75q5t3guce5bep2so25f7i5zxc6ipt5f56shof73", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "65536", "2048", "1", "497", "132", "True", "2048", "False", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/vg/cvgvwkysjpcw75q5t3guce5bep2so25f7i5zxc6ipt5f56shof73.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [1], [2048, 1], [2048, 1], [2048, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [2048], [65536, 2048], [65536, 2048], [132, 2048], [65536], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 5086 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 1336756, "tid": 1381189, + "ts": 1655275606253.339, "dur": 15.785, + "args": { + "External id": 4058080,"kernel_hash": "cu42i6zmxtvs2i7cs6x4ixaexke3lhgdiaye5oxwm7s3u6em6co4", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "66"], "kernel_file": "/tmp/torchinductor_cvm/u4/cu42i6zmxtvs2i7cs6x4ixaexke3lhgdiaye5oxwm7s3u6em6co4.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [4096, 1, 2048], [], []], "Input Dims": [[132, 2048], [1, 2048, 2], [], []], "Ev Idx": 5087 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 1336756, "tid": 1381189, + "ts": 1655275606301.719, "dur": 19.303, + "args": { + "External id": 4058081,"kernel_hash": "ckihofrorhmzazt2wfn2dz2m5wfx3auisu2gvfo2jsepr4zyekmq", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "2"], "kernel_file": "/tmp/torchinductor_cvm/ki/ckihofrorhmzazt2wfn2dz2m5wfx3auisu2gvfo2jsepr4zyekmq.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1, 2048], [2048, 1], [], []], "Input Dims": [[1, 2048, 2], [1, 2048], [], []], "Ev Idx": 5088 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_5", "pid": 1336756, "tid": 1381189, + "ts": 1655275606334.893, "dur": 16.960, + "args": { + "External id": 4058082,"kernel_hash": "cckrpn5uuxyvbancoio3sz2onrjto236n54xx4ycphq5p6r3jlfj", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/ck/cckrpn5uuxyvbancoio3sz2onrjto236n54xx4ycphq5p6r3jlfj.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [8388608, 2048, 1], []], "Input Dims": [[65536, 2048], [65536, 2048], [16, 4096, 2048], []], "Ev Idx": 5089 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275606437.677, "dur": 17.000, + "args": { + "External id": 4058083,"Record function id": 0, "Ev Idx": 5090 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275606441.610, "dur": 11.672, + "args": { + "External id": 4058084,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 5091 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275606445.954, "dur": 6.011, + "args": { + "External id": 4058085,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 5092 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275606447.592, "dur": 4.116, + "args": { + "External id": 4058086,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 5093 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275606459.541, "dur": 4.366, + "args": { + "External id": 4058087,"Record function id": 0, "Ev Idx": 5094 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275606460.967, "dur": 2.448, + "args": { + "External id": 4058088,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 5095 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275606461.557, "dur": 1.291, + "args": { + "External id": 4058089,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 5096 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275606461.930, "dur": 0.839, + "args": { + "External id": 4058090,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 5097 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275606467.244, "dur": 3.882, + "args": { + "External id": 4058091,"Record function id": 0, "Ev Idx": 5098 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275606468.505, "dur": 2.177, + "args": { + "External id": 4058092,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 5099 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275606469.176, "dur": 1.038, + "args": { + "External id": 4058093,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 5100 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275606469.612, "dur": 0.509, + "args": { + "External id": 4058094,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 5101 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275606474.172, "dur": 3.975, + "args": { + "External id": 4058095,"Record function id": 0, "Ev Idx": 5102 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275606475.157, "dur": 2.557, + "args": { + "External id": 4058096,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 5103 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275606475.645, "dur": 1.623, + "args": { + "External id": 4058097,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 5104 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275606476.260, "dur": 0.937, + "args": { + "External id": 4058098,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 5105 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275606481.143, "dur": 5.131, + "args": { + "External id": 4058099,"Record function id": 0, "Ev Idx": 5106 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275606482.294, "dur": 3.573, + "args": { + "External id": 4058100,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 5107 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275606482.745, "dur": 2.693, + "args": { + "External id": 4058101,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 5108 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275606483.334, "dur": 2.035, + "args": { + "External id": 4058102,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 5109 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275606492.525, "dur": 5.220, + "args": { + "External id": 4058103,"Record function id": 0, "Ev Idx": 5110 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275606493.527, "dur": 3.779, + "args": { + "External id": 4058104,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 5111 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275606494.027, "dur": 2.849, + "args": { + "External id": 4058105,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 5112 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275606496.018, "dur": 0.785, + "args": { + "External id": 4058106,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 5113 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275606500.985, "dur": 3.721, + "args": { + "External id": 4058107,"Record function id": 0, "Ev Idx": 5114 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275606502.055, "dur": 2.253, + "args": { + "External id": 4058108,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 5115 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275606502.632, "dur": 1.261, + "args": { + "External id": 4058109,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 5116 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275606503.036, "dur": 0.783, + "args": { + "External id": 4058110,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 5117 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275606507.746, "dur": 22.622, + "args": { + "External id": 4058111,"Record function id": 0, "Ev Idx": 5118 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275606508.725, "dur": 21.145, + "args": { + "External id": 4058112,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 5119 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275606528.333, "dur": 1.092, + "args": { + "External id": 4058113,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 5120 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275606528.676, "dur": 0.682, + "args": { + "External id": 4058114,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 5121 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275606533.444, "dur": 4.714, + "args": { + "External id": 4058115,"Record function id": 0, "Ev Idx": 5122 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275606534.587, "dur": 3.155, + "args": { + "External id": 4058116,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 5123 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275606535.063, "dur": 2.262, + "args": { + "External id": 4058117,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 5124 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275606536.632, "dur": 0.586, + "args": { + "External id": 4058118,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 5125 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RegisterPostBackwardFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1655275606541.908, "dur": 36523.628, + "args": { + "External id": 4058119,"Record function id": 0, "Sequence number": 40618361, "Fwd thread id": 1, "Ev Idx": 5126 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1655275606543.248, "dur": 36513.269, + "args": { + "External id": 4058120,"Sequence number": 40618361, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 5127 + } + }, + { + "ph": "f", "id": 219, "pid": 1336756, "tid": 1381189, "ts": 1655275606543.248, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.4)", "pid": 1336756, "tid": 1381189, + "ts": 1655275606571.829, "dur": 42.986, + "args": { + "External id": 4058121,"Record function id": 0, "Ev Idx": 5128 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.4)", "pid": 1336756, "tid": 1381189, + "ts": 1655275606622.530, "dur": 65.042, + "args": { + "External id": 4058122,"Record function id": 0, "Ev Idx": 5129 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.4)", "pid": 1336756, "tid": 1381189, + "ts": 1655275606693.155, "dur": 36353.916, + "args": { + "External id": 4058123,"Record function id": 0, "Ev Idx": 5130 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655275606780.855, "dur": 6.885, + "args": { + "External id": 4058124,"Record function id": 0, "Concrete Inputs": ["[51384320]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5131 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275606797.104, "dur": 4.620, + "args": { + "External id": 4058125,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[51384320], []], "Ev Idx": 5132 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::chunk_cat", "pid": 1336756, "tid": 1381189, + "ts": 1655275606815.535, "dur": 35427.888, + "args": { + "External id": 4058126,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [2048, 1], [2048, 1], [2048, 1], [2048, 1], [1], [2048, 1], [2048, 1], [5632, 1]], [], [], [6423040, 1]], "Input Dims": [[[2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048], [5632, 2048], [5632, 2048], [2048, 5632]], [], [], [8, 6423040]], "Ev Idx": 5133 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_chunk_cat", "pid": 1336756, "tid": 1381189, + "ts": 1655275606828.235, "dur": 35406.229, + "args": { + "External id": 4058127,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [2048, 1], [2048, 1], [2048, 1], [2048, 1], [1], [2048, 1], [2048, 1], [5632, 1]], [], [], [6423040, 1]], "Input Dims": [[[2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048], [5632, 2048], [5632, 2048], [2048, 5632]], [], [], [8, 6423040]], "Ev Idx": 5134 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655275606865.902, "dur": 13.070, + "args": { + "External id": 4058128,"Record function id": 0, "Concrete Inputs": ["[12602]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5135 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1381189, + "ts": 1655275606886.407, "dur": 35308.500, + "args": { + "External id": 4058129,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[12602], [], [], [], [], [], [], []], "Ev Idx": 5136 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336756, "tid": 1381189, + "ts": 1655275606888.758, "dur": 35305.440, + "args": { + "External id": 4058130,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[12602], [], [], [], [], [], []], "Ev Idx": 5137 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275606892.599, "dur": 6.272, + "args": { + "External id": 4058131,"Record function id": 0, "Concrete Inputs": ["[12602]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5138 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1381189, + "ts": 1655275606900.513, "dur": 35290.097, + "args": { + "External id": 4058132,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[12602], [12602], []], "Ev Idx": 5139 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 1336756, "tid": 1381189, + "ts": 1655275642329.083, "dur": 8.649, + "args": { + "External id": 4058133,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "", "", "", "False"], "Input type": ["float", "ScalarList", "", "", "", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[51384320], [], [], [], [], []], "Ev Idx": 5140 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655275642331.925, "dur": 5.452, + "args": { + "External id": 4058134,"Record function id": 0, "Concrete Inputs": ["[6423040]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5141 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_reduce_scatter_base_", "pid": 1336756, "tid": 1381189, + "ts": 1655275642367.130, "dur": 360.316, + "args": { + "External id": 4058135,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "-1"], "Input type": ["float", "float", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], [], []], "Input Dims": [[6423040], [51384320], [], [], [], []], "Ev Idx": 5142 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336756, "tid": 1381189, + "ts": 1655275642394.772, "dur": 327.756, + "args": { + "External id": 4058136,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 3, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "3", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 6423040, "Process Group Name": "0", "Input type": ["float", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[51384320], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 5143, "In msg nelems": 51384320 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_reduce_scatter_base", "pid": 1336756, "tid": 1381189, + "ts": 1655275642405.444, "dur": 311.619, + "args": { + "External id": 4058137,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[51384320]], "Ev Idx": 5144 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336756, "tid": 1381189, + "ts": 1655275642749.393, "dur": 2.344, + "args": { + "External id": 4058138,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "3", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 5145, "In msg nelems": 0, "Rank": 3, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275642811.337, "dur": 6.736, + "args": { + "External id": 4058139,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5146 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275642861.940, "dur": 1.567, + "args": { + "External id": 4058140,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "256"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5147 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275642877.227, "dur": 1.286, + "args": { + "External id": 4058141,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "524544"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5148 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275642889.411, "dur": 3.346, + "args": { + "External id": 4058142,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "1048832"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5149 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275642902.925, "dur": 0.877, + "args": { + "External id": 4058143,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "1573120"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5150 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275642912.658, "dur": 0.916, + "args": { + "External id": 4058144,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5151 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275642924.825, "dur": 0.979, + "args": { + "External id": 4058145,"Record function id": 0, "Concrete Inputs": ["", "[704, 2048]", "[2048, 1]", "2097664"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5152 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275642936.579, "dur": 3.131, + "args": { + "External id": 4058146,"Record function id": 0, "Concrete Inputs": ["", "[704, 2048]", "[2048, 1]", "3539456"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5153 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275642951.832, "dur": 0.985, + "args": { + "External id": 4058147,"Record function id": 0, "Concrete Inputs": ["", "[256, 5632]", "[5632, 1]", "4981248"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5154 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: CompiledFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1655275643081.904, "dur": 2594.067, + "args": { + "External id": 4058148,"Record function id": 0, "Ev Idx": 5155 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.3)", "pid": 1336756, "tid": 1381189, + "ts": 1655275643101.230, "dur": 981.760, + "args": { + "External id": 4058149,"Record function id": 0, "Ev Idx": 5156 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.3)", "pid": 1336756, "tid": 1381189, + "ts": 1655275643115.055, "dur": 298.228, + "args": { + "External id": 4058150,"Record function id": 0, "Ev Idx": 5157 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275643190.909, "dur": 4.397, + "args": { + "External id": 4058151,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[51384320], []], "Ev Idx": 5158 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275643198.602, "dur": 1.244, + "args": { + "External id": 4058152,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 5159 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275643202.461, "dur": 1.004, + "args": { + "External id": 4058153,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 5160 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275643204.900, "dur": 0.829, + "args": { + "External id": 4058154,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 5161 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275643207.116, "dur": 0.925, + "args": { + "External id": 4058155,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 5162 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275643209.556, "dur": 2.761, + "args": { + "External id": 4058156,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 5163 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275643214.851, "dur": 0.691, + "args": { + "External id": 4058157,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 5164 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275643216.785, "dur": 0.910, + "args": { + "External id": 4058158,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 5165 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275643219.232, "dur": 0.797, + "args": { + "External id": 4058159,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 5166 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275643221.445, "dur": 0.631, + "args": { + "External id": 4058160,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 5167 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 1336756, "tid": 1381189, + "ts": 1655275643241.521, "dur": 145.085, + "args": { + "External id": 4058161,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 5168 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 1336756, "tid": 1381189, + "ts": 1655275643257.319, "dur": 124.272, + "args": { + "External id": 4058162,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 5169 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655275643274.136, "dur": 12.118, + "args": { + "External id": 4058163,"Record function id": 0, "Concrete Inputs": ["[2133]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5170 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1381189, + "ts": 1655275643289.317, "dur": 65.768, + "args": { + "External id": 4058164,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], [], []], "Ev Idx": 5171 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336756, "tid": 1381189, + "ts": 1655275643291.648, "dur": 63.159, + "args": { + "External id": 4058165,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], []], "Ev Idx": 5172 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275643295.714, "dur": 5.683, + "args": { + "External id": 4058166,"Record function id": 0, "Concrete Inputs": ["[2133]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5173 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1381189, + "ts": 1655275643303.037, "dur": 51.061, + "args": { + "External id": 4058167,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[2133], [2133], []], "Ev Idx": 5174 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::backward_prefetch for model.layers.2", "pid": 1336756, "tid": 1381189, + "ts": 1655275643507.305, "dur": 567.966, + "args": { + "External id": 4058168,"Record function id": 0, "Ev Idx": 5175 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.2)", "pid": 1336756, "tid": 1381189, + "ts": 1655275643523.650, "dur": 538.669, + "args": { + "External id": 4058169,"Record function id": 0, "Ev Idx": 5176 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655275643576.810, "dur": 5.113, + "args": { + "External id": 4058170,"Record function id": 0, "Concrete Inputs": ["[6423040]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5177 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336756, "tid": 1381189, + "ts": 1655275643601.426, "dur": 29.183, + "args": { + "External id": 4058171,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 5178 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275643606.372, "dur": 3.088, + "args": { + "External id": 4058172,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5179 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275643611.849, "dur": 0.372, + "args": { + "External id": 4058173,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5180 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275643613.754, "dur": 0.320, + "args": { + "External id": 4058174,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5181 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275643616.638, "dur": 0.220, + "args": { + "External id": 4058175,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5182 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275643617.957, "dur": 0.432, + "args": { + "External id": 4058176,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5183 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275643619.870, "dur": 0.664, + "args": { + "External id": 4058177,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5184 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275643622.134, "dur": 0.332, + "args": { + "External id": 4058178,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5185 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275643623.706, "dur": 0.138, + "args": { + "External id": 4058179,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5186 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275643625.925, "dur": 1.841, + "args": { + "External id": 4058180,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5187 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336756, "tid": 1381189, + "ts": 1655275643640.201, "dur": 30.947, + "args": { + "External id": 4058181,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 5188 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 1336756, "tid": 1381189, + "ts": 1655275643700.634, "dur": 97.795, + "args": { + "External id": 4058182,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "6423040", "8", "3", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [], [], [], [], [], []], "Ev Idx": 5189 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655275643710.501, "dur": 3.151, + "args": { + "External id": 4058183,"Record function id": 0, "Concrete Inputs": ["[51384320]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5190 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 1336756, "tid": 1381189, + "ts": 1655275643718.636, "dur": 10.095, + "args": { + "External id": 4058184,"Record function id": 0, "Concrete Inputs": ["", "0", "19269120", "6423040"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 5191 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1381189, + "ts": 1655275643722.743, "dur": 5.585, + "args": { + "External id": 4058185,"Record function id": 0, "Concrete Inputs": ["", "0", "19269120", "25692160", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[51384320], [], [], [], []], "Ev Idx": 5192 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275643726.522, "dur": 0.543, + "args": { + "External id": 4058186,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "[1]", "19269120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 5193 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336756, "tid": 1381189, + "ts": 1655275643735.925, "dur": 24.685, + "args": { + "External id": 4058187,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 5194 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275643738.045, "dur": 0.629, + "args": { + "External id": 4058188,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "19269120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5195 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275643740.678, "dur": 0.633, + "args": { + "External id": 4058189,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "19269376"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5196 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275643743.092, "dur": 0.482, + "args": { + "External id": 4058190,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "19793664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5197 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275643745.047, "dur": 0.167, + "args": { + "External id": 4058191,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "20317952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5198 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275643746.474, "dur": 0.556, + "args": { + "External id": 4058192,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "20842240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5199 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275643748.931, "dur": 1.814, + "args": { + "External id": 4058193,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "21366528"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5200 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275643752.567, "dur": 0.315, + "args": { + "External id": 4058194,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "21366784"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5201 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275643754.202, "dur": 0.339, + "args": { + "External id": 4058195,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "22808576"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5202 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275643755.967, "dur": 0.139, + "args": { + "External id": 4058196,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "24250368"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5203 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336756, "tid": 1381189, + "ts": 1655275643772.098, "dur": 19.261, + "args": { + "External id": 4058197,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 5204 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 1336756, "tid": 1381189, + "ts": 1655275643840.650, "dur": 111.307, + "args": { + "External id": 4058198,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[51384320], [6423040], [], [], []], "Ev Idx": 5205 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336756, "tid": 1381189, + "ts": 1655275643865.663, "dur": 82.946, + "args": { + "External id": 4058199,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 3, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "3", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 51384320, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[6423040], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 5206, "In msg nelems": 6423040 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 1336756, "tid": 1381189, + "ts": 1655275643874.713, "dur": 69.477, + "args": { + "External id": 4058200,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[6423040]], "Ev Idx": 5207 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336756, "tid": 1381189, + "ts": 1655275643968.072, "dur": 1.931, + "args": { + "External id": 4058201,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "3", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 5208, "In msg nelems": 0, "Rank": 3, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1655275644089.616, "dur": 1567.983, + "args": { + "External id": 4058202,"Sequence number": 40618360, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 5209 + } + }, + { + "ph": "f", "id": 220, "pid": 1336756, "tid": 1381189, "ts": 1655275644089.616, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275644195.241, "dur": 104.854, + "args": { + "External id": 4058203,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [5632, 1], [5632, 1]], "Input Dims": [[65536, 2048], [2048, 5632], [65536, 5632]], "Ev Idx": 5210 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_add_mul_rsub_silu_0", "pid": 1336756, "tid": 1381189, + "ts": 1655275644342.110, "dur": 36.329, + "args": { + "External id": 4058204,"kernel_hash": "c2zszzsomz26dv2qwvmiurvgyrl5qxtyn6ocoqkdpzzhfzwqp5q6", "grid": "grid(369098752,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "369098752"], "kernel_file": "/tmp/torchinductor_cvm/2z/c2zszzsomz26dv2qwvmiurvgyrl5qxtyn6ocoqkdpzzhfzwqp5q6.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[5632, 1], [5632, 1], [5632, 1], [23068672, 5632, 1], [23068672, 5632, 1], [23068672, 5632, 1], []], "Input Dims": [[65536, 5632], [65536, 5632], [65536, 5632], [16, 4096, 5632], [16, 4096, 5632], [16, 4096, 5632], []], "Ev Idx": 5211 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 1336756, "tid": 1381189, + "ts": 1655275644393.439, "dur": 69.058, + "args": { + "External id": 4058205,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[0, 1, 2048], [0, 5632, 1], [11534336, 5632, 1]], "Input Dims": [[1, 2048, 65536], [1, 65536, 5632], [1, 2048, 5632]], "Ev Idx": 5212 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275644475.592, "dur": 36.388, + "args": { + "External id": 4058206,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 5632], [2048, 1], [2048, 1]], "Input Dims": [[5632, 65536], [65536, 2048], [5632, 2048]], "Ev Idx": 5213 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275644518.389, "dur": 46.236, + "args": { + "External id": 4058207,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 5632], [5632, 2048], [65536, 2048]], "Ev Idx": 5214 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275644572.264, "dur": 28.091, + "args": { + "External id": 4058208,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 5632], [2048, 1], [2048, 1]], "Input Dims": [[5632, 65536], [65536, 2048], [5632, 2048]], "Ev Idx": 5215 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275644607.193, "dur": 42.589, + "args": { + "External id": 4058209,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 5632], [5632, 2048], [65536, 2048]], "Ev Idx": 5216 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_1", "pid": 1336756, "tid": 1381189, + "ts": 1655275644674.014, "dur": 22.917, + "args": { + "External id": 4058210,"kernel_hash": "cjd6g3jfgntyoifzno6l2urmnhif7alxtw6zz7miov66vywxwv7d", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/jd/cjd6g3jfgntyoifzno6l2urmnhif7alxtw6zz7miov66vywxwv7d.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[65536, 2048], [65536, 2048], []], "Ev Idx": 5217 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 1336756, "tid": 1381189, + "ts": 1655275644714.638, "dur": 26.406, + "args": { + "External id": 4058211,"kernel_hash": "cxhg545cyph4gbk5vymzyh72vho7oogk3ycan2lp4cxntklp5hew", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "65536", "2048", "1", "497", "132", "True", "2048", "True", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/xh/cxhg545cyph4gbk5vymzyh72vho7oogk3ycan2lp4cxntklp5hew.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [1], [2048, 1], [2048, 1], [2048, 1], [2048, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [2048], [65536, 2048], [65536, 2048], [132, 2048], [65536, 2048], [65536], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 5218 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 1336756, "tid": 1381189, + "ts": 1655275644759.581, "dur": 18.693, + "args": { + "External id": 4058212,"kernel_hash": "cu42i6zmxtvs2i7cs6x4ixaexke3lhgdiaye5oxwm7s3u6em6co4", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "66"], "kernel_file": "/tmp/torchinductor_cvm/u4/cu42i6zmxtvs2i7cs6x4ixaexke3lhgdiaye5oxwm7s3u6em6co4.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [4096, 1, 2048], [], []], "Input Dims": [[132, 2048], [1, 2048, 2], [], []], "Ev Idx": 5219 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 1336756, "tid": 1381189, + "ts": 1655275644792.049, "dur": 14.846, + "args": { + "External id": 4058213,"kernel_hash": "ckihofrorhmzazt2wfn2dz2m5wfx3auisu2gvfo2jsepr4zyekmq", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "2"], "kernel_file": "/tmp/torchinductor_cvm/ki/ckihofrorhmzazt2wfn2dz2m5wfx3auisu2gvfo2jsepr4zyekmq.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1, 2048], [2048, 1], [], []], "Input Dims": [[1, 2048, 2], [1, 2048], [], []], "Ev Idx": 5220 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275644815.536, "dur": 27.683, + "args": { + "External id": 4058214,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 5221 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275644846.584, "dur": 32.922, + "args": { + "External id": 4058215,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 5222 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 1336756, "tid": 1381189, + "ts": 1655275644904.953, "dur": 203.471, + "args": { + "External id": 4058216,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.125", "True", "-1", "-1", "0.", "", "False", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar", "long int"], "Input Strides": [[8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [131072, 4096, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 32, 4096], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 5223 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655275644977.372, "dur": 42.382, + "args": { + "External id": 4058217,"Record function id": 0, "Concrete Inputs": ["[16, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5224 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655275645022.994, "dur": 2.588, + "args": { + "External id": 4058218,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5225 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336756, "tid": 1381189, + "ts": 1655275645142.812, "dur": 26.817, + "args": { + "External id": 4058219,"kernel_hash": "cb6oumcqb462ndf2ivcd2sc6qg6mfjahptjw4ih7cesqhfpziv3b", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/b6/cb6oumcqb462ndf2ivcd2sc6qg6mfjahptjw4ih7cesqhfpziv3b.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 5226 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336756, "tid": 1381189, + "ts": 1655275645180.906, "dur": 13.753, + "args": { + "External id": 4058220,"kernel_hash": "cb6oumcqb462ndf2ivcd2sc6qg6mfjahptjw4ih7cesqhfpziv3b", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/b6/cb6oumcqb462ndf2ivcd2sc6qg6mfjahptjw4ih7cesqhfpziv3b.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 5227 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275645203.917, "dur": 42.539, + "args": { + "External id": 4058221,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 5228 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275645251.953, "dur": 35.673, + "args": { + "External id": 4058222,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 5229 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275645294.286, "dur": 20.712, + "args": { + "External id": 4058223,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 5230 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275645318.974, "dur": 29.966, + "args": { + "External id": 4058224,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 5231 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275645356.241, "dur": 19.514, + "args": { + "External id": 4058225,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 5232 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275645382.354, "dur": 31.157, + "args": { + "External id": 4058226,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 5233 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_4", "pid": 1336756, "tid": 1381189, + "ts": 1655275645450.310, "dur": 24.349, + "args": { + "External id": 4058227,"kernel_hash": "c7pqhdjojzeazwsh5g3ibnyk4m2nfh3q73e3zc7hljz4yvhe7c4h", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/7p/c7pqhdjojzeazwsh5g3ibnyk4m2nfh3q73e3zc7hljz4yvhe7c4h.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1], []], "Input Dims": [[65536, 2048], [65536, 2048], [65536, 2048], []], "Ev Idx": 5234 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_2", "pid": 1336756, "tid": 1381189, + "ts": 1655275645494.432, "dur": 22.254, + "args": { + "External id": 4058228,"kernel_hash": "cvgvwkysjpcw75q5t3guce5bep2so25f7i5zxc6ipt5f56shof73", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "65536", "2048", "1", "497", "132", "True", "2048", "False", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/vg/cvgvwkysjpcw75q5t3guce5bep2so25f7i5zxc6ipt5f56shof73.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [1], [2048, 1], [2048, 1], [2048, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [2048], [65536, 2048], [65536, 2048], [132, 2048], [65536], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 5235 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 1336756, "tid": 1381189, + "ts": 1655275645542.953, "dur": 22.319, + "args": { + "External id": 4058229,"kernel_hash": "cu42i6zmxtvs2i7cs6x4ixaexke3lhgdiaye5oxwm7s3u6em6co4", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "66"], "kernel_file": "/tmp/torchinductor_cvm/u4/cu42i6zmxtvs2i7cs6x4ixaexke3lhgdiaye5oxwm7s3u6em6co4.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [4096, 1, 2048], [], []], "Input Dims": [[132, 2048], [1, 2048, 2], [], []], "Ev Idx": 5236 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 1336756, "tid": 1381189, + "ts": 1655275645586.100, "dur": 14.160, + "args": { + "External id": 4058230,"kernel_hash": "ckihofrorhmzazt2wfn2dz2m5wfx3auisu2gvfo2jsepr4zyekmq", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "2"], "kernel_file": "/tmp/torchinductor_cvm/ki/ckihofrorhmzazt2wfn2dz2m5wfx3auisu2gvfo2jsepr4zyekmq.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1, 2048], [2048, 1], [], []], "Input Dims": [[1, 2048, 2], [1, 2048], [], []], "Ev Idx": 5237 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_5", "pid": 1336756, "tid": 1381189, + "ts": 1655275645612.438, "dur": 14.336, + "args": { + "External id": 4058231,"kernel_hash": "cckrpn5uuxyvbancoio3sz2onrjto236n54xx4ycphq5p6r3jlfj", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/ck/cckrpn5uuxyvbancoio3sz2onrjto236n54xx4ycphq5p6r3jlfj.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [8388608, 2048, 1], []], "Input Dims": [[65536, 2048], [65536, 2048], [16, 4096, 2048], []], "Ev Idx": 5238 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275645697.474, "dur": 20.035, + "args": { + "External id": 4058232,"Record function id": 0, "Ev Idx": 5239 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275645704.325, "dur": 12.375, + "args": { + "External id": 4058233,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 5240 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275645708.532, "dur": 7.209, + "args": { + "External id": 4058234,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 5241 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275645709.894, "dur": 5.753, + "args": { + "External id": 4058235,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 5242 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275645721.517, "dur": 4.337, + "args": { + "External id": 4058236,"Record function id": 0, "Ev Idx": 5243 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275645722.891, "dur": 2.533, + "args": { + "External id": 4058237,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 5244 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275645723.590, "dur": 1.335, + "args": { + "External id": 4058238,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 5245 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275645723.911, "dur": 0.946, + "args": { + "External id": 4058239,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 5246 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275645729.204, "dur": 3.670, + "args": { + "External id": 4058240,"Record function id": 0, "Ev Idx": 5247 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275645730.354, "dur": 2.108, + "args": { + "External id": 4058241,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 5248 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275645730.810, "dur": 1.237, + "args": { + "External id": 4058242,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 5249 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275645731.347, "dur": 0.569, + "args": { + "External id": 4058243,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 5250 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275645736.056, "dur": 3.740, + "args": { + "External id": 4058244,"Record function id": 0, "Ev Idx": 5251 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275645737.188, "dur": 2.222, + "args": { + "External id": 4058245,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 5252 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275645737.898, "dur": 1.120, + "args": { + "External id": 4058246,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 5253 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275645738.306, "dur": 0.637, + "args": { + "External id": 4058247,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 5254 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275645742.836, "dur": 3.199, + "args": { + "External id": 4058248,"Record function id": 0, "Ev Idx": 5255 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275645743.781, "dur": 1.868, + "args": { + "External id": 4058249,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 5256 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275645744.227, "dur": 0.972, + "args": { + "External id": 4058250,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 5257 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275645744.516, "dur": 0.619, + "args": { + "External id": 4058251,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 5258 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275645749.251, "dur": 3.278, + "args": { + "External id": 4058252,"Record function id": 0, "Ev Idx": 5259 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275645750.249, "dur": 1.848, + "args": { + "External id": 4058253,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 5260 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275645750.715, "dur": 0.961, + "args": { + "External id": 4058254,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 5261 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275645751.097, "dur": 0.514, + "args": { + "External id": 4058255,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 5262 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275645755.744, "dur": 4.610, + "args": { + "External id": 4058256,"Record function id": 0, "Ev Idx": 5263 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275645756.870, "dur": 3.097, + "args": { + "External id": 4058257,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 5264 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275645757.412, "dur": 2.129, + "args": { + "External id": 4058258,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 5265 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275645758.902, "dur": 0.541, + "args": { + "External id": 4058259,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 5266 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275645763.429, "dur": 9.759, + "args": { + "External id": 4058260,"Record function id": 0, "Ev Idx": 5267 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275645764.614, "dur": 8.169, + "args": { + "External id": 4058261,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 5268 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275645769.603, "dur": 2.674, + "args": { + "External id": 4058262,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 5269 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275645770.129, "dur": 2.088, + "args": { + "External id": 4058263,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 5270 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275645776.261, "dur": 3.893, + "args": { + "External id": 4058264,"Record function id": 0, "Ev Idx": 5271 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275645777.596, "dur": 2.174, + "args": { + "External id": 4058265,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 5272 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275645778.271, "dur": 1.076, + "args": { + "External id": 4058266,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 5273 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275645778.633, "dur": 0.639, + "args": { + "External id": 4058267,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 5274 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RegisterPostBackwardFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1655275645783.550, "dur": 37550.035, + "args": { + "External id": 4058268,"Record function id": 0, "Sequence number": 40618359, "Fwd thread id": 1, "Ev Idx": 5275 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1655275645784.976, "dur": 37540.528, + "args": { + "External id": 4058269,"Sequence number": 40618359, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 5276 + } + }, + { + "ph": "f", "id": 221, "pid": 1336756, "tid": 1381189, "ts": 1655275645784.976, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.3)", "pid": 1336756, "tid": 1381189, + "ts": 1655275645813.650, "dur": 38.229, + "args": { + "External id": 4058270,"Record function id": 0, "Ev Idx": 5277 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.3)", "pid": 1336756, "tid": 1381189, + "ts": 1655275645859.323, "dur": 61.230, + "args": { + "External id": 4058271,"Record function id": 0, "Ev Idx": 5278 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.3)", "pid": 1336756, "tid": 1381189, + "ts": 1655275645926.076, "dur": 37391.738, + "args": { + "External id": 4058272,"Record function id": 0, "Ev Idx": 5279 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655275646050.522, "dur": 7.778, + "args": { + "External id": 4058273,"Record function id": 0, "Concrete Inputs": ["[51384320]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5280 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275646069.309, "dur": 5.100, + "args": { + "External id": 4058274,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[51384320], []], "Ev Idx": 5281 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::chunk_cat", "pid": 1336756, "tid": 1381189, + "ts": 1655275646089.031, "dur": 36427.285, + "args": { + "External id": 4058275,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [2048, 1], [2048, 1], [2048, 1], [2048, 1], [1], [2048, 1], [2048, 1], [5632, 1]], [], [], [6423040, 1]], "Input Dims": [[[2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048], [5632, 2048], [5632, 2048], [2048, 5632]], [], [], [8, 6423040]], "Ev Idx": 5282 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_chunk_cat", "pid": 1336756, "tid": 1381189, + "ts": 1655275646102.742, "dur": 36405.163, + "args": { + "External id": 4058276,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [2048, 1], [2048, 1], [2048, 1], [2048, 1], [1], [2048, 1], [2048, 1], [5632, 1]], [], [], [6423040, 1]], "Input Dims": [[[2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048], [5632, 2048], [5632, 2048], [2048, 5632]], [], [], [8, 6423040]], "Ev Idx": 5283 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655275646140.245, "dur": 13.357, + "args": { + "External id": 4058277,"Record function id": 0, "Concrete Inputs": ["[12602]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5284 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1381189, + "ts": 1655275646159.764, "dur": 36311.165, + "args": { + "External id": 4058278,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[12602], [], [], [], [], [], [], []], "Ev Idx": 5285 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336756, "tid": 1381189, + "ts": 1655275646162.109, "dur": 36308.176, + "args": { + "External id": 4058279,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[12602], [], [], [], [], [], []], "Ev Idx": 5286 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275646166.207, "dur": 6.080, + "args": { + "External id": 4058280,"Record function id": 0, "Concrete Inputs": ["[12602]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5287 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1381189, + "ts": 1655275646175.067, "dur": 36291.877, + "args": { + "External id": 4058281,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[12602], [12602], []], "Ev Idx": 5288 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 1336756, "tid": 1381189, + "ts": 1655275682599.990, "dur": 8.275, + "args": { + "External id": 4058282,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "", "", "", "False"], "Input type": ["float", "ScalarList", "", "", "", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[51384320], [], [], [], [], []], "Ev Idx": 5289 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655275682602.865, "dur": 5.051, + "args": { + "External id": 4058283,"Record function id": 0, "Concrete Inputs": ["[6423040]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5290 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_reduce_scatter_base_", "pid": 1336756, "tid": 1381189, + "ts": 1655275682639.818, "dur": 391.326, + "args": { + "External id": 4058284,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "-1"], "Input type": ["float", "float", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], [], []], "Input Dims": [[6423040], [51384320], [], [], [], []], "Ev Idx": 5291 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336756, "tid": 1381189, + "ts": 1655275682667.962, "dur": 357.683, + "args": { + "External id": 4058285,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 3, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "3", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 6423040, "Process Group Name": "0", "Input type": ["float", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[51384320], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 5292, "In msg nelems": 51384320 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_reduce_scatter_base", "pid": 1336756, "tid": 1381189, + "ts": 1655275682678.573, "dur": 340.480, + "args": { + "External id": 4058286,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[51384320]], "Ev Idx": 5293 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336756, "tid": 1381189, + "ts": 1655275683054.086, "dur": 2.610, + "args": { + "External id": 4058287,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "3", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 5294, "In msg nelems": 0, "Rank": 3, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275683118.078, "dur": 6.972, + "args": { + "External id": 4058288,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5295 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275683168.927, "dur": 1.421, + "args": { + "External id": 4058289,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "256"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5296 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275683184.118, "dur": 3.321, + "args": { + "External id": 4058290,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "524544"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5297 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275683198.294, "dur": 1.213, + "args": { + "External id": 4058291,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "1048832"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5298 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275683209.472, "dur": 1.167, + "args": { + "External id": 4058292,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "1573120"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5299 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275683221.340, "dur": 0.750, + "args": { + "External id": 4058293,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5300 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275683232.531, "dur": 2.659, + "args": { + "External id": 4058294,"Record function id": 0, "Concrete Inputs": ["", "[704, 2048]", "[2048, 1]", "2097664"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5301 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275683249.211, "dur": 1.024, + "args": { + "External id": 4058295,"Record function id": 0, "Concrete Inputs": ["", "[704, 2048]", "[2048, 1]", "3539456"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5302 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275683260.009, "dur": 0.761, + "args": { + "External id": 4058296,"Record function id": 0, "Concrete Inputs": ["", "[256, 5632]", "[5632, 1]", "4981248"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5303 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: CompiledFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1655275683347.259, "dur": 2602.321, + "args": { + "External id": 4058297,"Record function id": 0, "Ev Idx": 5304 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.2)", "pid": 1336756, "tid": 1381189, + "ts": 1655275683365.564, "dur": 998.397, + "args": { + "External id": 4058298,"Record function id": 0, "Ev Idx": 5305 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.2)", "pid": 1336756, "tid": 1381189, + "ts": 1655275683377.934, "dur": 324.952, + "args": { + "External id": 4058299,"Record function id": 0, "Ev Idx": 5306 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275683474.825, "dur": 4.496, + "args": { + "External id": 4058300,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[51384320], []], "Ev Idx": 5307 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275683482.750, "dur": 1.120, + "args": { + "External id": 4058301,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 5308 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275683486.944, "dur": 0.768, + "args": { + "External id": 4058302,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 5309 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275683489.182, "dur": 2.538, + "args": { + "External id": 4058303,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 5310 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275683493.234, "dur": 1.016, + "args": { + "External id": 4058304,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 5311 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275683495.588, "dur": 0.856, + "args": { + "External id": 4058305,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 5312 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275683498.870, "dur": 0.746, + "args": { + "External id": 4058306,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 5313 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275683500.970, "dur": 0.862, + "args": { + "External id": 4058307,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 5314 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275683503.242, "dur": 1.095, + "args": { + "External id": 4058308,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 5315 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275683505.823, "dur": 0.704, + "args": { + "External id": 4058309,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 5316 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 1336756, "tid": 1381189, + "ts": 1655275683526.949, "dur": 147.068, + "args": { + "External id": 4058310,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 5317 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 1336756, "tid": 1381189, + "ts": 1655275683544.009, "dur": 125.706, + "args": { + "External id": 4058311,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 5318 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655275683560.465, "dur": 12.060, + "args": { + "External id": 4058312,"Record function id": 0, "Concrete Inputs": ["[2133]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5319 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1381189, + "ts": 1655275683575.433, "dur": 68.251, + "args": { + "External id": 4058313,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], [], []], "Ev Idx": 5320 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336756, "tid": 1381189, + "ts": 1655275683577.865, "dur": 65.517, + "args": { + "External id": 4058314,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], []], "Ev Idx": 5321 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275683581.663, "dur": 7.638, + "args": { + "External id": 4058315,"Record function id": 0, "Concrete Inputs": ["[2133]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5322 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1381189, + "ts": 1655275683591.036, "dur": 51.813, + "args": { + "External id": 4058316,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[2133], [2133], []], "Ev Idx": 5323 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::backward_prefetch for model.layers.1", "pid": 1336756, "tid": 1381189, + "ts": 1655275683781.728, "dur": 574.882, + "args": { + "External id": 4058317,"Record function id": 0, "Ev Idx": 5324 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.1)", "pid": 1336756, "tid": 1381189, + "ts": 1655275683797.275, "dur": 547.038, + "args": { + "External id": 4058318,"Record function id": 0, "Ev Idx": 5325 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655275683849.818, "dur": 4.516, + "args": { + "External id": 4058319,"Record function id": 0, "Concrete Inputs": ["[6423040]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5326 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336756, "tid": 1381189, + "ts": 1655275683877.396, "dur": 27.657, + "args": { + "External id": 4058320,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 5327 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275683883.744, "dur": 1.966, + "args": { + "External id": 4058321,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5328 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275683887.213, "dur": 0.470, + "args": { + "External id": 4058322,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5329 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275683888.875, "dur": 0.528, + "args": { + "External id": 4058323,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5330 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275683891.941, "dur": 0.380, + "args": { + "External id": 4058324,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5331 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275683893.313, "dur": 0.274, + "args": { + "External id": 4058325,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5332 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275683894.474, "dur": 0.334, + "args": { + "External id": 4058326,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5333 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275683896.616, "dur": 1.993, + "args": { + "External id": 4058327,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5334 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275683899.794, "dur": 0.402, + "args": { + "External id": 4058328,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5335 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275683901.543, "dur": 0.740, + "args": { + "External id": 4058329,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5336 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336756, "tid": 1381189, + "ts": 1655275683914.323, "dur": 29.341, + "args": { + "External id": 4058330,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 5337 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 1336756, "tid": 1381189, + "ts": 1655275683973.673, "dur": 144.665, + "args": { + "External id": 4058331,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "6423040", "8", "3", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [], [], [], [], [], []], "Ev Idx": 5338 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655275684022.558, "dur": 5.311, + "args": { + "External id": 4058332,"Record function id": 0, "Concrete Inputs": ["[51384320]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5339 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 1336756, "tid": 1381189, + "ts": 1655275684034.209, "dur": 10.635, + "args": { + "External id": 4058333,"Record function id": 0, "Concrete Inputs": ["", "0", "19269120", "6423040"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 5340 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1381189, + "ts": 1655275684038.407, "dur": 6.030, + "args": { + "External id": 4058334,"Record function id": 0, "Concrete Inputs": ["", "0", "19269120", "25692160", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[51384320], [], [], [], []], "Ev Idx": 5341 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275684042.222, "dur": 0.663, + "args": { + "External id": 4058335,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "[1]", "19269120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 5342 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336756, "tid": 1381189, + "ts": 1655275684052.690, "dur": 23.129, + "args": { + "External id": 4058336,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 5343 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275684054.771, "dur": 0.298, + "args": { + "External id": 4058337,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "19269120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5344 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275684056.205, "dur": 0.470, + "args": { + "External id": 4058338,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "19269376"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5345 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275684057.766, "dur": 0.871, + "args": { + "External id": 4058339,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "19793664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5346 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275684059.648, "dur": 2.353, + "args": { + "External id": 4058340,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "20317952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5347 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275684063.070, "dur": 0.591, + "args": { + "External id": 4058341,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "20842240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5348 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275684065.286, "dur": 0.328, + "args": { + "External id": 4058342,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "21366528"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5349 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275684068.761, "dur": 0.369, + "args": { + "External id": 4058343,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "21366784"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5350 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275684070.130, "dur": 0.438, + "args": { + "External id": 4058344,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "22808576"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5351 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275684071.537, "dur": 0.311, + "args": { + "External id": 4058345,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "24250368"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5352 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336756, "tid": 1381189, + "ts": 1655275684087.830, "dur": 22.635, + "args": { + "External id": 4058346,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 5353 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 1336756, "tid": 1381189, + "ts": 1655275684167.097, "dur": 111.641, + "args": { + "External id": 4058347,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[51384320], [6423040], [], [], []], "Ev Idx": 5354 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336756, "tid": 1381189, + "ts": 1655275684191.586, "dur": 83.726, + "args": { + "External id": 4058348,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 3, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "3", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 51384320, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[6423040], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 5355, "In msg nelems": 6423040 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 1336756, "tid": 1381189, + "ts": 1655275684200.974, "dur": 70.379, + "args": { + "External id": 4058349,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[6423040]], "Ev Idx": 5356 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336756, "tid": 1381189, + "ts": 1655275684292.209, "dur": 1.834, + "args": { + "External id": 4058350,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "3", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 5357, "In msg nelems": 0, "Rank": 3, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1655275684371.088, "dur": 1559.416, + "args": { + "External id": 4058351,"Sequence number": 40618358, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 5358 + } + }, + { + "ph": "f", "id": 222, "pid": 1336756, "tid": 1381189, "ts": 1655275684371.088, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275684497.400, "dur": 105.212, + "args": { + "External id": 4058352,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [5632, 1], [5632, 1]], "Input Dims": [[65536, 2048], [2048, 5632], [65536, 5632]], "Ev Idx": 5359 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_add_mul_rsub_silu_0", "pid": 1336756, "tid": 1381189, + "ts": 1655275684644.753, "dur": 38.080, + "args": { + "External id": 4058353,"kernel_hash": "c2zszzsomz26dv2qwvmiurvgyrl5qxtyn6ocoqkdpzzhfzwqp5q6", "grid": "grid(369098752,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "369098752"], "kernel_file": "/tmp/torchinductor_cvm/2z/c2zszzsomz26dv2qwvmiurvgyrl5qxtyn6ocoqkdpzzhfzwqp5q6.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[5632, 1], [5632, 1], [5632, 1], [23068672, 5632, 1], [23068672, 5632, 1], [23068672, 5632, 1], []], "Input Dims": [[65536, 5632], [65536, 5632], [65536, 5632], [16, 4096, 5632], [16, 4096, 5632], [16, 4096, 5632], []], "Ev Idx": 5360 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 1336756, "tid": 1381189, + "ts": 1655275684699.341, "dur": 47.784, + "args": { + "External id": 4058354,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[0, 1, 2048], [0, 5632, 1], [11534336, 5632, 1]], "Input Dims": [[1, 2048, 65536], [1, 65536, 5632], [1, 2048, 5632]], "Ev Idx": 5361 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275684756.477, "dur": 31.734, + "args": { + "External id": 4058355,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 5632], [2048, 1], [2048, 1]], "Input Dims": [[5632, 65536], [65536, 2048], [5632, 2048]], "Ev Idx": 5362 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275684796.249, "dur": 45.833, + "args": { + "External id": 4058356,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 5632], [5632, 2048], [65536, 2048]], "Ev Idx": 5363 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275684848.587, "dur": 28.555, + "args": { + "External id": 4058357,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 5632], [2048, 1], [2048, 1]], "Input Dims": [[5632, 65536], [65536, 2048], [5632, 2048]], "Ev Idx": 5364 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275684883.991, "dur": 43.128, + "args": { + "External id": 4058358,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 5632], [5632, 2048], [65536, 2048]], "Ev Idx": 5365 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_1", "pid": 1336756, "tid": 1381189, + "ts": 1655275684950.081, "dur": 20.145, + "args": { + "External id": 4058359,"kernel_hash": "cjd6g3jfgntyoifzno6l2urmnhif7alxtw6zz7miov66vywxwv7d", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/jd/cjd6g3jfgntyoifzno6l2urmnhif7alxtw6zz7miov66vywxwv7d.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[65536, 2048], [65536, 2048], []], "Ev Idx": 5366 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 1336756, "tid": 1381189, + "ts": 1655275685033.076, "dur": 30.763, + "args": { + "External id": 4058360,"kernel_hash": "cxhg545cyph4gbk5vymzyh72vho7oogk3ycan2lp4cxntklp5hew", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "65536", "2048", "1", "497", "132", "True", "2048", "True", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/xh/cxhg545cyph4gbk5vymzyh72vho7oogk3ycan2lp4cxntklp5hew.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [1], [2048, 1], [2048, 1], [2048, 1], [2048, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [2048], [65536, 2048], [65536, 2048], [132, 2048], [65536, 2048], [65536], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 5367 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 1336756, "tid": 1381189, + "ts": 1655275685088.687, "dur": 17.530, + "args": { + "External id": 4058361,"kernel_hash": "cu42i6zmxtvs2i7cs6x4ixaexke3lhgdiaye5oxwm7s3u6em6co4", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "66"], "kernel_file": "/tmp/torchinductor_cvm/u4/cu42i6zmxtvs2i7cs6x4ixaexke3lhgdiaye5oxwm7s3u6em6co4.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [4096, 1, 2048], [], []], "Input Dims": [[132, 2048], [1, 2048, 2], [], []], "Ev Idx": 5368 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 1336756, "tid": 1381189, + "ts": 1655275685121.799, "dur": 14.452, + "args": { + "External id": 4058362,"kernel_hash": "ckihofrorhmzazt2wfn2dz2m5wfx3auisu2gvfo2jsepr4zyekmq", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "2"], "kernel_file": "/tmp/torchinductor_cvm/ki/ckihofrorhmzazt2wfn2dz2m5wfx3auisu2gvfo2jsepr4zyekmq.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1, 2048], [2048, 1], [], []], "Input Dims": [[1, 2048, 2], [1, 2048], [], []], "Ev Idx": 5369 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275685144.939, "dur": 32.649, + "args": { + "External id": 4058363,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 5370 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275685180.913, "dur": 33.361, + "args": { + "External id": 4058364,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 5371 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 1336756, "tid": 1381189, + "ts": 1655275685242.170, "dur": 162.111, + "args": { + "External id": 4058365,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.125", "True", "-1", "-1", "0.", "", "False", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar", "long int"], "Input Strides": [[8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [131072, 4096, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 32, 4096], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 5372 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655275685316.788, "dur": 5.726, + "args": { + "External id": 4058366,"Record function id": 0, "Concrete Inputs": ["[16, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5373 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655275685324.461, "dur": 2.094, + "args": { + "External id": 4058367,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5374 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336756, "tid": 1381189, + "ts": 1655275685455.930, "dur": 26.309, + "args": { + "External id": 4058368,"kernel_hash": "cb6oumcqb462ndf2ivcd2sc6qg6mfjahptjw4ih7cesqhfpziv3b", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/b6/cb6oumcqb462ndf2ivcd2sc6qg6mfjahptjw4ih7cesqhfpziv3b.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 5375 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336756, "tid": 1381189, + "ts": 1655275685493.728, "dur": 13.304, + "args": { + "External id": 4058369,"kernel_hash": "cb6oumcqb462ndf2ivcd2sc6qg6mfjahptjw4ih7cesqhfpziv3b", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/b6/cb6oumcqb462ndf2ivcd2sc6qg6mfjahptjw4ih7cesqhfpziv3b.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 5376 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275685515.827, "dur": 37.828, + "args": { + "External id": 4058370,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 5377 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275685559.210, "dur": 33.648, + "args": { + "External id": 4058371,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 5378 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275685599.533, "dur": 19.556, + "args": { + "External id": 4058372,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 5379 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275685624.629, "dur": 29.068, + "args": { + "External id": 4058373,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 5380 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275685658.637, "dur": 18.958, + "args": { + "External id": 4058374,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 5381 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275685682.868, "dur": 29.238, + "args": { + "External id": 4058375,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 5382 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_4", "pid": 1336756, "tid": 1381189, + "ts": 1655275685730.635, "dur": 20.362, + "args": { + "External id": 4058376,"kernel_hash": "c7pqhdjojzeazwsh5g3ibnyk4m2nfh3q73e3zc7hljz4yvhe7c4h", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/7p/c7pqhdjojzeazwsh5g3ibnyk4m2nfh3q73e3zc7hljz4yvhe7c4h.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1], []], "Input Dims": [[65536, 2048], [65536, 2048], [65536, 2048], []], "Ev Idx": 5383 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_2", "pid": 1336756, "tid": 1381189, + "ts": 1655275685768.211, "dur": 22.983, + "args": { + "External id": 4058377,"kernel_hash": "cvgvwkysjpcw75q5t3guce5bep2so25f7i5zxc6ipt5f56shof73", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "65536", "2048", "1", "497", "132", "True", "2048", "False", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/vg/cvgvwkysjpcw75q5t3guce5bep2so25f7i5zxc6ipt5f56shof73.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [1], [2048, 1], [2048, 1], [2048, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [2048], [65536, 2048], [65536, 2048], [132, 2048], [65536], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 5384 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 1336756, "tid": 1381189, + "ts": 1655275685804.277, "dur": 31.011, + "args": { + "External id": 4058378,"kernel_hash": "cu42i6zmxtvs2i7cs6x4ixaexke3lhgdiaye5oxwm7s3u6em6co4", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "66"], "kernel_file": "/tmp/torchinductor_cvm/u4/cu42i6zmxtvs2i7cs6x4ixaexke3lhgdiaye5oxwm7s3u6em6co4.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [4096, 1, 2048], [], []], "Input Dims": [[132, 2048], [1, 2048, 2], [], []], "Ev Idx": 5385 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 1336756, "tid": 1381189, + "ts": 1655275685860.091, "dur": 15.546, + "args": { + "External id": 4058379,"kernel_hash": "ckihofrorhmzazt2wfn2dz2m5wfx3auisu2gvfo2jsepr4zyekmq", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "2"], "kernel_file": "/tmp/torchinductor_cvm/ki/ckihofrorhmzazt2wfn2dz2m5wfx3auisu2gvfo2jsepr4zyekmq.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1, 2048], [2048, 1], [], []], "Input Dims": [[1, 2048, 2], [1, 2048], [], []], "Ev Idx": 5386 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_5", "pid": 1336756, "tid": 1381189, + "ts": 1655275685888.145, "dur": 14.871, + "args": { + "External id": 4058380,"kernel_hash": "cckrpn5uuxyvbancoio3sz2onrjto236n54xx4ycphq5p6r3jlfj", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/ck/cckrpn5uuxyvbancoio3sz2onrjto236n54xx4ycphq5p6r3jlfj.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [8388608, 2048, 1], []], "Input Dims": [[65536, 2048], [65536, 2048], [16, 4096, 2048], []], "Ev Idx": 5387 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275685971.168, "dur": 54.358, + "args": { + "External id": 4058381,"Record function id": 0, "Ev Idx": 5388 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275685974.039, "dur": 49.782, + "args": { + "External id": 4058382,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 5389 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275686016.136, "dur": 6.304, + "args": { + "External id": 4058383,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 5390 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275686017.757, "dur": 4.394, + "args": { + "External id": 4058384,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 5391 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275686031.734, "dur": 5.136, + "args": { + "External id": 4058385,"Record function id": 0, "Ev Idx": 5392 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275686033.477, "dur": 2.922, + "args": { + "External id": 4058386,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 5393 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275686034.588, "dur": 1.291, + "args": { + "External id": 4058387,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 5394 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275686034.926, "dur": 0.864, + "args": { + "External id": 4058388,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 5395 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275686043.581, "dur": 3.907, + "args": { + "External id": 4058389,"Record function id": 0, "Ev Idx": 5396 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275686044.823, "dur": 2.250, + "args": { + "External id": 4058390,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 5397 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275686045.400, "dur": 1.281, + "args": { + "External id": 4058391,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 5398 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275686045.866, "dur": 0.723, + "args": { + "External id": 4058392,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 5399 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275686050.805, "dur": 4.054, + "args": { + "External id": 4058393,"Record function id": 0, "Ev Idx": 5400 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275686052.023, "dur": 2.372, + "args": { + "External id": 4058394,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 5401 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275686052.676, "dur": 1.327, + "args": { + "External id": 4058395,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 5402 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275686053.263, "dur": 0.676, + "args": { + "External id": 4058396,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 5403 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275686058.019, "dur": 3.363, + "args": { + "External id": 4058397,"Record function id": 0, "Ev Idx": 5404 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275686059.123, "dur": 1.863, + "args": { + "External id": 4058398,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 5405 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275686059.620, "dur": 0.970, + "args": { + "External id": 4058399,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 5406 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275686059.952, "dur": 0.539, + "args": { + "External id": 4058400,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 5407 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275686064.516, "dur": 4.731, + "args": { + "External id": 4058401,"Record function id": 0, "Ev Idx": 5408 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275686065.579, "dur": 3.224, + "args": { + "External id": 4058402,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 5409 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275686066.236, "dur": 2.179, + "args": { + "External id": 4058403,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 5410 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275686067.687, "dur": 0.605, + "args": { + "External id": 4058404,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 5411 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275686072.419, "dur": 5.913, + "args": { + "External id": 4058405,"Record function id": 0, "Ev Idx": 5412 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275686073.531, "dur": 4.357, + "args": { + "External id": 4058406,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 5413 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275686074.252, "dur": 3.175, + "args": { + "External id": 4058407,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 5414 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275686074.655, "dur": 2.706, + "args": { + "External id": 4058408,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 5415 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275686081.511, "dur": 3.873, + "args": { + "External id": 4058409,"Record function id": 0, "Ev Idx": 5416 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275686082.664, "dur": 2.310, + "args": { + "External id": 4058410,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 5417 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275686083.103, "dur": 1.439, + "args": { + "External id": 4058411,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 5418 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275686083.775, "dur": 0.693, + "args": { + "External id": 4058412,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 5419 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275686088.358, "dur": 3.970, + "args": { + "External id": 4058413,"Record function id": 0, "Ev Idx": 5420 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275686089.346, "dur": 2.580, + "args": { + "External id": 4058414,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 5421 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275686090.143, "dur": 1.374, + "args": { + "External id": 4058415,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 5422 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275686090.681, "dur": 0.762, + "args": { + "External id": 4058416,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 5423 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RegisterPostBackwardFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1655275686095.756, "dur": 37025.181, + "args": { + "External id": 4058417,"Record function id": 0, "Sequence number": 40618357, "Fwd thread id": 1, "Ev Idx": 5424 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1655275686097.158, "dur": 37015.071, + "args": { + "External id": 4058418,"Sequence number": 40618357, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 5425 + } + }, + { + "ph": "f", "id": 223, "pid": 1336756, "tid": 1381189, "ts": 1655275686097.158, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.2)", "pid": 1336756, "tid": 1381189, + "ts": 1655275686125.532, "dur": 36.059, + "args": { + "External id": 4058419,"Record function id": 0, "Ev Idx": 5426 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.2)", "pid": 1336756, "tid": 1381189, + "ts": 1655275686168.637, "dur": 62.257, + "args": { + "External id": 4058420,"Record function id": 0, "Ev Idx": 5427 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.2)", "pid": 1336756, "tid": 1381189, + "ts": 1655275686236.715, "dur": 36867.529, + "args": { + "External id": 4058421,"Record function id": 0, "Ev Idx": 5428 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655275686322.460, "dur": 6.642, + "args": { + "External id": 4058422,"Record function id": 0, "Concrete Inputs": ["[51384320]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5429 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275686339.139, "dur": 4.732, + "args": { + "External id": 4058423,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[51384320], []], "Ev Idx": 5430 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::chunk_cat", "pid": 1336756, "tid": 1381189, + "ts": 1655275686358.894, "dur": 35885.206, + "args": { + "External id": 4058424,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [2048, 1], [2048, 1], [2048, 1], [2048, 1], [1], [2048, 1], [2048, 1], [5632, 1]], [], [], [6423040, 1]], "Input Dims": [[[2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048], [5632, 2048], [5632, 2048], [2048, 5632]], [], [], [8, 6423040]], "Ev Idx": 5431 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_chunk_cat", "pid": 1336756, "tid": 1381189, + "ts": 1655275686371.820, "dur": 35863.833, + "args": { + "External id": 4058425,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [2048, 1], [2048, 1], [2048, 1], [2048, 1], [1], [2048, 1], [2048, 1], [5632, 1]], [], [], [6423040, 1]], "Input Dims": [[[2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048], [5632, 2048], [5632, 2048], [2048, 5632]], [], [], [8, 6423040]], "Ev Idx": 5432 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655275686435.040, "dur": 14.178, + "args": { + "External id": 4058426,"Record function id": 0, "Concrete Inputs": ["[12602]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5433 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1381189, + "ts": 1655275686455.668, "dur": 35743.260, + "args": { + "External id": 4058427,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[12602], [], [], [], [], [], [], []], "Ev Idx": 5434 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336756, "tid": 1381189, + "ts": 1655275686458.091, "dur": 35740.208, + "args": { + "External id": 4058428,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[12602], [], [], [], [], [], []], "Ev Idx": 5435 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275686462.812, "dur": 6.275, + "args": { + "External id": 4058429,"Record function id": 0, "Concrete Inputs": ["[12602]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5436 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1381189, + "ts": 1655275686472.386, "dur": 35722.384, + "args": { + "External id": 4058430,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[12602], [12602], []], "Ev Idx": 5437 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 1336756, "tid": 1381189, + "ts": 1655275722329.915, "dur": 8.183, + "args": { + "External id": 4058431,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "", "", "", "False"], "Input type": ["float", "ScalarList", "", "", "", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[51384320], [], [], [], [], []], "Ev Idx": 5438 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655275722332.726, "dur": 5.043, + "args": { + "External id": 4058432,"Record function id": 0, "Concrete Inputs": ["[6423040]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5439 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_reduce_scatter_base_", "pid": 1336756, "tid": 1381189, + "ts": 1655275722368.199, "dur": 411.684, + "args": { + "External id": 4058433,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "-1"], "Input type": ["float", "float", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], [], []], "Input Dims": [[6423040], [51384320], [], [], [], []], "Ev Idx": 5440 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336756, "tid": 1381189, + "ts": 1655275722398.107, "dur": 376.317, + "args": { + "External id": 4058434,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 3, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "3", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 6423040, "Process Group Name": "0", "Input type": ["float", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[51384320], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 5441, "In msg nelems": 51384320 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_reduce_scatter_base", "pid": 1336756, "tid": 1381189, + "ts": 1655275722408.574, "dur": 359.871, + "args": { + "External id": 4058435,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[51384320]], "Ev Idx": 5442 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336756, "tid": 1381189, + "ts": 1655275722802.217, "dur": 2.239, + "args": { + "External id": 4058436,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "3", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 5443, "In msg nelems": 0, "Rank": 3, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275722865.133, "dur": 6.845, + "args": { + "External id": 4058437,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5444 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275722916.375, "dur": 3.424, + "args": { + "External id": 4058438,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "256"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5445 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275722934.732, "dur": 1.094, + "args": { + "External id": 4058439,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "524544"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5446 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275722946.321, "dur": 0.856, + "args": { + "External id": 4058440,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "1048832"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5447 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275722957.923, "dur": 1.023, + "args": { + "External id": 4058441,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "1573120"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5448 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275722968.589, "dur": 2.709, + "args": { + "External id": 4058442,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5449 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275722980.672, "dur": 35.249, + "args": { + "External id": 4058443,"Record function id": 0, "Concrete Inputs": ["", "[704, 2048]", "[2048, 1]", "2097664"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5450 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275723032.185, "dur": 1.300, + "args": { + "External id": 4058444,"Record function id": 0, "Concrete Inputs": ["", "[704, 2048]", "[2048, 1]", "3539456"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5451 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275723042.798, "dur": 0.745, + "args": { + "External id": 4058445,"Record function id": 0, "Concrete Inputs": ["", "[256, 5632]", "[5632, 1]", "4981248"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5452 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: CompiledFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1655275723136.578, "dur": 2593.458, + "args": { + "External id": 4058446,"Record function id": 0, "Ev Idx": 5453 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.1)", "pid": 1336756, "tid": 1381189, + "ts": 1655275723156.140, "dur": 967.453, + "args": { + "External id": 4058447,"Record function id": 0, "Ev Idx": 5454 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.1)", "pid": 1336756, "tid": 1381189, + "ts": 1655275723170.221, "dur": 318.906, + "args": { + "External id": 4058448,"Record function id": 0, "Ev Idx": 5455 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275723246.617, "dur": 4.099, + "args": { + "External id": 4058449,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[51384320], []], "Ev Idx": 5456 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275723253.615, "dur": 2.571, + "args": { + "External id": 4058450,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 5457 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275723257.811, "dur": 0.928, + "args": { + "External id": 4058451,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 5458 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275723260.224, "dur": 0.869, + "args": { + "External id": 4058452,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 5459 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275723262.332, "dur": 0.903, + "args": { + "External id": 4058453,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 5460 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275723265.959, "dur": 0.863, + "args": { + "External id": 4058454,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 5461 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275723268.189, "dur": 0.954, + "args": { + "External id": 4058455,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 5462 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275723270.435, "dur": 0.907, + "args": { + "External id": 4058456,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 5463 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275723272.865, "dur": 0.935, + "args": { + "External id": 4058457,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 5464 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275723275.933, "dur": 2.325, + "args": { + "External id": 4058458,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 5465 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 1336756, "tid": 1381189, + "ts": 1655275723295.121, "dur": 163.555, + "args": { + "External id": 4058459,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 5466 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 1336756, "tid": 1381189, + "ts": 1655275723310.748, "dur": 142.700, + "args": { + "External id": 4058460,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 5467 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655275723326.526, "dur": 11.864, + "args": { + "External id": 4058461,"Record function id": 0, "Concrete Inputs": ["[2133]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5468 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1381189, + "ts": 1655275723341.339, "dur": 66.816, + "args": { + "External id": 4058462,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], [], []], "Ev Idx": 5469 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336756, "tid": 1381189, + "ts": 1655275723344.051, "dur": 63.852, + "args": { + "External id": 4058463,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], []], "Ev Idx": 5470 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275723347.695, "dur": 5.912, + "args": { + "External id": 4058464,"Record function id": 0, "Concrete Inputs": ["[2133]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5471 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1381189, + "ts": 1655275723355.210, "dur": 52.186, + "args": { + "External id": 4058465,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[2133], [2133], []], "Ev Idx": 5472 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::backward_prefetch for model.layers.0", "pid": 1336756, "tid": 1381189, + "ts": 1655275723572.242, "dur": 543.683, + "args": { + "External id": 4058466,"Record function id": 0, "Ev Idx": 5473 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.0)", "pid": 1336756, "tid": 1381189, + "ts": 1655275723589.114, "dur": 514.953, + "args": { + "External id": 4058467,"Record function id": 0, "Ev Idx": 5474 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655275723645.654, "dur": 5.303, + "args": { + "External id": 4058468,"Record function id": 0, "Concrete Inputs": ["[6423040]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5475 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336756, "tid": 1381189, + "ts": 1655275723665.972, "dur": 23.376, + "args": { + "External id": 4058469,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 5476 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275723670.590, "dur": 2.308, + "args": { + "External id": 4058470,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5477 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275723674.784, "dur": 0.246, + "args": { + "External id": 4058471,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5478 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275723676.072, "dur": 0.190, + "args": { + "External id": 4058472,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5479 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275723677.932, "dur": 0.382, + "args": { + "External id": 4058473,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5480 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275723679.188, "dur": 1.682, + "args": { + "External id": 4058474,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5481 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275723681.971, "dur": 0.312, + "args": { + "External id": 4058475,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5482 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275723683.010, "dur": 0.382, + "args": { + "External id": 4058476,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5483 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275723684.597, "dur": 0.517, + "args": { + "External id": 4058477,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5484 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275723686.144, "dur": 0.435, + "args": { + "External id": 4058478,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5485 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336756, "tid": 1381189, + "ts": 1655275723699.684, "dur": 27.628, + "args": { + "External id": 4058479,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 5486 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 1336756, "tid": 1381189, + "ts": 1655275723756.566, "dur": 90.111, + "args": { + "External id": 4058480,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "6423040", "8", "3", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [], [], [], [], [], []], "Ev Idx": 5487 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655275723766.313, "dur": 2.823, + "args": { + "External id": 4058481,"Record function id": 0, "Concrete Inputs": ["[51384320]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5488 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 1336756, "tid": 1381189, + "ts": 1655275723773.496, "dur": 9.829, + "args": { + "External id": 4058482,"Record function id": 0, "Concrete Inputs": ["", "0", "19269120", "6423040"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 5489 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1381189, + "ts": 1655275723777.700, "dur": 5.192, + "args": { + "External id": 4058483,"Record function id": 0, "Concrete Inputs": ["", "0", "19269120", "25692160", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[51384320], [], [], [], []], "Ev Idx": 5490 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275723780.892, "dur": 0.640, + "args": { + "External id": 4058484,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "[1]", "19269120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 5491 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336756, "tid": 1381189, + "ts": 1655275723789.304, "dur": 21.089, + "args": { + "External id": 4058485,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 5492 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275723790.781, "dur": 0.384, + "args": { + "External id": 4058486,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "19269120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5493 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275723792.782, "dur": 1.861, + "args": { + "External id": 4058487,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "19269376"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5494 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275723796.022, "dur": 0.304, + "args": { + "External id": 4058488,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "19793664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5495 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275723797.736, "dur": 0.293, + "args": { + "External id": 4058489,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "20317952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5496 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275723799.769, "dur": 0.318, + "args": { + "External id": 4058490,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "20842240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5497 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275723801.236, "dur": 0.431, + "args": { + "External id": 4058491,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "21366528"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5498 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275723803.278, "dur": 0.376, + "args": { + "External id": 4058492,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "21366784"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5499 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275723805.048, "dur": 0.403, + "args": { + "External id": 4058493,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "22808576"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5500 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275723806.331, "dur": 0.335, + "args": { + "External id": 4058494,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "24250368"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5501 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336756, "tid": 1381189, + "ts": 1655275723820.999, "dur": 17.634, + "args": { + "External id": 4058495,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 5502 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 1336756, "tid": 1381189, + "ts": 1655275723888.697, "dur": 145.599, + "args": { + "External id": 4058496,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[51384320], [6423040], [], [], []], "Ev Idx": 5503 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336756, "tid": 1381189, + "ts": 1655275723909.873, "dur": 120.430, + "args": { + "External id": 4058497,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 3, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "3", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 51384320, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[6423040], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 5504, "In msg nelems": 6423040 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 1336756, "tid": 1381189, + "ts": 1655275723920.453, "dur": 104.478, + "args": { + "External id": 4058498,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[6423040]], "Ev Idx": 5505 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336756, "tid": 1381189, + "ts": 1655275724051.193, "dur": 2.397, + "args": { + "External id": 4058499,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "3", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 5506, "In msg nelems": 0, "Rank": 3, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1655275724131.335, "dur": 1577.367, + "args": { + "External id": 4058500,"Sequence number": 40618356, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 5507 + } + }, + { + "ph": "f", "id": 224, "pid": 1336756, "tid": 1381189, "ts": 1655275724131.335, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275724236.146, "dur": 106.255, + "args": { + "External id": 4058501,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [5632, 1], [5632, 1]], "Input Dims": [[65536, 2048], [2048, 5632], [65536, 5632]], "Ev Idx": 5508 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_add_mul_rsub_silu_0", "pid": 1336756, "tid": 1381189, + "ts": 1655275724381.578, "dur": 55.140, + "args": { + "External id": 4058502,"kernel_hash": "c2zszzsomz26dv2qwvmiurvgyrl5qxtyn6ocoqkdpzzhfzwqp5q6", "grid": "grid(369098752,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "369098752"], "kernel_file": "/tmp/torchinductor_cvm/2z/c2zszzsomz26dv2qwvmiurvgyrl5qxtyn6ocoqkdpzzhfzwqp5q6.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[5632, 1], [5632, 1], [5632, 1], [23068672, 5632, 1], [23068672, 5632, 1], [23068672, 5632, 1], []], "Input Dims": [[65536, 5632], [65536, 5632], [65536, 5632], [16, 4096, 5632], [16, 4096, 5632], [16, 4096, 5632], []], "Ev Idx": 5509 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 1336756, "tid": 1381189, + "ts": 1655275724455.903, "dur": 54.485, + "args": { + "External id": 4058503,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[0, 1, 2048], [0, 5632, 1], [11534336, 5632, 1]], "Input Dims": [[1, 2048, 65536], [1, 65536, 5632], [1, 2048, 5632]], "Ev Idx": 5510 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275724522.071, "dur": 32.820, + "args": { + "External id": 4058504,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 5632], [2048, 1], [2048, 1]], "Input Dims": [[5632, 65536], [65536, 2048], [5632, 2048]], "Ev Idx": 5511 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275724561.324, "dur": 45.982, + "args": { + "External id": 4058505,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 5632], [5632, 2048], [65536, 2048]], "Ev Idx": 5512 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275724614.589, "dur": 27.677, + "args": { + "External id": 4058506,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 5632], [2048, 1], [2048, 1]], "Input Dims": [[5632, 65536], [65536, 2048], [5632, 2048]], "Ev Idx": 5513 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275724648.977, "dur": 42.336, + "args": { + "External id": 4058507,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 5632], [5632, 2048], [65536, 2048]], "Ev Idx": 5514 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_1", "pid": 1336756, "tid": 1381189, + "ts": 1655275724717.181, "dur": 22.341, + "args": { + "External id": 4058508,"kernel_hash": "cjd6g3jfgntyoifzno6l2urmnhif7alxtw6zz7miov66vywxwv7d", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/jd/cjd6g3jfgntyoifzno6l2urmnhif7alxtw6zz7miov66vywxwv7d.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[65536, 2048], [65536, 2048], []], "Ev Idx": 5515 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 1336756, "tid": 1381189, + "ts": 1655275724757.676, "dur": 27.963, + "args": { + "External id": 4058509,"kernel_hash": "cxhg545cyph4gbk5vymzyh72vho7oogk3ycan2lp4cxntklp5hew", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "65536", "2048", "1", "497", "132", "True", "2048", "True", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/xh/cxhg545cyph4gbk5vymzyh72vho7oogk3ycan2lp4cxntklp5hew.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [1], [2048, 1], [2048, 1], [2048, 1], [2048, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [2048], [65536, 2048], [65536, 2048], [132, 2048], [65536, 2048], [65536], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 5516 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 1336756, "tid": 1381189, + "ts": 1655275724805.678, "dur": 18.275, + "args": { + "External id": 4058510,"kernel_hash": "cu42i6zmxtvs2i7cs6x4ixaexke3lhgdiaye5oxwm7s3u6em6co4", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "66"], "kernel_file": "/tmp/torchinductor_cvm/u4/cu42i6zmxtvs2i7cs6x4ixaexke3lhgdiaye5oxwm7s3u6em6co4.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [4096, 1, 2048], [], []], "Input Dims": [[132, 2048], [1, 2048, 2], [], []], "Ev Idx": 5517 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 1336756, "tid": 1381189, + "ts": 1655275724836.519, "dur": 14.879, + "args": { + "External id": 4058511,"kernel_hash": "ckihofrorhmzazt2wfn2dz2m5wfx3auisu2gvfo2jsepr4zyekmq", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "2"], "kernel_file": "/tmp/torchinductor_cvm/ki/ckihofrorhmzazt2wfn2dz2m5wfx3auisu2gvfo2jsepr4zyekmq.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1, 2048], [2048, 1], [], []], "Input Dims": [[1, 2048, 2], [1, 2048], [], []], "Ev Idx": 5518 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275724859.286, "dur": 30.384, + "args": { + "External id": 4058512,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 5519 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275724892.745, "dur": 34.446, + "args": { + "External id": 4058513,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 5520 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 1336756, "tid": 1381189, + "ts": 1655275724954.343, "dur": 205.678, + "args": { + "External id": 4058514,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.125", "True", "-1", "-1", "0.", "", "False", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar", "long int"], "Input Strides": [[8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [131072, 4096, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 32, 4096], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 5521 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655275725066.971, "dur": 7.003, + "args": { + "External id": 4058515,"Record function id": 0, "Concrete Inputs": ["[16, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5522 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655275725076.089, "dur": 2.040, + "args": { + "External id": 4058516,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5523 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336756, "tid": 1381189, + "ts": 1655275725190.177, "dur": 25.867, + "args": { + "External id": 4058517,"kernel_hash": "cb6oumcqb462ndf2ivcd2sc6qg6mfjahptjw4ih7cesqhfpziv3b", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/b6/cb6oumcqb462ndf2ivcd2sc6qg6mfjahptjw4ih7cesqhfpziv3b.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 5524 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336756, "tid": 1381189, + "ts": 1655275725226.778, "dur": 13.253, + "args": { + "External id": 4058518,"kernel_hash": "cb6oumcqb462ndf2ivcd2sc6qg6mfjahptjw4ih7cesqhfpziv3b", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/b6/cb6oumcqb462ndf2ivcd2sc6qg6mfjahptjw4ih7cesqhfpziv3b.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 5525 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275725249.041, "dur": 40.748, + "args": { + "External id": 4058519,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 5526 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275725296.161, "dur": 36.447, + "args": { + "External id": 4058520,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 5527 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275725340.562, "dur": 20.614, + "args": { + "External id": 4058521,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 5528 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275725366.154, "dur": 30.380, + "args": { + "External id": 4058522,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 5529 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275725402.253, "dur": 37.178, + "args": { + "External id": 4058523,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 5530 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275725449.754, "dur": 34.974, + "args": { + "External id": 4058524,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 5531 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_4", "pid": 1336756, "tid": 1381189, + "ts": 1655275725502.055, "dur": 21.972, + "args": { + "External id": 4058525,"kernel_hash": "c7pqhdjojzeazwsh5g3ibnyk4m2nfh3q73e3zc7hljz4yvhe7c4h", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/7p/c7pqhdjojzeazwsh5g3ibnyk4m2nfh3q73e3zc7hljz4yvhe7c4h.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1], []], "Input Dims": [[65536, 2048], [65536, 2048], [65536, 2048], []], "Ev Idx": 5532 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_2", "pid": 1336756, "tid": 1381189, + "ts": 1655275725545.895, "dur": 23.286, + "args": { + "External id": 4058526,"kernel_hash": "cvgvwkysjpcw75q5t3guce5bep2so25f7i5zxc6ipt5f56shof73", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "65536", "2048", "1", "497", "132", "True", "2048", "False", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/vg/cvgvwkysjpcw75q5t3guce5bep2so25f7i5zxc6ipt5f56shof73.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [1], [2048, 1], [2048, 1], [2048, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [2048], [65536, 2048], [65536, 2048], [132, 2048], [65536], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 5533 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 1336756, "tid": 1381189, + "ts": 1655275725582.343, "dur": 26.960, + "args": { + "External id": 4058527,"kernel_hash": "cu42i6zmxtvs2i7cs6x4ixaexke3lhgdiaye5oxwm7s3u6em6co4", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "66"], "kernel_file": "/tmp/torchinductor_cvm/u4/cu42i6zmxtvs2i7cs6x4ixaexke3lhgdiaye5oxwm7s3u6em6co4.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [4096, 1, 2048], [], []], "Input Dims": [[132, 2048], [1, 2048, 2], [], []], "Ev Idx": 5534 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 1336756, "tid": 1381189, + "ts": 1655275725632.248, "dur": 17.613, + "args": { + "External id": 4058528,"kernel_hash": "ckihofrorhmzazt2wfn2dz2m5wfx3auisu2gvfo2jsepr4zyekmq", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "2"], "kernel_file": "/tmp/torchinductor_cvm/ki/ckihofrorhmzazt2wfn2dz2m5wfx3auisu2gvfo2jsepr4zyekmq.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1, 2048], [2048, 1], [], []], "Input Dims": [[1, 2048, 2], [1, 2048], [], []], "Ev Idx": 5535 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_5", "pid": 1336756, "tid": 1381189, + "ts": 1655275725662.922, "dur": 15.594, + "args": { + "External id": 4058529,"kernel_hash": "cckrpn5uuxyvbancoio3sz2onrjto236n54xx4ycphq5p6r3jlfj", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/ck/cckrpn5uuxyvbancoio3sz2onrjto236n54xx4ycphq5p6r3jlfj.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [8388608, 2048, 1], []], "Input Dims": [[65536, 2048], [65536, 2048], [16, 4096, 2048], []], "Ev Idx": 5536 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275725751.759, "dur": 14.794, + "args": { + "External id": 4058530,"Record function id": 0, "Ev Idx": 5537 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275725754.909, "dur": 10.635, + "args": { + "External id": 4058531,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 5538 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275725758.900, "dur": 5.741, + "args": { + "External id": 4058532,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 5539 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275725760.694, "dur": 3.809, + "args": { + "External id": 4058533,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 5540 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275725773.432, "dur": 4.757, + "args": { + "External id": 4058534,"Record function id": 0, "Ev Idx": 5541 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275725774.922, "dur": 2.838, + "args": { + "External id": 4058535,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 5542 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275725775.631, "dur": 1.689, + "args": { + "External id": 4058536,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 5543 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275725776.367, "dur": 0.858, + "args": { + "External id": 4058537,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 5544 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275725781.488, "dur": 4.998, + "args": { + "External id": 4058538,"Record function id": 0, "Ev Idx": 5545 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275725782.687, "dur": 3.364, + "args": { + "External id": 4058539,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 5546 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275725783.627, "dur": 1.900, + "args": { + "External id": 4058540,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 5547 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275725784.233, "dur": 1.185, + "args": { + "External id": 4058541,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 5548 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275725789.546, "dur": 4.052, + "args": { + "External id": 4058542,"Record function id": 0, "Ev Idx": 5549 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275725790.903, "dur": 2.290, + "args": { + "External id": 4058543,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 5550 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275725791.513, "dur": 1.206, + "args": { + "External id": 4058544,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 5551 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275725791.949, "dur": 0.697, + "args": { + "External id": 4058545,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 5552 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275725796.667, "dur": 4.248, + "args": { + "External id": 4058546,"Record function id": 0, "Ev Idx": 5553 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275725797.775, "dur": 2.754, + "args": { + "External id": 4058547,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 5554 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275725798.513, "dur": 1.453, + "args": { + "External id": 4058548,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 5555 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275725799.246, "dur": 0.656, + "args": { + "External id": 4058549,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 5556 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275725803.988, "dur": 3.480, + "args": { + "External id": 4058550,"Record function id": 0, "Ev Idx": 5557 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275725805.035, "dur": 1.978, + "args": { + "External id": 4058551,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 5558 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275725805.524, "dur": 1.068, + "args": { + "External id": 4058552,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 5559 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275725805.996, "dur": 0.471, + "args": { + "External id": 4058553,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 5560 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275725810.691, "dur": 4.947, + "args": { + "External id": 4058554,"Record function id": 0, "Ev Idx": 5561 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275725812.055, "dur": 3.155, + "args": { + "External id": 4058555,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 5562 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275725812.702, "dur": 2.097, + "args": { + "External id": 4058556,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 5563 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275725813.095, "dur": 1.595, + "args": { + "External id": 4058557,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 5564 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275725818.671, "dur": 3.538, + "args": { + "External id": 4058558,"Record function id": 0, "Ev Idx": 5565 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275725819.816, "dur": 1.959, + "args": { + "External id": 4058559,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 5566 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275725820.287, "dur": 1.064, + "args": { + "External id": 4058560,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 5567 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275725820.547, "dur": 0.689, + "args": { + "External id": 4058561,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 5568 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275725825.201, "dur": 3.870, + "args": { + "External id": 4058562,"Record function id": 0, "Ev Idx": 5569 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275725826.434, "dur": 2.203, + "args": { + "External id": 4058563,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 5570 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275725827.058, "dur": 1.144, + "args": { + "External id": 4058564,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 5571 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275725827.611, "dur": 0.472, + "args": { + "External id": 4058565,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 5572 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RegisterPostBackwardFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1655275725832.573, "dur": 37275.160, + "args": { + "External id": 4058566,"Record function id": 0, "Sequence number": 40618355, "Fwd thread id": 1, "Ev Idx": 5573 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1655275725834.047, "dur": 37264.797, + "args": { + "External id": 4058567,"Sequence number": 40618355, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 5574 + } + }, + { + "ph": "f", "id": 225, "pid": 1336756, "tid": 1381189, "ts": 1655275725834.047, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.1)", "pid": 1336756, "tid": 1381189, + "ts": 1655275725860.005, "dur": 37.659, + "args": { + "External id": 4058568,"Record function id": 0, "Ev Idx": 5575 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.1)", "pid": 1336756, "tid": 1381189, + "ts": 1655275725905.924, "dur": 66.108, + "args": { + "External id": 4058569,"Record function id": 0, "Ev Idx": 5576 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.1)", "pid": 1336756, "tid": 1381189, + "ts": 1655275725978.396, "dur": 37112.073, + "args": { + "External id": 4058570,"Record function id": 0, "Ev Idx": 5577 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655275726121.084, "dur": 7.096, + "args": { + "External id": 4058571,"Record function id": 0, "Concrete Inputs": ["[51384320]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5578 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275726138.994, "dur": 5.276, + "args": { + "External id": 4058572,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[51384320], []], "Ev Idx": 5579 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::chunk_cat", "pid": 1336756, "tid": 1381189, + "ts": 1655275726158.798, "dur": 36131.178, + "args": { + "External id": 4058573,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [2048, 1], [2048, 1], [2048, 1], [2048, 1], [1], [2048, 1], [2048, 1], [5632, 1]], [], [], [6423040, 1]], "Input Dims": [[[2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048], [5632, 2048], [5632, 2048], [2048, 5632]], [], [], [8, 6423040]], "Ev Idx": 5580 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_chunk_cat", "pid": 1336756, "tid": 1381189, + "ts": 1655275726172.675, "dur": 36109.068, + "args": { + "External id": 4058574,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [2048, 1], [2048, 1], [2048, 1], [2048, 1], [1], [2048, 1], [2048, 1], [5632, 1]], [], [], [6423040, 1]], "Input Dims": [[[2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048], [5632, 2048], [5632, 2048], [2048, 5632]], [], [], [8, 6423040]], "Ev Idx": 5581 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655275726219.239, "dur": 13.917, + "args": { + "External id": 4058575,"Record function id": 0, "Concrete Inputs": ["[12602]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5582 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1381189, + "ts": 1655275726239.281, "dur": 36004.480, + "args": { + "External id": 4058576,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[12602], [], [], [], [], [], [], []], "Ev Idx": 5583 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336756, "tid": 1381189, + "ts": 1655275726241.923, "dur": 36001.263, + "args": { + "External id": 4058577,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[12602], [], [], [], [], [], []], "Ev Idx": 5584 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275726245.828, "dur": 5.258, + "args": { + "External id": 4058578,"Record function id": 0, "Concrete Inputs": ["[12602]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5585 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1381189, + "ts": 1655275726252.781, "dur": 35986.665, + "args": { + "External id": 4058579,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[12602], [12602], []], "Ev Idx": 5586 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 1336756, "tid": 1381189, + "ts": 1655275762378.096, "dur": 8.871, + "args": { + "External id": 4058580,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "", "", "", "False"], "Input type": ["float", "ScalarList", "", "", "", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[51384320], [], [], [], [], []], "Ev Idx": 5587 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655275762380.994, "dur": 5.623, + "args": { + "External id": 4058581,"Record function id": 0, "Concrete Inputs": ["[6423040]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5588 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_reduce_scatter_base_", "pid": 1336756, "tid": 1381189, + "ts": 1655275762429.986, "dur": 343.619, + "args": { + "External id": 4058582,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "-1"], "Input type": ["float", "float", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], [], []], "Input Dims": [[6423040], [51384320], [], [], [], []], "Ev Idx": 5589 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336756, "tid": 1381189, + "ts": 1655275762457.122, "dur": 311.656, + "args": { + "External id": 4058583,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 3, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "3", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 6423040, "Process Group Name": "0", "Input type": ["float", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[51384320], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 5590, "In msg nelems": 51384320 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_reduce_scatter_base", "pid": 1336756, "tid": 1381189, + "ts": 1655275762468.619, "dur": 295.175, + "args": { + "External id": 4058584,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[51384320]], "Ev Idx": 5591 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336756, "tid": 1381189, + "ts": 1655275762792.384, "dur": 1.994, + "args": { + "External id": 4058585,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "3", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 5592, "In msg nelems": 0, "Rank": 3, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275762853.729, "dur": 6.778, + "args": { + "External id": 4058586,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5593 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275762904.382, "dur": 2.592, + "args": { + "External id": 4058587,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "256"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5594 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275762922.707, "dur": 0.839, + "args": { + "External id": 4058588,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "524544"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5595 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275762934.942, "dur": 0.793, + "args": { + "External id": 4058589,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "1048832"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5596 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275762946.829, "dur": 0.910, + "args": { + "External id": 4058590,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "1573120"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5597 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275762957.308, "dur": 1.785, + "args": { + "External id": 4058591,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5598 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275762968.129, "dur": 1.049, + "args": { + "External id": 4058592,"Record function id": 0, "Concrete Inputs": ["", "[704, 2048]", "[2048, 1]", "2097664"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5599 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275762979.055, "dur": 1.470, + "args": { + "External id": 4058593,"Record function id": 0, "Concrete Inputs": ["", "[704, 2048]", "[2048, 1]", "3539456"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5600 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275763031.000, "dur": 1.494, + "args": { + "External id": 4058594,"Record function id": 0, "Concrete Inputs": ["", "[256, 5632]", "[5632, 1]", "4981248"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5601 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: CompiledFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1655275763122.748, "dur": 2054.640, + "args": { + "External id": 4058595,"Record function id": 0, "Ev Idx": 5602 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.0)", "pid": 1336756, "tid": 1381189, + "ts": 1655275763142.992, "dur": 430.497, + "args": { + "External id": 4058596,"Record function id": 0, "Ev Idx": 5603 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.0)", "pid": 1336756, "tid": 1381189, + "ts": 1655275763157.310, "dur": 326.258, + "args": { + "External id": 4058597,"Record function id": 0, "Ev Idx": 5604 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275763235.942, "dur": 3.775, + "args": { + "External id": 4058598,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[51384320], []], "Ev Idx": 5605 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275763242.810, "dur": 0.693, + "args": { + "External id": 4058599,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 5606 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275763245.281, "dur": 1.702, + "args": { + "External id": 4058600,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 5607 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275763248.750, "dur": 0.636, + "args": { + "External id": 4058601,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 5608 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275763250.689, "dur": 0.881, + "args": { + "External id": 4058602,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 5609 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275763253.667, "dur": 1.047, + "args": { + "External id": 4058603,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 5610 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275763256.203, "dur": 0.693, + "args": { + "External id": 4058604,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 5611 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275763259.856, "dur": 0.702, + "args": { + "External id": 4058605,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 5612 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275763261.722, "dur": 0.789, + "args": { + "External id": 4058606,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 5613 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275763263.698, "dur": 0.769, + "args": { + "External id": 4058607,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 5614 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 1336756, "tid": 1381189, + "ts": 1655275763282.065, "dur": 170.501, + "args": { + "External id": 4058608,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 5615 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 1336756, "tid": 1381189, + "ts": 1655275763299.811, "dur": 147.826, + "args": { + "External id": 4058609,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 5616 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655275763314.418, "dur": 13.932, + "args": { + "External id": 4058610,"Record function id": 0, "Concrete Inputs": ["[2133]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5617 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1381189, + "ts": 1655275763331.396, "dur": 69.844, + "args": { + "External id": 4058611,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], [], []], "Ev Idx": 5618 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336756, "tid": 1381189, + "ts": 1655275763334.139, "dur": 66.805, + "args": { + "External id": 4058612,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], []], "Ev Idx": 5619 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275763338.183, "dur": 6.455, + "args": { + "External id": 4058613,"Record function id": 0, "Concrete Inputs": ["[2133]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5620 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1381189, + "ts": 1655275763347.401, "dur": 52.724, + "args": { + "External id": 4058614,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[2133], [2133], []], "Ev Idx": 5621 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1655275763581.230, "dur": 1576.233, + "args": { + "External id": 4058615,"Sequence number": 40618354, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 5622 + } + }, + { + "ph": "f", "id": 226, "pid": 1336756, "tid": 1381189, "ts": 1655275763581.230, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275763686.953, "dur": 102.857, + "args": { + "External id": 4058616,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [5632, 1], [5632, 1]], "Input Dims": [[65536, 2048], [2048, 5632], [65536, 5632]], "Ev Idx": 5623 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_add_mul_rsub_silu_0", "pid": 1336756, "tid": 1381189, + "ts": 1655275763826.403, "dur": 37.408, + "args": { + "External id": 4058617,"kernel_hash": "c2zszzsomz26dv2qwvmiurvgyrl5qxtyn6ocoqkdpzzhfzwqp5q6", "grid": "grid(369098752,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "369098752"], "kernel_file": "/tmp/torchinductor_cvm/2z/c2zszzsomz26dv2qwvmiurvgyrl5qxtyn6ocoqkdpzzhfzwqp5q6.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[5632, 1], [5632, 1], [5632, 1], [23068672, 5632, 1], [23068672, 5632, 1], [23068672, 5632, 1], []], "Input Dims": [[65536, 5632], [65536, 5632], [65536, 5632], [16, 4096, 5632], [16, 4096, 5632], [16, 4096, 5632], []], "Ev Idx": 5624 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::bmm", "pid": 1336756, "tid": 1381189, + "ts": 1655275763879.453, "dur": 47.618, + "args": { + "External id": 4058618,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[0, 1, 2048], [0, 5632, 1], [11534336, 5632, 1]], "Input Dims": [[1, 2048, 65536], [1, 65536, 5632], [1, 2048, 5632]], "Ev Idx": 5625 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275763937.845, "dur": 32.799, + "args": { + "External id": 4058619,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 5632], [2048, 1], [2048, 1]], "Input Dims": [[5632, 65536], [65536, 2048], [5632, 2048]], "Ev Idx": 5626 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275763977.592, "dur": 94.171, + "args": { + "External id": 4058620,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 5632], [5632, 2048], [65536, 2048]], "Ev Idx": 5627 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275764083.761, "dur": 30.333, + "args": { + "External id": 4058621,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 5632], [2048, 1], [2048, 1]], "Input Dims": [[5632, 65536], [65536, 2048], [5632, 2048]], "Ev Idx": 5628 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275764121.485, "dur": 43.954, + "args": { + "External id": 4058622,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 5632], [5632, 2048], [65536, 2048]], "Ev Idx": 5629 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_1", "pid": 1336756, "tid": 1381189, + "ts": 1655275764189.740, "dur": 22.603, + "args": { + "External id": 4058623,"kernel_hash": "cjd6g3jfgntyoifzno6l2urmnhif7alxtw6zz7miov66vywxwv7d", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/jd/cjd6g3jfgntyoifzno6l2urmnhif7alxtw6zz7miov66vywxwv7d.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[65536, 2048], [65536, 2048], []], "Ev Idx": 5630 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 1336756, "tid": 1381189, + "ts": 1655275764229.514, "dur": 27.738, + "args": { + "External id": 4058624,"kernel_hash": "cxhg545cyph4gbk5vymzyh72vho7oogk3ycan2lp4cxntklp5hew", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "65536", "2048", "1", "497", "132", "True", "2048", "True", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/xh/cxhg545cyph4gbk5vymzyh72vho7oogk3ycan2lp4cxntklp5hew.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [1], [2048, 1], [2048, 1], [2048, 1], [2048, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [2048], [65536, 2048], [65536, 2048], [132, 2048], [65536, 2048], [65536], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 5631 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 1336756, "tid": 1381189, + "ts": 1655275764296.834, "dur": 20.315, + "args": { + "External id": 4058625,"kernel_hash": "cu42i6zmxtvs2i7cs6x4ixaexke3lhgdiaye5oxwm7s3u6em6co4", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "66"], "kernel_file": "/tmp/torchinductor_cvm/u4/cu42i6zmxtvs2i7cs6x4ixaexke3lhgdiaye5oxwm7s3u6em6co4.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [4096, 1, 2048], [], []], "Input Dims": [[132, 2048], [1, 2048, 2], [], []], "Ev Idx": 5632 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 1336756, "tid": 1381189, + "ts": 1655275764330.243, "dur": 15.619, + "args": { + "External id": 4058626,"kernel_hash": "ckihofrorhmzazt2wfn2dz2m5wfx3auisu2gvfo2jsepr4zyekmq", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "2"], "kernel_file": "/tmp/torchinductor_cvm/ki/ckihofrorhmzazt2wfn2dz2m5wfx3auisu2gvfo2jsepr4zyekmq.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1, 2048], [2048, 1], [], []], "Input Dims": [[1, 2048, 2], [1, 2048], [], []], "Ev Idx": 5633 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275764353.886, "dur": 28.917, + "args": { + "External id": 4058627,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 5634 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275764386.160, "dur": 49.457, + "args": { + "External id": 4058628,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 5635 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_backward", "pid": 1336756, "tid": 1381189, + "ts": 1655275764467.454, "dur": 164.464, + "args": { + "External id": 4058629,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "0.", "0.125", "True", "-1", "-1", "0.", "", "False", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar", "long int"], "Input Strides": [[8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [131072, 4096, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [1]], "Input Dims": [[16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 32, 4096], [16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [2]], "Ev Idx": 5636 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655275764542.568, "dur": 5.425, + "args": { + "External id": 4058630,"Record function id": 0, "Concrete Inputs": ["[16, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5637 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655275764549.881, "dur": 1.688, + "args": { + "External id": 4058631,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5638 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336756, "tid": 1381189, + "ts": 1655275764663.615, "dur": 25.658, + "args": { + "External id": 4058632,"kernel_hash": "cb6oumcqb462ndf2ivcd2sc6qg6mfjahptjw4ih7cesqhfpziv3b", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/b6/cb6oumcqb462ndf2ivcd2sc6qg6mfjahptjw4ih7cesqhfpziv3b.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 5639 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336756, "tid": 1381189, + "ts": 1655275764700.308, "dur": 13.647, + "args": { + "External id": 4058633,"kernel_hash": "cb6oumcqb462ndf2ivcd2sc6qg6mfjahptjw4ih7cesqhfpziv3b", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "True"], "kernel_file": "/tmp/torchinductor_cvm/b6/cb6oumcqb462ndf2ivcd2sc6qg6mfjahptjw4ih7cesqhfpziv3b.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 5640 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275764721.143, "dur": 36.389, + "args": { + "External id": 4058634,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 5641 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275764763.897, "dur": 35.183, + "args": { + "External id": 4058635,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 5642 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275764806.450, "dur": 20.774, + "args": { + "External id": 4058636,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 5643 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275764832.465, "dur": 30.300, + "args": { + "External id": 4058637,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 5644 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275764868.159, "dur": 19.646, + "args": { + "External id": 4058638,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 2048], [2048, 1], [2048, 1]], "Input Dims": [[2048, 65536], [65536, 2048], [2048, 2048]], "Ev Idx": 5645 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1655275764894.777, "dur": 31.221, + "args": { + "External id": 4058639,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 5646 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_4", "pid": 1336756, "tid": 1381189, + "ts": 1655275764941.554, "dur": 20.884, + "args": { + "External id": 4058640,"kernel_hash": "c7pqhdjojzeazwsh5g3ibnyk4m2nfh3q73e3zc7hljz4yvhe7c4h", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/7p/c7pqhdjojzeazwsh5g3ibnyk4m2nfh3q73e3zc7hljz4yvhe7c4h.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [2048, 1], []], "Input Dims": [[65536, 2048], [65536, 2048], [65536, 2048], []], "Ev Idx": 5647 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_2", "pid": 1336756, "tid": 1381189, + "ts": 1655275764977.702, "dur": 62.854, + "args": { + "External id": 4058641,"kernel_hash": "cvgvwkysjpcw75q5t3guce5bep2so25f7i5zxc6ipt5f56shof73", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "65536", "2048", "1", "497", "132", "True", "2048", "False", "False", "True", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/vg/cvgvwkysjpcw75q5t3guce5bep2so25f7i5zxc6ipt5f56shof73.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [1], [2048, 1], [2048, 1], [2048, 1], [1], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [2048], [65536, 2048], [65536, 2048], [132, 2048], [65536], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 5648 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_red_fused_sum_2", "pid": 1336756, "tid": 1381189, + "ts": 1655275765056.964, "dur": 16.634, + "args": { + "External id": 4058642,"kernel_hash": "cu42i6zmxtvs2i7cs6x4ixaexke3lhgdiaye5oxwm7s3u6em6co4", "grid": "grid(4096,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "4096", "66"], "kernel_file": "/tmp/torchinductor_cvm/u4/cu42i6zmxtvs2i7cs6x4ixaexke3lhgdiaye5oxwm7s3u6em6co4.py", "kernel_backend": "triton", "Input type": ["float", "float", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [4096, 1, 2048], [], []], "Input Dims": [[132, 2048], [1, 2048, 2], [], []], "Ev Idx": 5649 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_per_fused__to_copy_sum_3", "pid": 1336756, "tid": 1381189, + "ts": 1655275765089.246, "dur": 14.362, + "args": { + "External id": 4058643,"kernel_hash": "ckihofrorhmzazt2wfn2dz2m5wfx3auisu2gvfo2jsepr4zyekmq", "grid": "grid(2048,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "2048", "2"], "kernel_file": "/tmp/torchinductor_cvm/ki/ckihofrorhmzazt2wfn2dz2m5wfx3auisu2gvfo2jsepr4zyekmq.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[4096, 1, 2048], [2048, 1], [], []], "Input Dims": [[1, 2048, 2], [1, 2048], [], []], "Ev Idx": 5650 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_5", "pid": 1336756, "tid": 1381189, + "ts": 1655275765115.447, "dur": 14.742, + "args": { + "External id": 4058644,"kernel_hash": "cckrpn5uuxyvbancoio3sz2onrjto236n54xx4ycphq5p6r3jlfj", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/ck/cckrpn5uuxyvbancoio3sz2onrjto236n54xx4ycphq5p6r3jlfj.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [8388608, 2048, 1], []], "Input Dims": [[65536, 2048], [65536, 2048], [16, 4096, 2048], []], "Ev Idx": 5651 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275765200.018, "dur": 15.072, + "args": { + "External id": 4058645,"Record function id": 0, "Ev Idx": 5652 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275765203.347, "dur": 10.866, + "args": { + "External id": 4058646,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 5653 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275765207.620, "dur": 5.709, + "args": { + "External id": 4058647,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 5654 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275765209.295, "dur": 3.887, + "args": { + "External id": 4058648,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 5655 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275765218.646, "dur": 5.560, + "args": { + "External id": 4058649,"Record function id": 0, "Ev Idx": 5656 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275765220.350, "dur": 3.397, + "args": { + "External id": 4058650,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 5657 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275765221.218, "dur": 2.054, + "args": { + "External id": 4058651,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 5658 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275765222.323, "dur": 0.849, + "args": { + "External id": 4058652,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 5659 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275765227.400, "dur": 4.267, + "args": { + "External id": 4058653,"Record function id": 0, "Ev Idx": 5660 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275765228.818, "dur": 2.460, + "args": { + "External id": 4058654,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 5661 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275765229.297, "dur": 1.552, + "args": { + "External id": 4058655,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 5662 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275765229.776, "dur": 0.913, + "args": { + "External id": 4058656,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[2048]], "Ev Idx": 5663 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275765234.755, "dur": 4.100, + "args": { + "External id": 4058657,"Record function id": 0, "Ev Idx": 5664 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275765236.199, "dur": 2.254, + "args": { + "External id": 4058658,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 5665 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275765236.810, "dur": 1.251, + "args": { + "External id": 4058659,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 5666 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275765237.327, "dur": 0.662, + "args": { + "External id": 4058660,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 5667 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275765241.879, "dur": 3.786, + "args": { + "External id": 4058661,"Record function id": 0, "Ev Idx": 5668 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275765243.237, "dur": 2.039, + "args": { + "External id": 4058662,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 5669 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275765243.693, "dur": 1.114, + "args": { + "External id": 4058663,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 5670 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275765244.003, "dur": 0.730, + "args": { + "External id": 4058664,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 5671 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275765248.763, "dur": 4.448, + "args": { + "External id": 4058665,"Record function id": 0, "Ev Idx": 5672 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275765250.171, "dur": 2.558, + "args": { + "External id": 4058666,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 5673 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275765250.661, "dur": 1.640, + "args": { + "External id": 4058667,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 5674 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275765251.665, "dur": 0.541, + "args": { + "External id": 4058668,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 5675 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275765256.350, "dur": 4.981, + "args": { + "External id": 4058669,"Record function id": 0, "Ev Idx": 5676 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275765257.527, "dur": 3.397, + "args": { + "External id": 4058670,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 5677 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275765258.064, "dur": 2.456, + "args": { + "External id": 4058671,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 5678 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275765258.489, "dur": 1.922, + "args": { + "External id": 4058672,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 5679 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275765264.319, "dur": 3.816, + "args": { + "External id": 4058673,"Record function id": 0, "Ev Idx": 5680 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275765265.723, "dur": 1.982, + "args": { + "External id": 4058674,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 5681 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275765266.438, "dur": 0.866, + "args": { + "External id": 4058675,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 5682 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275765266.717, "dur": 0.490, + "args": { + "External id": 4058676,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 5683 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275765271.076, "dur": 3.820, + "args": { + "External id": 4058677,"Record function id": 0, "Ev Idx": 5684 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275765272.102, "dur": 2.387, + "args": { + "External id": 4058678,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 5685 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275765272.830, "dur": 1.257, + "args": { + "External id": 4058679,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 5686 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275765273.317, "dur": 0.670, + "args": { + "External id": 4058680,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 5687 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: RegisterPostBackwardFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1655275765278.301, "dur": 37307.470, + "args": { + "External id": 4058681,"Record function id": 0, "Sequence number": 40618353, "Fwd thread id": 1, "Ev Idx": 5688 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1655275765279.647, "dur": 37297.354, + "args": { + "External id": 4058682,"Sequence number": 40618353, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 5689 + } + }, + { + "ph": "f", "id": 227, "pid": 1336756, "tid": 1381189, "ts": 1655275765279.647, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.0)", "pid": 1336756, "tid": 1381189, + "ts": 1655275765306.424, "dur": 36.109, + "args": { + "External id": 4058683,"Record function id": 0, "Ev Idx": 5690 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard (model.layers.0)", "pid": 1336756, "tid": 1381189, + "ts": 1655275765349.345, "dur": 82.847, + "args": { + "External id": 4058684,"Record function id": 0, "Ev Idx": 5691 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce (model.layers.0)", "pid": 1336756, "tid": 1381189, + "ts": 1655275765440.839, "dur": 37127.850, + "args": { + "External id": 4058685,"Record function id": 0, "Ev Idx": 5692 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655275765528.581, "dur": 6.373, + "args": { + "External id": 4058686,"Record function id": 0, "Concrete Inputs": ["[51384320]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5693 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275765545.438, "dur": 4.944, + "args": { + "External id": 4058687,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[51384320], []], "Ev Idx": 5694 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::chunk_cat", "pid": 1336756, "tid": 1381189, + "ts": 1655275765564.006, "dur": 36281.955, + "args": { + "External id": 4058688,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [2048, 1], [2048, 1], [2048, 1], [2048, 1], [1], [2048, 1], [2048, 1], [5632, 1]], [], [], [6423040, 1]], "Input Dims": [[[2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048], [5632, 2048], [5632, 2048], [2048, 5632]], [], [], [8, 6423040]], "Ev Idx": 5695 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_chunk_cat", "pid": 1336756, "tid": 1381189, + "ts": 1655275765590.386, "dur": 36247.901, + "args": { + "External id": 4058689,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[[1], [2048, 1], [2048, 1], [2048, 1], [2048, 1], [1], [2048, 1], [2048, 1], [5632, 1]], [], [], [6423040, 1]], "Input Dims": [[[2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048, 2048], [2048], [5632, 2048], [5632, 2048], [2048, 5632]], [], [], [8, 6423040]], "Ev Idx": 5696 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655275765642.882, "dur": 13.348, + "args": { + "External id": 4058690,"Record function id": 0, "Concrete Inputs": ["[12602]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5697 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1381189, + "ts": 1655275765663.165, "dur": 36141.658, + "args": { + "External id": 4058691,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[12602], [], [], [], [], [], [], []], "Ev Idx": 5698 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336756, "tid": 1381189, + "ts": 1655275765665.623, "dur": 36138.623, + "args": { + "External id": 4058692,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[12602], [], [], [], [], [], []], "Ev Idx": 5699 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275765670.030, "dur": 5.498, + "args": { + "External id": 4058693,"Record function id": 0, "Concrete Inputs": ["[12602]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5700 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1381189, + "ts": 1655275765677.313, "dur": 36124.048, + "args": { + "External id": 4058694,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[12602], [12602], []], "Ev Idx": 5701 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 1336756, "tid": 1381189, + "ts": 1655275801928.215, "dur": 8.010, + "args": { + "External id": 4058695,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "", "", "", "False"], "Input type": ["float", "ScalarList", "", "", "", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[51384320], [], [], [], [], []], "Ev Idx": 5702 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655275801930.775, "dur": 5.107, + "args": { + "External id": 4058696,"Record function id": 0, "Concrete Inputs": ["[6423040]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5703 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_reduce_scatter_base_", "pid": 1336756, "tid": 1381189, + "ts": 1655275801965.298, "dur": 307.740, + "args": { + "External id": 4058697,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "-1"], "Input type": ["float", "float", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], [], []], "Input Dims": [[6423040], [51384320], [], [], [], []], "Ev Idx": 5704 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336756, "tid": 1381189, + "ts": 1655275802018.717, "dur": 249.665, + "args": { + "External id": 4058698,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 3, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "3", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 6423040, "Process Group Name": "0", "Input type": ["float", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[51384320], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 5705, "In msg nelems": 51384320 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_reduce_scatter_base", "pid": 1336756, "tid": 1381189, + "ts": 1655275802031.070, "dur": 232.469, + "args": { + "External id": 4058699,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[51384320]], "Ev Idx": 5706 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336756, "tid": 1381189, + "ts": 1655275802291.210, "dur": 2.193, + "args": { + "External id": 4058700,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "3", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 5707, "In msg nelems": 0, "Rank": 3, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275802349.468, "dur": 6.364, + "args": { + "External id": 4058701,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5708 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275802399.895, "dur": 1.218, + "args": { + "External id": 4058702,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "256"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5709 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275802431.316, "dur": 2.725, + "args": { + "External id": 4058703,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "524544"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5710 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275802449.798, "dur": 0.814, + "args": { + "External id": 4058704,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "1048832"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5711 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275802462.429, "dur": 0.768, + "args": { + "External id": 4058705,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "1573120"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5712 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275802472.600, "dur": 1.328, + "args": { + "External id": 4058706,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5713 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275802483.514, "dur": 1.977, + "args": { + "External id": 4058707,"Record function id": 0, "Concrete Inputs": ["", "[704, 2048]", "[2048, 1]", "2097664"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5714 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275802496.407, "dur": 0.769, + "args": { + "External id": 4058708,"Record function id": 0, "Concrete Inputs": ["", "[704, 2048]", "[2048, 1]", "3539456"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5715 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275802506.430, "dur": 1.063, + "args": { + "External id": 4058709,"Record function id": 0, "Concrete Inputs": ["", "[256, 5632]", "[5632, 1]", "4981248"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5716 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: CompiledFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1655275802600.963, "dur": 247.101, + "args": { + "External id": 4058710,"Record function id": 0, "Sequence number": 40618352, "Fwd thread id": 1, "Ev Idx": 5717 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1655275802603.680, "dur": 236.725, + "args": { + "External id": 4058711,"Sequence number": 40618352, "Fwd thread id": 1, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 5718 + } + }, + { + "ph": "f", "id": 228, "pid": 1336756, "tid": 1381189, "ts": 1655275802603.680, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_embedding_dense_backward_0", "pid": 1336756, "tid": 1381189, + "ts": 1655275802712.474, "dur": 42.375, + "args": { + "External id": 4058712,"kernel_hash": "cqirzqrltfdqnxhjos6hp6gemkm4gwku4foo6uqui7opbq4ng4m5", "grid": "grid(65536000,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "65536000"], "kernel_file": "/tmp/torchinductor_cvm/qi/cqirzqrltfdqnxhjos6hp6gemkm4gwku4foo6uqui7opbq4ng4m5.py", "kernel_backend": "triton", "Input type": ["float", "Scalar"], "Input Strides": [[2048, 1], []], "Input Dims": [[32000, 2048], []], "Ev Idx": 5719 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_embedding_dense_backward_1", "pid": 1336756, "tid": 1381189, + "ts": 1655275802767.418, "dur": 25.720, + "args": { + "External id": 4058713,"kernel_hash": "cjxnzfkkndlwdapjvgkkjvqxc72zinfqxyyoxiyd5swlefndj6n5", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/jx/cjxnzfkkndlwdapjvgkkjvqxc72zinfqxyyoxiyd5swlefndj6n5.py", "kernel_backend": "triton", "Input type": ["long int", "c10::BFloat16", "float", "Scalar"], "Input Strides": [[4096, 1], [8388608, 2048, 1], [2048, 1], []], "Input Dims": [[16, 4096], [16, 4096, 2048], [32000, 2048], []], "Ev Idx": 5720 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_embedding_dense_backward_2", "pid": 1336756, "tid": 1381189, + "ts": 1655275802807.966, "dur": 18.827, + "args": { + "External id": 4058714,"kernel_hash": "cycx64w3vzu6rbiohboydiqd4wfbj7vazwzbvujyhnlqv6l7yuhz", "grid": "grid(65536000,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "65536000"], "kernel_file": "/tmp/torchinductor_cvm/yc/cycx64w3vzu6rbiohboydiqd4wfbj7vazwzbvujyhnlqv6l7yuhz.py", "kernel_backend": "triton", "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[32000, 2048], [32000, 2048], []], "Ev Idx": 5721 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275802857.832, "dur": 13.916, + "args": { + "External id": 4058715,"Record function id": 0, "Ev Idx": 5722 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1655275802860.471, "dur": 10.468, + "args": { + "External id": 4058716,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[32000, 2048]], "Ev Idx": 5723 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275802864.616, "dur": 5.499, + "args": { + "External id": 4058717,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[32000, 2048]], "Ev Idx": 5724 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1381189, + "ts": 1655275802865.993, "dur": 3.997, + "args": { + "External id": 4058718,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[32000, 2048]], "Ev Idx": 5725 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::root_post_backward_callback", "pid": 1336756, "tid": 1381189, + "ts": 1655275802891.511, "dur": 14001.793, + "args": { + "External id": 4058719,"Record function id": 0, "Ev Idx": 5726 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate", "pid": 1336756, "tid": 1381189, + "ts": 1655275802910.353, "dur": 30.100, + "args": { + "External id": 4058720,"Record function id": 0, "Ev Idx": 5727 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard", "pid": 1336756, "tid": 1381189, + "ts": 1655275802946.369, "dur": 240.522, + "args": { + "External id": 4058721,"Record function id": 0, "Ev Idx": 5728 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce", "pid": 1336756, "tid": 1381189, + "ts": 1655275803195.747, "dur": 13438.337, + "args": { + "External id": 4058722,"Record function id": 0, "Ev Idx": 5729 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655275803311.199, "dur": 7.227, + "args": { + "External id": 4058723,"Record function id": 0, "Concrete Inputs": ["[336611328]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5730 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1655275803328.774, "dur": 5.013, + "args": { + "External id": 4058724,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[336611328], []], "Ev Idx": 5731 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::chunk_cat", "pid": 1336756, "tid": 1381189, + "ts": 1655275803352.952, "dur": 12012.986, + "args": { + "External id": 4058725,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[], [], [], [42076416, 1]], "Input Dims": [[], [], [], [8, 42076416]], "Ev Idx": 5732 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_chunk_cat", "pid": 1336756, "tid": 1381189, + "ts": 1655275803371.895, "dur": 11981.536, + "args": { + "External id": 4058726,"Record function id": 0, "Concrete Inputs": ["", "0", "8", ""], "Input type": ["TensorList", "Scalar", "Scalar", "float"], "Input Strides": [[], [], [], [42076416, 1]], "Input Dims": [[], [], [], [8, 42076416]], "Ev Idx": 5733 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655275803644.061, "dur": 21.529, + "args": { + "External id": 4058727,"Record function id": 0, "Concrete Inputs": ["[82421]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5734 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1381189, + "ts": 1655275803719.315, "dur": 11587.859, + "args": { + "External id": 4058728,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[82421], [], [], [], [], [], [], []], "Ev Idx": 5735 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336756, "tid": 1381189, + "ts": 1655275803722.436, "dur": 11583.663, + "args": { + "External id": 4058729,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[82421], [], [], [], [], [], []], "Ev Idx": 5736 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275803727.237, "dur": 14.415, + "args": { + "External id": 4058730,"Record function id": 0, "Concrete Inputs": ["[82421]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5737 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1381189, + "ts": 1655275803743.932, "dur": 11556.547, + "args": { + "External id": 4058731,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[82421], [82421], []], "Ev Idx": 5738 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 1336756, "tid": 1381189, + "ts": 1655275815508.633, "dur": 10.981, + "args": { + "External id": 4058732,"Record function id": 0, "Concrete Inputs": ["", "[42076416]", "", "", "", "False"], "Input type": ["float", "ScalarList", "", "", "", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[336611328], [], [], [], [], []], "Ev Idx": 5739 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1655275815511.837, "dur": 7.151, + "args": { + "External id": 4058733,"Record function id": 0, "Concrete Inputs": ["[42076416]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5740 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_reduce_scatter_base_", "pid": 1336756, "tid": 1381189, + "ts": 1655275815550.339, "dur": 469.126, + "args": { + "External id": 4058734,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "-1"], "Input type": ["float", "float", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], [], []], "Input Dims": [[42076416], [336611328], [], [], [], []], "Ev Idx": 5741 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336756, "tid": 1381189, + "ts": 1655275815575.771, "dur": 405.240, + "args": { + "External id": 4058735,"Record function id": 0, "Collective name": "_reduce_scatter_base", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 3, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "3", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 42076416, "Process Group Name": "0", "Input type": ["float", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[336611328], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 5742, "In msg nelems": 336611328 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_reduce_scatter_base", "pid": 1336756, "tid": 1381189, + "ts": 1655275815591.615, "dur": 383.733, + "args": { + "External id": 4058736,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[336611328]], "Ev Idx": 5743 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336756, "tid": 1381189, + "ts": 1655275816042.967, "dur": 3.573, + "args": { + "External id": 4058737,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "3", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 5744, "In msg nelems": 0, "Rank": 3, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275816109.174, "dur": 7.269, + "args": { + "External id": 4058738,"Record function id": 0, "Concrete Inputs": ["", "[4000, 2048]", "[2048, 1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5745 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275816159.802, "dur": 1.112, + "args": { + "External id": 4058739,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "8192000"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5746 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275816174.436, "dur": 1.144, + "args": { + "External id": 4058740,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "8192256"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5747 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275816186.288, "dur": 2.020, + "args": { + "External id": 4058741,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "8716544"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5748 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275816198.150, "dur": 1.098, + "args": { + "External id": 4058742,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "9240832"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5749 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275816208.019, "dur": 1.199, + "args": { + "External id": 4058743,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "9765120"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5750 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275816220.959, "dur": 1.154, + "args": { + "External id": 4058744,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "10289408"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5751 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275816232.266, "dur": 1.917, + "args": { + "External id": 4058745,"Record function id": 0, "Concrete Inputs": ["", "[704, 2048]", "[2048, 1]", "10289664"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5752 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275816244.381, "dur": 1.005, + "args": { + "External id": 4058746,"Record function id": 0, "Concrete Inputs": ["", "[704, 2048]", "[2048, 1]", "11731456"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5753 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275816254.442, "dur": 0.880, + "args": { + "External id": 4058747,"Record function id": 0, "Concrete Inputs": ["", "[256, 5632]", "[5632, 1]", "13173248"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5754 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275816265.209, "dur": 1.006, + "args": { + "External id": 4058748,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "14615040"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5755 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275816274.634, "dur": 2.285, + "args": { + "External id": 4058749,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "14615296"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5756 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275816285.608, "dur": 1.193, + "args": { + "External id": 4058750,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "15139584"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5757 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275816295.854, "dur": 0.880, + "args": { + "External id": 4058751,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "15663872"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5758 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275816306.791, "dur": 1.039, + "args": { + "External id": 4058752,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "16188160"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5759 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275816316.233, "dur": 1.579, + "args": { + "External id": 4058753,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "16712448"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5760 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275816326.258, "dur": 1.157, + "args": { + "External id": 4058754,"Record function id": 0, "Concrete Inputs": ["", "[704, 2048]", "[2048, 1]", "16712704"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5761 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275816336.111, "dur": 0.832, + "args": { + "External id": 4058755,"Record function id": 0, "Concrete Inputs": ["", "[704, 2048]", "[2048, 1]", "18154496"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5762 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275816346.245, "dur": 0.767, + "args": { + "External id": 4058756,"Record function id": 0, "Concrete Inputs": ["", "[256, 5632]", "[5632, 1]", "19596288"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5763 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275816354.844, "dur": 1.826, + "args": { + "External id": 4058757,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "21038080"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5764 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275816365.616, "dur": 1.031, + "args": { + "External id": 4058758,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "21038336"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5765 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275816375.451, "dur": 1.132, + "args": { + "External id": 4058759,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "21562624"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5766 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275816385.387, "dur": 1.117, + "args": { + "External id": 4058760,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "22086912"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5767 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275816395.401, "dur": 2.165, + "args": { + "External id": 4058761,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "22611200"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5768 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275816406.208, "dur": 1.341, + "args": { + "External id": 4058762,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "23135488"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5769 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275816432.829, "dur": 1.970, + "args": { + "External id": 4058763,"Record function id": 0, "Concrete Inputs": ["", "[704, 2048]", "[2048, 1]", "23135744"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5770 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275816447.416, "dur": 1.005, + "args": { + "External id": 4058764,"Record function id": 0, "Concrete Inputs": ["", "[704, 2048]", "[2048, 1]", "24577536"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5771 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275816457.548, "dur": 2.343, + "args": { + "External id": 4058765,"Record function id": 0, "Concrete Inputs": ["", "[256, 5632]", "[5632, 1]", "26019328"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5772 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275816468.232, "dur": 1.337, + "args": { + "External id": 4058766,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "27461120"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5773 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275816478.456, "dur": 1.347, + "args": { + "External id": 4058767,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "27461376"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5774 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275816489.071, "dur": 1.306, + "args": { + "External id": 4058768,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "27985664"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5775 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275816499.058, "dur": 2.104, + "args": { + "External id": 4058769,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "28509952"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5776 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275816509.931, "dur": 1.126, + "args": { + "External id": 4058770,"Record function id": 0, "Concrete Inputs": ["", "[256, 2048]", "[2048, 1]", "29034240"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5777 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275816520.183, "dur": 1.050, + "args": { + "External id": 4058771,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "29558528"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5778 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275816530.074, "dur": 1.377, + "args": { + "External id": 4058772,"Record function id": 0, "Concrete Inputs": ["", "[704, 2048]", "[2048, 1]", "29558784"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5779 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275816540.481, "dur": 2.407, + "args": { + "External id": 4058773,"Record function id": 0, "Concrete Inputs": ["", "[704, 2048]", "[2048, 1]", "31000576"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5780 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275816552.210, "dur": 1.305, + "args": { + "External id": 4058774,"Record function id": 0, "Concrete Inputs": ["", "[256, 5632]", "[5632, 1]", "32442368"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5781 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275816562.017, "dur": 1.232, + "args": { + "External id": 4058775,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "33884160"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5782 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1381189, + "ts": 1655275816572.684, "dur": 1.335, + "args": { + "External id": 4058776,"Record function id": 0, "Concrete Inputs": ["", "[4000, 2048]", "[2048, 1]", "33884416"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5783 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "ProfilerStep#168959", "pid": 1336756, "tid": 1336756, + "ts": 1655273725537.919, "dur": 2123796.827, + "args": { + "External id": 4047873,"Record function id": 0, "Ev Idx": 5784 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "Optimizer.zero_grad#AdamW.zero_grad", "pid": 1336756, "tid": 1336756, + "ts": 1655273725567.140, "dur": 545.254, + "args": { + "External id": 4047874,"Record function id": 0, "Ev Idx": 5785 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "enumerate(DataLoader)#_StatefulMultiProcessingDataLoaderIter.__next__", "pid": 1336756, "tid": 1336756, + "ts": 1655273726152.647, "dur": 75.877, + "args": { + "External id": 4047875,"Record function id": 0, "Ev Idx": 5786 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1336756, + "ts": 1655273727197.746, "dur": 19.414, + "args": { + "External id": 4047876,"Sequence number": 40618352, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "0", "0", "9223372036854775807", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8192, 1], [], [], [], []], "Input Dims": [[16, 8192], [], [], [], []], "Ev Idx": 5787 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273727210.358, "dur": 2.753, + "args": { + "External id": 4047877,"Record function id": 0, "Concrete Inputs": ["", "[16, 8192]", "[8192, 1]", "0"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[8192, 1], [], [], []], "Input Dims": [[16, 8192], [], [], []], "Ev Idx": 5788 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1336756, + "ts": 1655273727219.049, "dur": 6.375, + "args": { + "External id": 4047878,"Sequence number": 40618352, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "1", "0", "4096", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8192, 1], [], [], [], []], "Input Dims": [[16, 8192], [], [], [], []], "Ev Idx": 5789 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273727223.191, "dur": 0.993, + "args": { + "External id": 4047879,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096]", "[8192, 1]", "0"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[8192, 1], [], [], []], "Input Dims": [[16, 8192], [], [], []], "Ev Idx": 5790 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655273727247.305, "dur": 540.212, + "args": { + "External id": 4047880,"Sequence number": 40618352, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "4", "0", "", "", "False", "False", ""], "Input type": ["long int", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[8192, 1], [], [], [], [], [], [], []], "Input Dims": [[16, 4096], [], [], [], [], [], [], []], "Ev Idx": 5791 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336756, "tid": 1336756, + "ts": 1655273727254.077, "dur": 532.815, + "args": { + "External id": 4047881,"Sequence number": 40618352, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "4", "0", "", "", "False", ""], "Input type": ["long int", "Scalar", "Scalar", "", "", "Scalar", ""], "Input Strides": [[8192, 1], [], [], [], [], [], []], "Input Dims": [[16, 4096], [], [], [], [], [], []], "Ev Idx": 5792 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273727262.990, "dur": 9.431, + "args": { + "External id": 4047882,"Record function id": 0, "Concrete Inputs": ["[16, 4096]", "[4096, 1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5793 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1336756, + "ts": 1655273727274.828, "dur": 510.460, + "args": { + "External id": 4047883,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[4096, 1], [8192, 1], []], "Input Dims": [[16, 4096], [16, 4096], []], "Ev Idx": 5794 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655273727284.844, "dur": 0.454, + "args": { + "External id": 4047884,"Record function id": 0, "Concrete Inputs": ["", "4", "False", "False", ""], "Input type": ["long int", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[8192, 1], [], [], [], []], "Input Dims": [[16, 4096], [], [], [], []], "Ev Idx": 5795 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::expand_as", "pid": 1336756, "tid": 1336756, + "ts": 1655273727290.652, "dur": 5.993, + "args": { + "External id": 4047885,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["long int", "long int"], "Input Strides": [[8192, 1], [4096, 1]], "Input Dims": [[16, 4096], [16, 4096]], "Ev Idx": 5796 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::expand", "pid": 1336756, "tid": 1336756, + "ts": 1655273727293.160, "dur": 3.329, + "args": { + "External id": 4047886,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096]", "False"], "Input type": ["long int", "ScalarList", "Scalar"], "Input Strides": [[8192, 1], [], []], "Input Dims": [[16, 4096], [], []], "Ev Idx": 5797 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273727295.748, "dur": 0.509, + "args": { + "External id": 4047887,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096]", "[8192, 1]", ""], "Input type": ["long int", "ScalarList", "ScalarList", ""], "Input Strides": [[8192, 1], [], [], []], "Input Dims": [[16, 4096], [], [], []], "Ev Idx": 5798 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::contiguous", "pid": 1336756, "tid": 1336756, + "ts": 1655273727298.984, "dur": 258.131, + "args": { + "External id": 4047888,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["long int", "Scalar"], "Input Strides": [[8192, 1], []], "Input Dims": [[16, 4096], []], "Ev Idx": 5799 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 1336756, "tid": 1336756, + "ts": 1655273727301.502, "dur": 255.167, + "args": { + "External id": 4047889,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["long int", "Scalar"], "Input Strides": [[8192, 1], []], "Input Dims": [[16, 4096], []], "Ev Idx": 5800 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336756, "tid": 1336756, + "ts": 1655273727303.829, "dur": 11.357, + "args": { + "External id": 4047890,"Record function id": 0, "Concrete Inputs": ["", "4", "0", "", "", "0"], "Input type": ["long int", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[8192, 1], [], [], [], [], []], "Input Dims": [[16, 4096], [], [], [], [], []], "Ev Idx": 5801 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655273727310.667, "dur": 4.088, + "args": { + "External id": 4047891,"Record function id": 0, "Concrete Inputs": ["[16, 4096]", "4", "0", "", "", "0"], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5802 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1336756, + "ts": 1655273727317.568, "dur": 237.876, + "args": { + "External id": 4047892,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[4096, 1], [8192, 1], []], "Input Dims": [[16, 4096], [16, 4096], []], "Ev Idx": 5803 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1336756, + "ts": 1655273727560.382, "dur": 221.834, + "args": { + "External id": 4047893,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[16, 4096], [16, 4096], []], "Ev Idx": 5804 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655273727802.662, "dur": 542.948, + "args": { + "External id": 4047894,"Sequence number": 40618352, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "4", "0", "", "", "False", "False", ""], "Input type": ["long int", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[8192, 1], [], [], [], [], [], [], []], "Input Dims": [[16, 8192], [], [], [], [], [], [], []], "Ev Idx": 5805 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336756, "tid": 1336756, + "ts": 1655273727804.601, "dur": 540.384, + "args": { + "External id": 4047895,"Sequence number": 40618352, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "4", "0", "", "", "False", ""], "Input type": ["long int", "Scalar", "Scalar", "", "", "Scalar", ""], "Input Strides": [[8192, 1], [], [], [], [], [], []], "Input Dims": [[16, 8192], [], [], [], [], [], []], "Ev Idx": 5806 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273727809.380, "dur": 8.044, + "args": { + "External id": 4047896,"Record function id": 0, "Concrete Inputs": ["[16, 8192]", "[8192, 1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5807 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1336756, + "ts": 1655273727818.278, "dur": 522.021, + "args": { + "External id": 4047897,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[8192, 1], [8192, 1], []], "Input Dims": [[16, 8192], [16, 8192], []], "Ev Idx": 5808 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::arange", "pid": 1336756, "tid": 1336756, + "ts": 1655273728378.657, "dur": 65.797, + "args": { + "External id": 4047898,"Record function id": 0, "Concrete Inputs": ["0", "4096", "", "", "", "False"], "Input type": ["Scalar", "Scalar", "", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5809 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655273728384.708, "dur": 5.445, + "args": { + "External id": 4047899,"Record function id": 0, "Concrete Inputs": ["[0]", "4", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5810 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::arange", "pid": 1336756, "tid": 1336756, + "ts": 1655273728393.214, "dur": 50.571, + "args": { + "External id": 4047900,"Record function id": 0, "Concrete Inputs": ["0", "4096", "1", ""], "Input type": ["Scalar", "Scalar", "Scalar", "long int"], "Input Strides": [[], [], [], [1]], "Input Dims": [[], [], [], [0]], "Ev Idx": 5811 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336756, "tid": 1336756, + "ts": 1655273728398.110, "dur": 6.966, + "args": { + "External id": 4047901,"Record function id": 0, "Concrete Inputs": ["", "[4096]", ""], "Input type": ["long int", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 5812 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::repeat", "pid": 1336756, "tid": 1336756, + "ts": 1655273728457.318, "dur": 67.388, + "args": { + "External id": 4047902,"Sequence number": 40618352, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[16, 1]"], "Input type": ["long int", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4096], []], "Ev Idx": 5813 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::expand", "pid": 1336756, "tid": 1336756, + "ts": 1655273728462.547, "dur": 6.484, + "args": { + "External id": 4047903,"Record function id": 0, "Concrete Inputs": ["", "[1, 4096]", "False"], "Input type": ["long int", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[4096], [], []], "Ev Idx": 5814 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273728467.135, "dur": 1.584, + "args": { + "External id": 4047904,"Record function id": 0, "Concrete Inputs": ["", "[1, 4096]", "[4096, 1]", ""], "Input type": ["long int", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[4096], [], [], []], "Ev Idx": 5815 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655273728471.838, "dur": 3.951, + "args": { + "External id": 4047905,"Record function id": 0, "Concrete Inputs": ["[16, 4096]", "4", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5816 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::alias", "pid": 1336756, "tid": 1336756, + "ts": 1655273728478.614, "dur": 3.250, + "args": { + "External id": 4047906,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["long int"], "Input Strides": [[4096, 1]], "Input Dims": [[16, 4096]], "Ev Idx": 5817 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unfold", "pid": 1336756, "tid": 1336756, + "ts": 1655273728484.537, "dur": 6.017, + "args": { + "External id": 4047907,"Record function id": 0, "Concrete Inputs": ["", "0", "1", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[16, 4096], [], [], []], "Ev Idx": 5818 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273728489.840, "dur": 0.580, + "args": { + "External id": 4047908,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 1]", "[4096, 1, 4096]", ""], "Input type": ["long int", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[16, 4096], [], [], []], "Ev Idx": 5819 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unfold", "pid": 1336756, "tid": 1336756, + "ts": 1655273728491.397, "dur": 2.086, + "args": { + "External id": 4047909,"Record function id": 0, "Concrete Inputs": ["", "1", "4096", "4096"], "Input type": ["long int", "Scalar", "Scalar", "Scalar"], "Input Strides": [[4096, 1, 4096], [], [], []], "Input Dims": [[16, 4096, 1], [], [], []], "Ev Idx": 5820 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273728492.690, "dur": 0.700, + "args": { + "External id": 4047910,"Record function id": 0, "Concrete Inputs": ["", "[16, 1, 1, 4096]", "[4096, 4096, 4096, 1]", ""], "Input type": ["long int", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1, 4096], [], [], []], "Input Dims": [[16, 4096, 1], [], [], []], "Ev Idx": 5821 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::expand_as", "pid": 1336756, "tid": 1336756, + "ts": 1655273728495.344, "dur": 3.083, + "args": { + "External id": 4047911,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["long int", "long int"], "Input Strides": [[4096, 1], [4096, 4096, 4096, 1]], "Input Dims": [[1, 4096], [16, 1, 1, 4096]], "Ev Idx": 5822 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::expand", "pid": 1336756, "tid": 1336756, + "ts": 1655273728496.477, "dur": 1.770, + "args": { + "External id": 4047912,"Record function id": 0, "Concrete Inputs": ["", "[16, 1, 1, 4096]", "False"], "Input type": ["long int", "ScalarList", "Scalar"], "Input Strides": [[4096, 1], [], []], "Input Dims": [[1, 4096], [], []], "Ev Idx": 5823 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273728497.500, "dur": 0.657, + "args": { + "External id": 4047913,"Record function id": 0, "Concrete Inputs": ["", "[16, 1, 1, 4096]", "[0, 4096, 4096, 1]", ""], "Input type": ["long int", "ScalarList", "ScalarList", ""], "Input Strides": [[4096, 1], [], [], []], "Input Dims": [[1, 4096], [], [], []], "Ev Idx": 5824 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1336756, + "ts": 1655273728499.374, "dur": 24.710, + "args": { + "External id": 4047914,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[4096, 4096, 4096, 1], [0, 4096, 4096, 1], []], "Input Dims": [[16, 1, 1, 4096], [16, 1, 1, 4096], []], "Ev Idx": 5825 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655273728532.600, "dur": 29.313, + "args": { + "External id": 4047915,"Sequence number": 40618352, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "3", "False", "False", ""], "Input type": ["long int", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], []], "Input Dims": [[16, 4096], [], [], [], []], "Ev Idx": 5826 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336756, "tid": 1336756, + "ts": 1655273728535.784, "dur": 25.971, + "args": { + "External id": 4047916,"Sequence number": 40618352, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "3", "", "", "", "False", ""], "Input type": ["long int", "Scalar", "", "", "", "Scalar", ""], "Input Strides": [[4096, 1], [], [], [], [], [], []], "Input Dims": [[16, 4096], [], [], [], [], [], []], "Ev Idx": 5827 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273728540.430, "dur": 3.291, + "args": { + "External id": 4047917,"Record function id": 0, "Concrete Inputs": ["[16, 4096]", "[4096, 1]", "3", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5828 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1336756, + "ts": 1655273728544.520, "dur": 16.720, + "args": { + "External id": 4047918,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["int", "long int", "Scalar"], "Input Strides": [[4096, 1], [4096, 1], []], "Input Dims": [[16, 4096], [16, 4096], []], "Ev Idx": 5829 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::root_pre_forward", "pid": 1336756, "tid": 1336756, + "ts": 1655273728662.561, "dur": 133.373, + "args": { + "External id": 4047919,"Record function id": 0, "Ev Idx": 5830 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::inputs_to_device", "pid": 1336756, "tid": 1336756, + "ts": 1655273728732.293, "dur": 54.518, + "args": { + "External id": 4047920,"Record function id": 0, "Ev Idx": 5831 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 1336756, "tid": 1336756, + "ts": 1655273728801.903, "dur": 38.829, + "args": { + "External id": 4047921,"Record function id": 0, "Ev Idx": 5832 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward", "pid": 1336756, "tid": 1336756, + "ts": 1655273728850.152, "dur": 11781.997, + "args": { + "External id": 4047922,"Record function id": 0, "Ev Idx": 5833 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather", "pid": 1336756, "tid": 1336756, + "ts": 1655273728857.506, "dur": 1206.773, + "args": { + "External id": 4047923,"Record function id": 0, "Ev Idx": 5834 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655273728944.654, "dur": 5.432, + "args": { + "External id": 4047924,"Record function id": 0, "Concrete Inputs": ["[42076416]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5835 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336756, "tid": 1336756, + "ts": 1655273728965.939, "dur": 150.951, + "args": { + "External id": 4047925,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["c10::BFloat16", "", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[42076416], [], []], "Ev Idx": 5836 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273728969.912, "dur": 1.577, + "args": { + "External id": 4047926,"Record function id": 0, "Concrete Inputs": ["", "[8192000]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5837 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273728974.685, "dur": 2.290, + "args": { + "External id": 4047927,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "8192000"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5838 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273728977.872, "dur": 0.446, + "args": { + "External id": 4047928,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "8192256"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5839 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273728978.966, "dur": 1.422, + "args": { + "External id": 4047929,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "8716544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5840 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273729022.916, "dur": 0.538, + "args": { + "External id": 4047930,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "9240832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5841 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273729024.212, "dur": 0.296, + "args": { + "External id": 4047931,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "9765120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5842 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273729027.387, "dur": 0.427, + "args": { + "External id": 4047932,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "10289408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5843 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273729030.696, "dur": 0.346, + "args": { + "External id": 4047933,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "10289664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5844 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273729031.643, "dur": 0.273, + "args": { + "External id": 4047934,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "11731456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5845 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273729034.388, "dur": 1.933, + "args": { + "External id": 4047935,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "13173248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5846 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273729036.924, "dur": 0.251, + "args": { + "External id": 4047936,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "14615040"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5847 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273729037.823, "dur": 0.966, + "args": { + "External id": 4047937,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "14615296"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5848 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273729042.802, "dur": 0.240, + "args": { + "External id": 4047938,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "15139584"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5849 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273729043.499, "dur": 0.159, + "args": { + "External id": 4047939,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "15663872"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5850 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273729046.308, "dur": 0.349, + "args": { + "External id": 4047940,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "16188160"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5851 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273729048.739, "dur": 0.316, + "args": { + "External id": 4047941,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "16712448"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5852 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273729049.729, "dur": 0.286, + "args": { + "External id": 4047942,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "16712704"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5853 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273729052.539, "dur": 1.933, + "args": { + "External id": 4047943,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "18154496"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5854 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273729055.263, "dur": 0.418, + "args": { + "External id": 4047944,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "19596288"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5855 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273729056.233, "dur": 1.055, + "args": { + "External id": 4047945,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "21038080"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5856 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273729062.126, "dur": 0.135, + "args": { + "External id": 4047946,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "21038336"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5857 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273729062.847, "dur": 0.251, + "args": { + "External id": 4047947,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "21562624"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5858 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273729065.293, "dur": 0.214, + "args": { + "External id": 4047948,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "22086912"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5859 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273729068.270, "dur": 0.166, + "args": { + "External id": 4047949,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "22611200"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5860 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273729068.980, "dur": 0.354, + "args": { + "External id": 4047950,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "23135488"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5861 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273729071.882, "dur": 1.794, + "args": { + "External id": 4047951,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "23135744"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5862 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273729074.188, "dur": 0.289, + "args": { + "External id": 4047952,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "24577536"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5863 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273729075.060, "dur": 1.058, + "args": { + "External id": 4047953,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "26019328"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5864 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273729080.625, "dur": 0.269, + "args": { + "External id": 4047954,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "27461120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5865 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273729081.339, "dur": 0.228, + "args": { + "External id": 4047955,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "27461376"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5866 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273729083.739, "dur": 0.374, + "args": { + "External id": 4047956,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "27985664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5867 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273729086.581, "dur": 0.304, + "args": { + "External id": 4047957,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "28509952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5868 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273729087.447, "dur": 0.313, + "args": { + "External id": 4047958,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "29034240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5869 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273729090.006, "dur": 1.702, + "args": { + "External id": 4047959,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "29558528"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5870 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273729092.290, "dur": 0.280, + "args": { + "External id": 4047960,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "29558784"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5871 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273729093.411, "dur": 0.996, + "args": { + "External id": 4047961,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "31000576"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5872 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273729098.956, "dur": 0.136, + "args": { + "External id": 4047962,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "32442368"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5873 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273729099.660, "dur": 0.147, + "args": { + "External id": 4047963,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "33884160"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5874 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273729101.973, "dur": 0.144, + "args": { + "External id": 4047964,"Record function id": 0, "Concrete Inputs": ["", "[8192000]", "[1]", "33884416"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5875 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336756, "tid": 1336756, + "ts": 1655273729136.695, "dur": 78.456, + "args": { + "External id": 4047965,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[], [], []], "Input Dims": [[], [], []], "Ev Idx": 5876 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 1336756, "tid": 1336756, + "ts": 1655273729278.978, "dur": 254.464, + "args": { + "External id": 4047966,"Record function id": 0, "Concrete Inputs": ["", "", "42076416", "8", "3", "15", ""], "Input type": ["TensorList", "", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], []], "Ev Idx": 5877 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655273729293.950, "dur": 6.563, + "args": { + "External id": 4047967,"Record function id": 0, "Concrete Inputs": ["[336611328]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5878 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 1336756, "tid": 1336756, + "ts": 1655273729307.214, "dur": 13.395, + "args": { + "External id": 4047968,"Record function id": 0, "Concrete Inputs": ["", "0", "126229248", "42076416"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[336611328], [], [], []], "Ev Idx": 5879 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1336756, + "ts": 1655273729312.927, "dur": 7.280, + "args": { + "External id": 4047969,"Record function id": 0, "Concrete Inputs": ["", "0", "126229248", "168305664", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[336611328], [], [], [], []], "Ev Idx": 5880 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273729317.266, "dur": 0.484, + "args": { + "External id": 4047970,"Record function id": 0, "Concrete Inputs": ["", "[42076416]", "[1]", "126229248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[336611328], [], [], []], "Ev Idx": 5881 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336756, "tid": 1336756, + "ts": 1655273729328.406, "dur": 109.902, + "args": { + "External id": 4047971,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["c10::BFloat16", "", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[42076416], [], []], "Ev Idx": 5882 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273729330.194, "dur": 0.399, + "args": { + "External id": 4047972,"Record function id": 0, "Concrete Inputs": ["", "[8192000]", "[1]", "126229248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5883 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273729333.026, "dur": 0.452, + "args": { + "External id": 4047973,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "134421248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5884 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273729334.086, "dur": 1.086, + "args": { + "External id": 4047974,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "134421504"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5885 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273729335.840, "dur": 0.559, + "args": { + "External id": 4047975,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "134945792"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5886 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273729338.675, "dur": 0.189, + "args": { + "External id": 4047976,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "135470080"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5887 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273729339.426, "dur": 0.216, + "args": { + "External id": 4047977,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "135994368"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5888 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273729340.562, "dur": 0.163, + "args": { + "External id": 4047978,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "136518656"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5889 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273729342.905, "dur": 0.294, + "args": { + "External id": 4047979,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "136518912"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5890 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273729343.943, "dur": 0.625, + "args": { + "External id": 4047980,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "137960704"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5891 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273729346.643, "dur": 0.286, + "args": { + "External id": 4047981,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "139402496"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5892 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273729349.375, "dur": 1.092, + "args": { + "External id": 4047982,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "140844288"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5893 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273729351.024, "dur": 0.275, + "args": { + "External id": 4047983,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "140844544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5894 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273729353.746, "dur": 0.453, + "args": { + "External id": 4047984,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "141368832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5895 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273729356.100, "dur": 0.142, + "args": { + "External id": 4047985,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "141893120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5896 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273729356.861, "dur": 0.228, + "args": { + "External id": 4047986,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "142417408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5897 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273729359.350, "dur": 1.968, + "args": { + "External id": 4047987,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "142941696"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5898 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273729361.898, "dur": 0.400, + "args": { + "External id": 4047988,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "142941952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5899 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273729364.718, "dur": 0.357, + "args": { + "External id": 4047989,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "144383744"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5900 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273729367.494, "dur": 1.001, + "args": { + "External id": 4047990,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "145825536"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5901 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273729369.138, "dur": 0.347, + "args": { + "External id": 4047991,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "147267328"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5902 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273729371.445, "dur": 0.253, + "args": { + "External id": 4047992,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "147267584"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5903 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273729373.788, "dur": 0.175, + "args": { + "External id": 4047993,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "147791872"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5904 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273729374.520, "dur": 0.154, + "args": { + "External id": 4047994,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "148316160"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5905 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273729376.956, "dur": 1.703, + "args": { + "External id": 4047995,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "148840448"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5906 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273729379.408, "dur": 0.146, + "args": { + "External id": 4047996,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "149364736"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5907 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273729382.001, "dur": 0.280, + "args": { + "External id": 4047997,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "149364992"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5908 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273729384.747, "dur": 0.871, + "args": { + "External id": 4047998,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "150806784"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5909 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273729386.228, "dur": 0.149, + "args": { + "External id": 4047999,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "152248576"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5910 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273729389.181, "dur": 0.147, + "args": { + "External id": 4048000,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "153690368"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5911 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273729391.578, "dur": 0.350, + "args": { + "External id": 4048001,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "153690624"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5912 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273729392.677, "dur": 0.386, + "args": { + "External id": 4048002,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "154214912"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5913 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273729395.137, "dur": 1.574, + "args": { + "External id": 4048003,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "154739200"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5914 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273729397.428, "dur": 0.332, + "args": { + "External id": 4048004,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "155263488"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5915 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273729400.029, "dur": 0.174, + "args": { + "External id": 4048005,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "155787776"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5916 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273729402.539, "dur": 1.000, + "args": { + "External id": 4048006,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "155788032"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5917 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273729404.012, "dur": 0.144, + "args": { + "External id": 4048007,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "157229824"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5918 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273729406.227, "dur": 0.145, + "args": { + "External id": 4048008,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "158671616"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5919 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273729408.572, "dur": 0.173, + "args": { + "External id": 4048009,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "160113408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5920 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273729409.312, "dur": 0.150, + "args": { + "External id": 4048010,"Record function id": 0, "Concrete Inputs": ["", "[8192000]", "[1]", "160113664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[42076416], [], [], []], "Ev Idx": 5921 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336756, "tid": 1336756, + "ts": 1655273729460.540, "dur": 57.742, + "args": { + "External id": 4048011,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[], [], []], "Input Dims": [[], [], []], "Ev Idx": 5922 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 1336756, "tid": 1336756, + "ts": 1655273729590.769, "dur": 339.909, + "args": { + "External id": 4048012,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[336611328], [42076416], [], [], []], "Ev Idx": 5923 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336756, "tid": 1336756, + "ts": 1655273729629.240, "dur": 296.233, + "args": { + "External id": 4048013,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 3, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "3", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 336611328, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[42076416], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 5924, "In msg nelems": 42076416 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 1336756, "tid": 1336756, + "ts": 1655273729639.688, "dur": 280.252, + "args": { + "External id": 4048014,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[42076416]], "Ev Idx": 5925 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336756, "tid": 1336756, + "ts": 1655273729951.101, "dur": 2.355, + "args": { + "External id": 4048015,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "3", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 5926, "In msg nelems": 0, "Rank": 3, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out", "pid": 1336756, "tid": 1336756, + "ts": 1655273730081.107, "dur": 10385.754, + "args": { + "External id": 4048016,"Record function id": 0, "Ev Idx": 5927 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655273730250.228, "dur": 6.350, + "args": { + "External id": 4048017,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[336611328], []], "Ev Idx": 5928 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655273730260.328, "dur": 0.984, + "args": { + "External id": 4048018,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[65536000], []], "Ev Idx": 5929 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655273730263.126, "dur": 0.833, + "args": { + "External id": 4048019,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 5930 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655273730265.497, "dur": 1.848, + "args": { + "External id": 4048020,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 5931 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655273730270.324, "dur": 0.759, + "args": { + "External id": 4048021,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 5932 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655273730272.372, "dur": 0.948, + "args": { + "External id": 4048022,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 5933 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655273730274.815, "dur": 0.876, + "args": { + "External id": 4048023,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 5934 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655273730279.066, "dur": 1.659, + "args": { + "External id": 4048024,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 5935 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655273730284.042, "dur": 0.758, + "args": { + "External id": 4048025,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 5936 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655273730286.079, "dur": 0.678, + "args": { + "External id": 4048026,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 5937 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655273730288.152, "dur": 0.785, + "args": { + "External id": 4048027,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 5938 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655273730290.049, "dur": 1.875, + "args": { + "External id": 4048028,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 5939 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655273730294.975, "dur": 0.640, + "args": { + "External id": 4048029,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 5940 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655273730296.721, "dur": 0.912, + "args": { + "External id": 4048030,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 5941 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655273730298.790, "dur": 0.653, + "args": { + "External id": 4048031,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 5942 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655273730301.995, "dur": 1.613, + "args": { + "External id": 4048032,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 5943 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655273730306.145, "dur": 0.650, + "args": { + "External id": 4048033,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 5944 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655273730308.053, "dur": 0.644, + "args": { + "External id": 4048034,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 5945 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655273730309.908, "dur": 0.768, + "args": { + "External id": 4048035,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 5946 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655273730312.136, "dur": 1.223, + "args": { + "External id": 4048036,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 5947 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655273730316.113, "dur": 0.813, + "args": { + "External id": 4048037,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 5948 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655273730318.024, "dur": 0.685, + "args": { + "External id": 4048038,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 5949 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655273730319.975, "dur": 0.575, + "args": { + "External id": 4048039,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 5950 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655273730323.215, "dur": 1.706, + "args": { + "External id": 4048040,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 5951 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655273730327.748, "dur": 0.614, + "args": { + "External id": 4048041,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 5952 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655273730329.590, "dur": 0.666, + "args": { + "External id": 4048042,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 5953 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655273730331.454, "dur": 0.667, + "args": { + "External id": 4048043,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 5954 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655273730333.173, "dur": 1.572, + "args": { + "External id": 4048044,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 5955 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655273730337.240, "dur": 0.584, + "args": { + "External id": 4048045,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 5956 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655273730339.139, "dur": 0.902, + "args": { + "External id": 4048046,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 5957 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655273730341.256, "dur": 0.881, + "args": { + "External id": 4048047,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 5958 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655273730344.996, "dur": 1.877, + "args": { + "External id": 4048048,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 5959 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655273730350.156, "dur": 0.411, + "args": { + "External id": 4048049,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 5960 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655273730351.714, "dur": 0.539, + "args": { + "External id": 4048050,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 5961 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655273730353.815, "dur": 0.653, + "args": { + "External id": 4048051,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 5962 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655273730355.560, "dur": 1.500, + "args": { + "External id": 4048052,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 5963 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655273730359.670, "dur": 0.652, + "args": { + "External id": 4048053,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 5964 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655273730375.092, "dur": 0.746, + "args": { + "External id": 4048054,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 5965 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655273730377.027, "dur": 0.896, + "args": { + "External id": 4048055,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 5966 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655273730380.955, "dur": 1.468, + "args": { + "External id": 4048056,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[65536000], []], "Ev Idx": 5967 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 1336756, "tid": 1336756, + "ts": 1655273730408.952, "dur": 9992.320, + "args": { + "External id": 4048057,"Record function id": 0, "Concrete Inputs": ["", "", "1", ""], "Input type": ["c10::BFloat16", "", "Scalar", "TensorList"], "Input Strides": [[42076416, 1], [], [], []], "Input Dims": [[8, 42076416], [], [], []], "Ev Idx": 5968 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 1336756, "tid": 1336756, + "ts": 1655273730451.690, "dur": 9940.809, + "args": { + "External id": 4048058,"Record function id": 0, "Concrete Inputs": ["", "", "1", ""], "Input type": ["c10::BFloat16", "", "Scalar", "TensorList"], "Input Strides": [[42076416, 1], [], [], []], "Input Dims": [[8, 42076416], [], [], []], "Ev Idx": 5969 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655273730472.014, "dur": 5.318, + "args": { + "External id": 4048059,"Record function id": 0, "Concrete Inputs": ["[4290]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5970 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655273730483.787, "dur": 9871.240, + "args": { + "External id": 4048060,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[4290], [], [], [], [], [], [], []], "Ev Idx": 5971 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336756, "tid": 1336756, + "ts": 1655273730486.280, "dur": 9868.046, + "args": { + "External id": 4048061,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[4290], [], [], [], [], [], []], "Ev Idx": 5972 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273730492.663, "dur": 5.680, + "args": { + "External id": 4048062,"Record function id": 0, "Concrete Inputs": ["[4290]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5973 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1336756, + "ts": 1655273730499.904, "dur": 9851.203, + "args": { + "External id": 4048063,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[4290], [4290], []], "Ev Idx": 5974 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 1336756, "tid": 1336756, + "ts": 1655273740705.511, "dur": 34.441, + "args": { + "External id": 4048064,"Record function id": 0, "Ev Idx": 5975 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 0/0", "pid": 1336756, "tid": 1336756, + "ts": 1655273740741.293, "dur": 194.765, + "args": { + "External id": 4048065,"Record function id": 0, "Ev Idx": 5976 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 1336756, "tid": 1336756, + "ts": 1655273740779.704, "dur": 148.214, + "args": { + "External id": 4048066,"Sequence number": 40618352, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "long int"], "Input Strides": [[2048, 1], [4096, 1]], "Input Dims": [[32000, 2048], [16, 4096]], "Ev Idx": 5977 + } + }, + { + "ph": "s", "id": 228, "pid": 1336756, "tid": 1336756, "ts": 1655273740779.704, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_embedding_0", "pid": 1336756, "tid": 1336756, + "ts": 1655273740846.660, "dur": 47.458, + "args": { + "External id": 4048067,"kernel_hash": "ccn7soditjd7aij6esf6mo5c3yt5tfcdquxcuegqoe6voa34krv7", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/cn/ccn7soditjd7aij6esf6mo5c3yt5tfcdquxcuegqoe6voa34krv7.py", "kernel_backend": "triton", "Input type": ["long int", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[4096, 1], [2048, 1], [8388608, 2048, 1], []], "Input Dims": [[16, 4096], [32000, 2048], [16, 4096, 2048], []], "Ev Idx": 5978 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 1336756, "tid": 1336756, + "ts": 1655273741032.170, "dur": 55.068, + "args": { + "External id": 4048068,"Record function id": 0, "Ev Idx": 5979 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.0)", "pid": 1336756, "tid": 1336756, + "ts": 1655273741097.825, "dur": 7021.158, + "args": { + "External id": 4048069,"Record function id": 0, "Ev Idx": 5980 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.0)", "pid": 1336756, "tid": 1336756, + "ts": 1655273741104.931, "dur": 724.116, + "args": { + "External id": 4048070,"Record function id": 0, "Ev Idx": 5981 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655273741172.106, "dur": 11.316, + "args": { + "External id": 4048071,"Record function id": 0, "Concrete Inputs": ["[6423040]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5982 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336756, "tid": 1336756, + "ts": 1655273741196.303, "dur": 36.925, + "args": { + "External id": 4048072,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 5983 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273741204.387, "dur": 2.390, + "args": { + "External id": 4048073,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5984 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273741208.271, "dur": 0.486, + "args": { + "External id": 4048074,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5985 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273741211.445, "dur": 2.175, + "args": { + "External id": 4048075,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5986 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273741214.182, "dur": 0.223, + "args": { + "External id": 4048076,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5987 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273741215.017, "dur": 0.176, + "args": { + "External id": 4048077,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5988 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273741219.820, "dur": 0.241, + "args": { + "External id": 4048078,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5989 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273741220.735, "dur": 0.410, + "args": { + "External id": 4048079,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5990 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273741221.756, "dur": 1.152, + "args": { + "External id": 4048080,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5991 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273741227.028, "dur": 0.214, + "args": { + "External id": 4048081,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 5992 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336756, "tid": 1336756, + "ts": 1655273741243.199, "dur": 35.099, + "args": { + "External id": 4048082,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 5993 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 1336756, "tid": 1336756, + "ts": 1655273741308.086, "dur": 100.199, + "args": { + "External id": 4048083,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "6423040", "8", "3", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [], [], [], [], [], []], "Ev Idx": 5994 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655273741320.236, "dur": 3.879, + "args": { + "External id": 4048084,"Record function id": 0, "Concrete Inputs": ["[51384320]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 5995 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 1336756, "tid": 1336756, + "ts": 1655273741328.466, "dur": 9.127, + "args": { + "External id": 4048085,"Record function id": 0, "Concrete Inputs": ["", "0", "19269120", "6423040"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 5996 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1336756, + "ts": 1655273741332.428, "dur": 4.753, + "args": { + "External id": 4048086,"Record function id": 0, "Concrete Inputs": ["", "0", "19269120", "25692160", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[51384320], [], [], [], []], "Ev Idx": 5997 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273741335.525, "dur": 0.574, + "args": { + "External id": 4048087,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "[1]", "19269120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 5998 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336756, "tid": 1336756, + "ts": 1655273741344.038, "dur": 26.861, + "args": { + "External id": 4048088,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 5999 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273741347.132, "dur": 0.429, + "args": { + "External id": 4048089,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "19269120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6000 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273741348.465, "dur": 0.453, + "args": { + "External id": 4048090,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "19269376"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6001 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273741351.204, "dur": 0.630, + "args": { + "External id": 4048091,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "19793664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6002 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273741354.280, "dur": 0.272, + "args": { + "External id": 4048092,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "20317952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6003 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273741355.254, "dur": 2.901, + "args": { + "External id": 4048093,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "20842240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6004 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273741358.828, "dur": 0.417, + "args": { + "External id": 4048094,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "21366528"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6005 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273741361.443, "dur": 0.329, + "args": { + "External id": 4048095,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "21366784"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6006 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273741364.239, "dur": 0.151, + "args": { + "External id": 4048096,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "22808576"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6007 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273741366.767, "dur": 0.259, + "args": { + "External id": 4048097,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "24250368"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6008 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336756, "tid": 1336756, + "ts": 1655273741380.000, "dur": 20.106, + "args": { + "External id": 4048098,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 6009 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 1336756, "tid": 1336756, + "ts": 1655273741473.801, "dur": 275.244, + "args": { + "External id": 4048099,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[51384320], [6423040], [], [], []], "Ev Idx": 6010 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336756, "tid": 1336756, + "ts": 1655273741499.883, "dur": 245.073, + "args": { + "External id": 4048100,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 3, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "3", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 51384320, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[6423040], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 6011, "In msg nelems": 6423040 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 1336756, "tid": 1336756, + "ts": 1655273741509.299, "dur": 228.155, + "args": { + "External id": 4048101,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[6423040]], "Ev Idx": 6012 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336756, "tid": 1336756, + "ts": 1655273741767.647, "dur": 2.438, + "args": { + "External id": 4048102,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "3", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 6013, "In msg nelems": 0, "Rank": 3, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.0)", "pid": 1336756, "tid": 1336756, + "ts": 1655273741847.326, "dur": 6036.125, + "args": { + "External id": 4048103,"Record function id": 0, "Ev Idx": 6014 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655273741931.128, "dur": 5.806, + "args": { + "External id": 4048104,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[51384320], []], "Ev Idx": 6015 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655273741939.990, "dur": 1.067, + "args": { + "External id": 4048105,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 6016 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655273741942.539, "dur": 0.953, + "args": { + "External id": 4048106,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 6017 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655273741945.230, "dur": 1.718, + "args": { + "External id": 4048107,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 6018 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655273741948.035, "dur": 0.837, + "args": { + "External id": 4048108,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 6019 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655273741950.163, "dur": 0.685, + "args": { + "External id": 4048109,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 6020 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655273741955.627, "dur": 0.768, + "args": { + "External id": 4048110,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 6021 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655273741957.562, "dur": 2.004, + "args": { + "External id": 4048111,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 6022 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655273741960.877, "dur": 0.813, + "args": { + "External id": 4048112,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 6023 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655273741962.918, "dur": 0.568, + "args": { + "External id": 4048113,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 6024 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 1336756, "tid": 1336756, + "ts": 1655273742015.627, "dur": 5833.936, + "args": { + "External id": 4048114,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 6025 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 1336756, "tid": 1336756, + "ts": 1655273742034.005, "dur": 5809.727, + "args": { + "External id": 4048115,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 6026 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655273742059.986, "dur": 12.154, + "args": { + "External id": 4048116,"Record function id": 0, "Concrete Inputs": ["[2133]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6027 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655273742075.236, "dur": 5735.831, + "args": { + "External id": 4048117,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], [], []], "Ev Idx": 6028 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336756, "tid": 1336756, + "ts": 1655273742077.476, "dur": 5733.150, + "args": { + "External id": 4048118,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], []], "Ev Idx": 6029 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273742082.525, "dur": 6.184, + "args": { + "External id": 4048119,"Record function id": 0, "Concrete Inputs": ["[2133]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6030 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1336756, + "ts": 1655273742090.325, "dur": 5717.410, + "args": { + "External id": 4048120,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[2133], [2133], []], "Ev Idx": 6031 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 1336756, "tid": 1336756, + "ts": 1655273748065.288, "dur": 29.133, + "args": { + "External id": 4048121,"Sequence number": 40618353, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 6032 + } + }, + { + "ph": "s", "id": 227, "pid": 1336756, "tid": 1336756, "ts": 1655273748065.288, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 1336756, "tid": 1336756, + "ts": 1655273748080.769, "dur": 9.228, + "args": { + "External id": 4048122,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[8388608, 2048, 1], [8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048], [16, 4096, 2048]], "Ev Idx": 6033 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655273748085.562, "dur": 4.083, + "args": { + "External id": 4048123,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 6034 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 1336756, "tid": 1336756, + "ts": 1655273748155.306, "dur": 73.936, + "args": { + "External id": 4048124,"Record function id": 0, "Ev Idx": 6035 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 1336756, "tid": 1336756, + "ts": 1655273748230.692, "dur": 1080.107, + "args": { + "External id": 4048125,"Record function id": 0, "Ev Idx": 6036 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 1336756, "tid": 1336756, + "ts": 1655273748268.551, "dur": 1029.000, + "args": { + "External id": 4048126,"Sequence number": 40618354, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[8388608, 2048, 1], [1], [2048, 1], [2048, 1], [2048, 1], [32, 1], [32, 1], [2048, 1], [1], [2048, 1], [2048, 1], [5632, 1]], "Input Dims": [[16, 4096, 2048], [2048], [2048, 2048], [2048, 2048], [2048, 2048], [8192, 32], [8192, 32], [2048, 2048], [2048], [5632, 2048], [5632, 2048], [2048, 5632]], "Ev Idx": 6037 + } + }, + { + "ph": "s", "id": 226, "pid": 1336756, "tid": 1336756, "ts": 1655273748268.551, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 1336756, "tid": 1336756, + "ts": 1655273748330.650, "dur": 42.562, + "args": { + "External id": 4048127,"kernel_hash": "cd26ogptnjelaibpl2zumx5nxdttspqepvjkh7lpmsxbzrrexbxm", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "2048", "1", "9.9999999999999995e-07", "True", "2048", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/d2/cd26ogptnjelaibpl2zumx5nxdttspqepvjkh7lpmsxbzrrexbxm.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [65536, 2048], [2048], [65536], [], [], [], [], [], [], [], [], []], "Ev Idx": 6038 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655273748385.228, "dur": 131.614, + "args": { + "External id": 4048128,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 6039 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655273748531.470, "dur": 39.989, + "args": { + "External id": 4048129,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 6040 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655273748578.945, "dur": 31.190, + "args": { + "External id": 4048130,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 6041 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336756, "tid": 1336756, + "ts": 1655273748635.971, "dur": 25.526, + "args": { + "External id": 4048131,"kernel_hash": "cahe5odluo4swiyj4n2lohwh57qg5lym5qsijyjsjca7pvto5oka", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/ah/cahe5odluo4swiyj4n2lohwh57qg5lym5qsijyjsjca7pvto5oka.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 6042 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336756, "tid": 1336756, + "ts": 1655273748678.669, "dur": 15.049, + "args": { + "External id": 4048132,"kernel_hash": "cahe5odluo4swiyj4n2lohwh57qg5lym5qsijyjsjca7pvto5oka", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/ah/cahe5odluo4swiyj4n2lohwh57qg5lym5qsijyjsjca7pvto5oka.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 6043 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 1336756, "tid": 1336756, + "ts": 1655273748712.050, "dur": 120.686, + "args": { + "External id": 4048133,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.125", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [], [], [], [], [], [], [], []], "Ev Idx": 6044 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336756, "tid": 1336756, + "ts": 1655273748759.302, "dur": 10.023, + "args": { + "External id": 4048134,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[8388608, 2048, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [], [], [], [], []], "Ev Idx": 6045 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273748763.857, "dur": 4.555, + "args": { + "External id": 4048135,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "[8388608, 2048, 64, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6046 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655273748773.429, "dur": 3.497, + "args": { + "External id": 4048136,"Record function id": 0, "Concrete Inputs": ["[16, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6047 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655273748778.184, "dur": 1.053, + "args": { + "External id": 4048137,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6048 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655273748781.550, "dur": 2.460, + "args": { + "External id": 4048138,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6049 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655273748842.447, "dur": 42.944, + "args": { + "External id": 4048139,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 6050 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_2", "pid": 1336756, "tid": 1336756, + "ts": 1655273748913.647, "dur": 26.192, + "args": { + "External id": 4048140,"kernel_hash": "ckbsutlugbs4qoncxuwq6kkwome3xojo3ke4p7z74lcl5h4q62to", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "2048", "1", "9.9999999999999995e-07", "True", "2048", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/kb/ckbsutlugbs4qoncxuwq6kkwome3xojo3ke4p7z74lcl5h4q62to.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [1], [2048, 1], [2048, 1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [65536, 2048], [2048], [65536, 2048], [65536, 2048], [65536], [], [], [], [], [], [], [], [], []], "Ev Idx": 6051 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655273748946.435, "dur": 95.251, + "args": { + "External id": 4048141,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [5632, 1]], "Input Dims": [[65536, 2048], [2048, 5632], [65536, 5632]], "Ev Idx": 6052 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655273749055.363, "dur": 39.733, + "args": { + "External id": 4048142,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [5632, 1]], "Input Dims": [[65536, 2048], [2048, 5632], [65536, 5632]], "Ev Idx": 6053 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 1336756, "tid": 1336756, + "ts": 1655273749119.151, "dur": 23.995, + "args": { + "External id": 4048143,"kernel_hash": "cgh2wg2b6li2ipjwrhdr326ycb37fu4v576nwebfoyhwx5kppapn", "grid": "grid(369098752,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "369098752"], "kernel_file": "/tmp/torchinductor_cvm/gh/cgh2wg2b6li2ipjwrhdr326ycb37fu4v576nwebfoyhwx5kppapn.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[5632, 1], [5632, 1], [23068672, 5632, 1], []], "Input Dims": [[65536, 5632], [65536, 5632], [16, 4096, 5632], []], "Ev Idx": 6054 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655273749148.754, "dur": 34.882, + "args": { + "External id": 4048144,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [1, 5632], [2048, 1]], "Input Dims": [[65536, 5632], [5632, 2048], [65536, 2048]], "Ev Idx": 6055 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 1336756, "tid": 1336756, + "ts": 1655273749207.088, "dur": 17.846, + "args": { + "External id": 4048145,"kernel_hash": "cta7vcczabyyuqarwmn4dcnazkxudhfwrvnick7ql5cmsd5lz4rz", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/ta/cta7vcczabyyuqarwmn4dcnazkxudhfwrvnick7ql5cmsd5lz4rz.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[8388608, 2048, 1], [2048, 1], []], "Input Dims": [[16, 4096, 2048], [65536, 2048], []], "Ev Idx": 6056 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.0)", "pid": 1336756, "tid": 1336756, + "ts": 1655273749372.668, "dur": 106.182, + "args": { + "External id": 4048146,"Record function id": 0, "Ev Idx": 6057 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 1336756, "tid": 1336756, + "ts": 1655273749551.173, "dur": 46.538, + "args": { + "External id": 4048147,"Record function id": 0, "Ev Idx": 6058 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.1)", "pid": 1336756, "tid": 1336756, + "ts": 1655273749606.219, "dur": 19064.062, + "args": { + "External id": 4048148,"Record function id": 0, "Ev Idx": 6059 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.1)", "pid": 1336756, "tid": 1336756, + "ts": 1655273749617.169, "dur": 891.247, + "args": { + "External id": 4048149,"Record function id": 0, "Ev Idx": 6060 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655273749689.986, "dur": 8.633, + "args": { + "External id": 4048150,"Record function id": 0, "Concrete Inputs": ["[6423040]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6061 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336756, "tid": 1336756, + "ts": 1655273749713.116, "dur": 34.552, + "args": { + "External id": 4048151,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 6062 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273749718.029, "dur": 3.135, + "args": { + "External id": 4048152,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6063 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273749722.551, "dur": 0.432, + "args": { + "External id": 4048153,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6064 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273749725.451, "dur": 0.426, + "args": { + "External id": 4048154,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6065 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273749728.264, "dur": 0.243, + "args": { + "External id": 4048155,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6066 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273749729.311, "dur": 1.429, + "args": { + "External id": 4048156,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6067 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273749733.032, "dur": 0.520, + "args": { + "External id": 4048157,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6068 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273749736.157, "dur": 0.294, + "args": { + "External id": 4048158,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6069 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273749738.764, "dur": 0.459, + "args": { + "External id": 4048159,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6070 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273749739.854, "dur": 2.318, + "args": { + "External id": 4048160,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6071 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336756, "tid": 1336756, + "ts": 1655273749757.721, "dur": 39.361, + "args": { + "External id": 4048161,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 6072 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 1336756, "tid": 1336756, + "ts": 1655273749829.719, "dur": 103.687, + "args": { + "External id": 4048162,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "6423040", "8", "3", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [], [], [], [], [], []], "Ev Idx": 6073 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655273749840.581, "dur": 3.537, + "args": { + "External id": 4048163,"Record function id": 0, "Concrete Inputs": ["[51384320]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6074 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 1336756, "tid": 1336756, + "ts": 1655273749849.835, "dur": 8.785, + "args": { + "External id": 4048164,"Record function id": 0, "Concrete Inputs": ["", "0", "19269120", "6423040"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 6075 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1336756, + "ts": 1655273749854.026, "dur": 4.180, + "args": { + "External id": 4048165,"Record function id": 0, "Concrete Inputs": ["", "0", "19269120", "25692160", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[51384320], [], [], [], []], "Ev Idx": 6076 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273749856.680, "dur": 0.534, + "args": { + "External id": 4048166,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "[1]", "19269120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 6077 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336756, "tid": 1336756, + "ts": 1655273749864.867, "dur": 26.277, + "args": { + "External id": 4048167,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 6078 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273749868.300, "dur": 0.440, + "args": { + "External id": 4048168,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "19269120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6079 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273749869.569, "dur": 1.356, + "args": { + "External id": 4048169,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "19269376"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6080 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273749871.969, "dur": 2.136, + "args": { + "External id": 4048170,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "19793664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6081 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273749876.472, "dur": 0.162, + "args": { + "External id": 4048171,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "20317952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6082 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273749877.549, "dur": 0.413, + "args": { + "External id": 4048172,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "20842240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6083 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273749882.083, "dur": 0.275, + "args": { + "External id": 4048173,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "21366528"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6084 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273749883.186, "dur": 0.226, + "args": { + "External id": 4048174,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "21366784"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6085 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273749883.955, "dur": 0.601, + "args": { + "External id": 4048175,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "22808576"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6086 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273749887.096, "dur": 0.480, + "args": { + "External id": 4048176,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "24250368"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6087 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336756, "tid": 1336756, + "ts": 1655273749902.020, "dur": 23.340, + "args": { + "External id": 4048177,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 6088 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 1336756, "tid": 1336756, + "ts": 1655273750043.897, "dur": 344.070, + "args": { + "External id": 4048178,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[51384320], [6423040], [], [], []], "Ev Idx": 6089 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336756, "tid": 1336756, + "ts": 1655273750074.896, "dur": 308.557, + "args": { + "External id": 4048179,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 3, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "3", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 51384320, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[6423040], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 6090, "In msg nelems": 6423040 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 1336756, "tid": 1336756, + "ts": 1655273750085.461, "dur": 292.825, + "args": { + "External id": 4048180,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[6423040]], "Ev Idx": 6091 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336756, "tid": 1336756, + "ts": 1655273750407.216, "dur": 2.481, + "args": { + "External id": 4048181,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "3", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 6092, "In msg nelems": 0, "Rank": 3, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.1)", "pid": 1336756, "tid": 1336756, + "ts": 1655273750528.605, "dur": 17965.974, + "args": { + "External id": 4048182,"Record function id": 0, "Ev Idx": 6093 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655273750618.073, "dur": 6.267, + "args": { + "External id": 4048183,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[51384320], []], "Ev Idx": 6094 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655273750627.828, "dur": 1.087, + "args": { + "External id": 4048184,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 6095 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655273750630.524, "dur": 0.644, + "args": { + "External id": 4048185,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 6096 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655273750632.839, "dur": 0.660, + "args": { + "External id": 4048186,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 6097 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655273750634.695, "dur": 0.782, + "args": { + "External id": 4048187,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 6098 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655273750638.299, "dur": 0.827, + "args": { + "External id": 4048188,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 6099 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655273750640.580, "dur": 0.805, + "args": { + "External id": 4048189,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 6100 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655273750642.913, "dur": 2.596, + "args": { + "External id": 4048190,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 6101 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655273750646.975, "dur": 0.736, + "args": { + "External id": 4048191,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 6102 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655273750650.500, "dur": 0.611, + "args": { + "External id": 4048192,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 6103 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 1336756, "tid": 1336756, + "ts": 1655273750670.420, "dur": 17786.668, + "args": { + "External id": 4048193,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 6104 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 1336756, "tid": 1336756, + "ts": 1655273750684.832, "dur": 17765.621, + "args": { + "External id": 4048194,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 6105 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655273750710.513, "dur": 11.966, + "args": { + "External id": 4048195,"Record function id": 0, "Concrete Inputs": ["[2133]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6106 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655273750725.374, "dur": 17679.918, + "args": { + "External id": 4048196,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], [], []], "Ev Idx": 6107 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336756, "tid": 1336756, + "ts": 1655273750728.081, "dur": 17676.672, + "args": { + "External id": 4048197,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], []], "Ev Idx": 6108 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273750733.299, "dur": 4.688, + "args": { + "External id": 4048198,"Record function id": 0, "Concrete Inputs": ["[2133]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6109 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1336756, + "ts": 1655273750739.560, "dur": 17662.162, + "args": { + "External id": 4048199,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[2133], [2133], []], "Ev Idx": 6110 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 1336756, "tid": 1336756, + "ts": 1655273768620.060, "dur": 27.472, + "args": { + "External id": 4048200,"Sequence number": 40618355, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 6111 + } + }, + { + "ph": "s", "id": 225, "pid": 1336756, "tid": 1336756, "ts": 1655273768620.060, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 1336756, "tid": 1336756, + "ts": 1655273768636.221, "dur": 6.799, + "args": { + "External id": 4048201,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[8388608, 2048, 1], [8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048], [16, 4096, 2048]], "Ev Idx": 6112 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655273768638.986, "dur": 3.799, + "args": { + "External id": 4048202,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 6113 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 1336756, "tid": 1336756, + "ts": 1655273768708.200, "dur": 73.713, + "args": { + "External id": 4048203,"Record function id": 0, "Ev Idx": 6114 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 1336756, "tid": 1336756, + "ts": 1655273768783.524, "dur": 1032.480, + "args": { + "External id": 4048204,"Record function id": 0, "Ev Idx": 6115 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 1336756, "tid": 1336756, + "ts": 1655273768820.470, "dur": 983.518, + "args": { + "External id": 4048205,"Sequence number": 40618356, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[8388608, 2048, 1], [1], [2048, 1], [2048, 1], [2048, 1], [32, 1], [32, 1], [2048, 1], [1], [2048, 1], [2048, 1], [5632, 1]], "Input Dims": [[16, 4096, 2048], [2048], [2048, 2048], [2048, 2048], [2048, 2048], [8192, 32], [8192, 32], [2048, 2048], [2048], [5632, 2048], [5632, 2048], [2048, 5632]], "Ev Idx": 6116 + } + }, + { + "ph": "s", "id": 224, "pid": 1336756, "tid": 1336756, "ts": 1655273768820.470, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 1336756, "tid": 1336756, + "ts": 1655273768894.269, "dur": 38.876, + "args": { + "External id": 4048206,"kernel_hash": "cd26ogptnjelaibpl2zumx5nxdttspqepvjkh7lpmsxbzrrexbxm", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "2048", "1", "9.9999999999999995e-07", "True", "2048", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/d2/cd26ogptnjelaibpl2zumx5nxdttspqepvjkh7lpmsxbzrrexbxm.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [65536, 2048], [2048], [65536], [], [], [], [], [], [], [], [], []], "Ev Idx": 6117 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655273768947.119, "dur": 130.859, + "args": { + "External id": 4048207,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 6118 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655273769089.783, "dur": 41.534, + "args": { + "External id": 4048208,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 6119 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655273769136.811, "dur": 31.317, + "args": { + "External id": 4048209,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 6120 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336756, "tid": 1336756, + "ts": 1655273769198.599, "dur": 25.974, + "args": { + "External id": 4048210,"kernel_hash": "cahe5odluo4swiyj4n2lohwh57qg5lym5qsijyjsjca7pvto5oka", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/ah/cahe5odluo4swiyj4n2lohwh57qg5lym5qsijyjsjca7pvto5oka.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 6121 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336756, "tid": 1336756, + "ts": 1655273769239.399, "dur": 15.818, + "args": { + "External id": 4048211,"kernel_hash": "cahe5odluo4swiyj4n2lohwh57qg5lym5qsijyjsjca7pvto5oka", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/ah/cahe5odluo4swiyj4n2lohwh57qg5lym5qsijyjsjca7pvto5oka.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 6122 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 1336756, "tid": 1336756, + "ts": 1655273769269.467, "dur": 124.711, + "args": { + "External id": 4048212,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.125", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [], [], [], [], [], [], [], []], "Ev Idx": 6123 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336756, "tid": 1336756, + "ts": 1655273769317.888, "dur": 13.384, + "args": { + "External id": 4048213,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[8388608, 2048, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [], [], [], [], []], "Ev Idx": 6124 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273769324.728, "dur": 5.798, + "args": { + "External id": 4048214,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "[8388608, 2048, 64, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6125 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655273769333.556, "dur": 5.207, + "args": { + "External id": 4048215,"Record function id": 0, "Concrete Inputs": ["[16, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6126 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655273769339.993, "dur": 2.747, + "args": { + "External id": 4048216,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6127 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655273769344.744, "dur": 2.436, + "args": { + "External id": 4048217,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6128 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655273769404.492, "dur": 63.590, + "args": { + "External id": 4048218,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 6129 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_2", "pid": 1336756, "tid": 1336756, + "ts": 1655273769500.507, "dur": 26.846, + "args": { + "External id": 4048219,"kernel_hash": "ckbsutlugbs4qoncxuwq6kkwome3xojo3ke4p7z74lcl5h4q62to", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "2048", "1", "9.9999999999999995e-07", "True", "2048", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/kb/ckbsutlugbs4qoncxuwq6kkwome3xojo3ke4p7z74lcl5h4q62to.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [1], [2048, 1], [2048, 1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [65536, 2048], [2048], [65536, 2048], [65536, 2048], [65536], [], [], [], [], [], [], [], [], []], "Ev Idx": 6130 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655273769536.130, "dur": 41.677, + "args": { + "External id": 4048220,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [5632, 1]], "Input Dims": [[65536, 2048], [2048, 5632], [65536, 5632]], "Ev Idx": 6131 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655273769583.933, "dur": 34.532, + "args": { + "External id": 4048221,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [5632, 1]], "Input Dims": [[65536, 2048], [2048, 5632], [65536, 5632]], "Ev Idx": 6132 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 1336756, "tid": 1336756, + "ts": 1655273769641.595, "dur": 21.871, + "args": { + "External id": 4048222,"kernel_hash": "cgh2wg2b6li2ipjwrhdr326ycb37fu4v576nwebfoyhwx5kppapn", "grid": "grid(369098752,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "369098752"], "kernel_file": "/tmp/torchinductor_cvm/gh/cgh2wg2b6li2ipjwrhdr326ycb37fu4v576nwebfoyhwx5kppapn.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[5632, 1], [5632, 1], [23068672, 5632, 1], []], "Input Dims": [[65536, 5632], [65536, 5632], [16, 4096, 5632], []], "Ev Idx": 6133 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655273769668.796, "dur": 35.046, + "args": { + "External id": 4048223,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [1, 5632], [2048, 1]], "Input Dims": [[65536, 5632], [5632, 2048], [65536, 2048]], "Ev Idx": 6134 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 1336756, "tid": 1336756, + "ts": 1655273769724.775, "dur": 18.600, + "args": { + "External id": 4048224,"kernel_hash": "cta7vcczabyyuqarwmn4dcnazkxudhfwrvnick7ql5cmsd5lz4rz", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/ta/cta7vcczabyyuqarwmn4dcnazkxudhfwrvnick7ql5cmsd5lz4rz.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[8388608, 2048, 1], [2048, 1], []], "Input Dims": [[16, 4096, 2048], [65536, 2048], []], "Ev Idx": 6135 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.1)", "pid": 1336756, "tid": 1336756, + "ts": 1655273769877.515, "dur": 70.895, + "args": { + "External id": 4048225,"Record function id": 0, "Ev Idx": 6136 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 1336756, "tid": 1336756, + "ts": 1655273770061.087, "dur": 46.173, + "args": { + "External id": 4048226,"Record function id": 0, "Ev Idx": 6137 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.2)", "pid": 1336756, "tid": 1336756, + "ts": 1655273770116.651, "dur": 17942.955, + "args": { + "External id": 4048227,"Record function id": 0, "Ev Idx": 6138 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.2)", "pid": 1336756, "tid": 1336756, + "ts": 1655273770126.810, "dur": 811.145, + "args": { + "External id": 4048228,"Record function id": 0, "Ev Idx": 6139 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655273770199.246, "dur": 8.733, + "args": { + "External id": 4048229,"Record function id": 0, "Concrete Inputs": ["[6423040]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6140 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336756, "tid": 1336756, + "ts": 1655273770220.841, "dur": 33.652, + "args": { + "External id": 4048230,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 6141 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273770226.105, "dur": 2.278, + "args": { + "External id": 4048231,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6142 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273770234.381, "dur": 0.305, + "args": { + "External id": 4048232,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6143 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273770235.463, "dur": 0.358, + "args": { + "External id": 4048233,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6144 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273770236.769, "dur": 0.273, + "args": { + "External id": 4048234,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6145 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273770239.721, "dur": 0.301, + "args": { + "External id": 4048235,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6146 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273770240.821, "dur": 0.268, + "args": { + "External id": 4048236,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6147 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273770243.163, "dur": 3.172, + "args": { + "External id": 4048237,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6148 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273770247.328, "dur": 0.167, + "args": { + "External id": 4048238,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6149 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273770248.461, "dur": 0.147, + "args": { + "External id": 4048239,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6150 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336756, "tid": 1336756, + "ts": 1655273770266.023, "dur": 37.959, + "args": { + "External id": 4048240,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 6151 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 1336756, "tid": 1336756, + "ts": 1655273770335.800, "dur": 121.562, + "args": { + "External id": 4048241,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "6423040", "8", "3", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [], [], [], [], [], []], "Ev Idx": 6152 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655273770347.436, "dur": 3.613, + "args": { + "External id": 4048242,"Record function id": 0, "Concrete Inputs": ["[51384320]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6153 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 1336756, "tid": 1336756, + "ts": 1655273770356.393, "dur": 9.129, + "args": { + "External id": 4048243,"Record function id": 0, "Concrete Inputs": ["", "0", "19269120", "6423040"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 6154 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1336756, + "ts": 1655273770360.565, "dur": 4.553, + "args": { + "External id": 4048244,"Record function id": 0, "Concrete Inputs": ["", "0", "19269120", "25692160", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[51384320], [], [], [], []], "Ev Idx": 6155 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273770363.499, "dur": 0.425, + "args": { + "External id": 4048245,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "[1]", "19269120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 6156 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336756, "tid": 1336756, + "ts": 1655273770373.050, "dur": 25.394, + "args": { + "External id": 4048246,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 6157 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273770374.579, "dur": 2.227, + "args": { + "External id": 4048247,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "19269120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6158 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273770377.848, "dur": 0.177, + "args": { + "External id": 4048248,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "19269376"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6159 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273770379.729, "dur": 0.204, + "args": { + "External id": 4048249,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "19793664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6160 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273770382.615, "dur": 1.209, + "args": { + "External id": 4048250,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "20317952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6161 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273770385.694, "dur": 0.169, + "args": { + "External id": 4048251,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "20842240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6162 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273770386.754, "dur": 0.248, + "args": { + "External id": 4048252,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "21366528"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6163 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273770389.228, "dur": 0.329, + "args": { + "External id": 4048253,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "21366784"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6164 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273770391.716, "dur": 0.296, + "args": { + "External id": 4048254,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "22808576"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6165 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273770392.574, "dur": 2.046, + "args": { + "External id": 4048255,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "24250368"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6166 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336756, "tid": 1336756, + "ts": 1655273770407.653, "dur": 40.567, + "args": { + "External id": 4048256,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 6167 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 1336756, "tid": 1336756, + "ts": 1655273770511.308, "dur": 342.462, + "args": { + "External id": 4048257,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[51384320], [6423040], [], [], []], "Ev Idx": 6168 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336756, "tid": 1336756, + "ts": 1655273770541.709, "dur": 307.209, + "args": { + "External id": 4048258,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 3, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "3", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 51384320, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[6423040], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 6169, "In msg nelems": 6423040 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 1336756, "tid": 1336756, + "ts": 1655273770553.632, "dur": 290.358, + "args": { + "External id": 4048259,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[6423040]], "Ev Idx": 6170 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336756, "tid": 1336756, + "ts": 1655273770873.583, "dur": 2.437, + "args": { + "External id": 4048260,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "3", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 6171, "In msg nelems": 0, "Rank": 3, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.2)", "pid": 1336756, "tid": 1336756, + "ts": 1655273770957.256, "dur": 16890.544, + "args": { + "External id": 4048261,"Record function id": 0, "Ev Idx": 6172 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655273771095.246, "dur": 6.506, + "args": { + "External id": 4048262,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[51384320], []], "Ev Idx": 6173 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655273771105.236, "dur": 0.990, + "args": { + "External id": 4048263,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 6174 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655273771107.823, "dur": 1.823, + "args": { + "External id": 4048264,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 6175 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655273771111.346, "dur": 0.783, + "args": { + "External id": 4048265,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 6176 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655273771113.515, "dur": 0.750, + "args": { + "External id": 4048266,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 6177 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655273771115.511, "dur": 0.806, + "args": { + "External id": 4048267,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 6178 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655273771119.513, "dur": 0.564, + "args": { + "External id": 4048268,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 6179 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655273771121.469, "dur": 1.788, + "args": { + "External id": 4048269,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 6180 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655273771124.669, "dur": 0.592, + "args": { + "External id": 4048270,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 6181 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655273771126.523, "dur": 0.563, + "args": { + "External id": 4048271,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 6182 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 1336756, "tid": 1336756, + "ts": 1655273771147.422, "dur": 16663.958, + "args": { + "External id": 4048272,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 6183 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 1336756, "tid": 1336756, + "ts": 1655273771162.206, "dur": 16642.551, + "args": { + "External id": 4048273,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 6184 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655273771185.212, "dur": 12.326, + "args": { + "External id": 4048274,"Record function id": 0, "Concrete Inputs": ["[2133]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6185 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655273771200.165, "dur": 16573.106, + "args": { + "External id": 4048275,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], [], []], "Ev Idx": 6186 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336756, "tid": 1336756, + "ts": 1655273771202.724, "dur": 16570.048, + "args": { + "External id": 4048276,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], []], "Ev Idx": 6187 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273771207.764, "dur": 4.457, + "args": { + "External id": 4048277,"Record function id": 0, "Concrete Inputs": ["[2133]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6188 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1336756, + "ts": 1655273771213.890, "dur": 16556.137, + "args": { + "External id": 4048278,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[2133], [2133], []], "Ev Idx": 6189 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 1336756, "tid": 1336756, + "ts": 1655273787971.215, "dur": 61.575, + "args": { + "External id": 4048279,"Sequence number": 40618357, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 6190 + } + }, + { + "ph": "s", "id": 223, "pid": 1336756, "tid": 1336756, "ts": 1655273787971.215, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 1336756, "tid": 1336756, + "ts": 1655273788020.064, "dur": 7.295, + "args": { + "External id": 4048280,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[8388608, 2048, 1], [8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048], [16, 4096, 2048]], "Ev Idx": 6191 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655273788022.786, "dur": 4.217, + "args": { + "External id": 4048281,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 6192 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 1336756, "tid": 1336756, + "ts": 1655273788098.528, "dur": 68.429, + "args": { + "External id": 4048282,"Record function id": 0, "Ev Idx": 6193 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 1336756, "tid": 1336756, + "ts": 1655273788168.546, "dur": 1032.479, + "args": { + "External id": 4048283,"Record function id": 0, "Ev Idx": 6194 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 1336756, "tid": 1336756, + "ts": 1655273788208.455, "dur": 979.790, + "args": { + "External id": 4048284,"Sequence number": 40618358, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[8388608, 2048, 1], [1], [2048, 1], [2048, 1], [2048, 1], [32, 1], [32, 1], [2048, 1], [1], [2048, 1], [2048, 1], [5632, 1]], "Input Dims": [[16, 4096, 2048], [2048], [2048, 2048], [2048, 2048], [2048, 2048], [8192, 32], [8192, 32], [2048, 2048], [2048], [5632, 2048], [5632, 2048], [2048, 5632]], "Ev Idx": 6195 + } + }, + { + "ph": "s", "id": 222, "pid": 1336756, "tid": 1336756, "ts": 1655273788208.455, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 1336756, "tid": 1336756, + "ts": 1655273788271.482, "dur": 40.351, + "args": { + "External id": 4048285,"kernel_hash": "cd26ogptnjelaibpl2zumx5nxdttspqepvjkh7lpmsxbzrrexbxm", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "2048", "1", "9.9999999999999995e-07", "True", "2048", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/d2/cd26ogptnjelaibpl2zumx5nxdttspqepvjkh7lpmsxbzrrexbxm.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [65536, 2048], [2048], [65536], [], [], [], [], [], [], [], [], []], "Ev Idx": 6196 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655273788323.465, "dur": 113.528, + "args": { + "External id": 4048286,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 6197 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655273788449.305, "dur": 41.539, + "args": { + "External id": 4048287,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 6198 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655273788499.404, "dur": 31.084, + "args": { + "External id": 4048288,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 6199 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336756, "tid": 1336756, + "ts": 1655273788554.360, "dur": 25.806, + "args": { + "External id": 4048289,"kernel_hash": "cahe5odluo4swiyj4n2lohwh57qg5lym5qsijyjsjca7pvto5oka", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/ah/cahe5odluo4swiyj4n2lohwh57qg5lym5qsijyjsjca7pvto5oka.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 6200 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336756, "tid": 1336756, + "ts": 1655273788596.932, "dur": 13.924, + "args": { + "External id": 4048290,"kernel_hash": "cahe5odluo4swiyj4n2lohwh57qg5lym5qsijyjsjca7pvto5oka", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/ah/cahe5odluo4swiyj4n2lohwh57qg5lym5qsijyjsjca7pvto5oka.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 6201 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 1336756, "tid": 1336756, + "ts": 1655273788627.649, "dur": 122.193, + "args": { + "External id": 4048291,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.125", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [], [], [], [], [], [], [], []], "Ev Idx": 6202 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336756, "tid": 1336756, + "ts": 1655273788674.527, "dur": 10.885, + "args": { + "External id": 4048292,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[8388608, 2048, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [], [], [], [], []], "Ev Idx": 6203 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273788680.194, "dur": 4.515, + "args": { + "External id": 4048293,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "[8388608, 2048, 64, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6204 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655273788687.732, "dur": 5.299, + "args": { + "External id": 4048294,"Record function id": 0, "Concrete Inputs": ["[16, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6205 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655273788694.117, "dur": 0.960, + "args": { + "External id": 4048295,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6206 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655273788697.450, "dur": 3.252, + "args": { + "External id": 4048296,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6207 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655273788759.695, "dur": 42.929, + "args": { + "External id": 4048297,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 6208 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_2", "pid": 1336756, "tid": 1336756, + "ts": 1655273788830.197, "dur": 25.515, + "args": { + "External id": 4048298,"kernel_hash": "ckbsutlugbs4qoncxuwq6kkwome3xojo3ke4p7z74lcl5h4q62to", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "2048", "1", "9.9999999999999995e-07", "True", "2048", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/kb/ckbsutlugbs4qoncxuwq6kkwome3xojo3ke4p7z74lcl5h4q62to.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [1], [2048, 1], [2048, 1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [65536, 2048], [2048], [65536, 2048], [65536, 2048], [65536], [], [], [], [], [], [], [], [], []], "Ev Idx": 6209 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655273788862.841, "dur": 40.153, + "args": { + "External id": 4048299,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [5632, 1]], "Input Dims": [[65536, 2048], [2048, 5632], [65536, 5632]], "Ev Idx": 6210 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655273788910.105, "dur": 35.689, + "args": { + "External id": 4048300,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [5632, 1]], "Input Dims": [[65536, 2048], [2048, 5632], [65536, 5632]], "Ev Idx": 6211 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 1336756, "tid": 1336756, + "ts": 1655273788964.952, "dur": 63.105, + "args": { + "External id": 4048301,"kernel_hash": "cgh2wg2b6li2ipjwrhdr326ycb37fu4v576nwebfoyhwx5kppapn", "grid": "grid(369098752,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "369098752"], "kernel_file": "/tmp/torchinductor_cvm/gh/cgh2wg2b6li2ipjwrhdr326ycb37fu4v576nwebfoyhwx5kppapn.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[5632, 1], [5632, 1], [23068672, 5632, 1], []], "Input Dims": [[65536, 5632], [65536, 5632], [16, 4096, 5632], []], "Ev Idx": 6212 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655273789035.827, "dur": 40.866, + "args": { + "External id": 4048302,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [1, 5632], [2048, 1]], "Input Dims": [[65536, 5632], [5632, 2048], [65536, 2048]], "Ev Idx": 6213 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 1336756, "tid": 1336756, + "ts": 1655273789100.463, "dur": 17.409, + "args": { + "External id": 4048303,"kernel_hash": "cta7vcczabyyuqarwmn4dcnazkxudhfwrvnick7ql5cmsd5lz4rz", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/ta/cta7vcczabyyuqarwmn4dcnazkxudhfwrvnick7ql5cmsd5lz4rz.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[8388608, 2048, 1], [2048, 1], []], "Input Dims": [[16, 4096, 2048], [65536, 2048], []], "Ev Idx": 6214 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.2)", "pid": 1336756, "tid": 1336756, + "ts": 1655273789262.781, "dur": 69.891, + "args": { + "External id": 4048304,"Record function id": 0, "Ev Idx": 6215 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 1336756, "tid": 1336756, + "ts": 1655273789402.498, "dur": 70.912, + "args": { + "External id": 4048305,"Record function id": 0, "Ev Idx": 6216 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.3)", "pid": 1336756, "tid": 1336756, + "ts": 1655273789483.626, "dur": 18430.605, + "args": { + "External id": 4048306,"Record function id": 0, "Ev Idx": 6217 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.3)", "pid": 1336756, "tid": 1336756, + "ts": 1655273789494.915, "dur": 899.014, + "args": { + "External id": 4048307,"Record function id": 0, "Ev Idx": 6218 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655273789567.456, "dur": 8.796, + "args": { + "External id": 4048308,"Record function id": 0, "Concrete Inputs": ["[6423040]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6219 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336756, "tid": 1336756, + "ts": 1655273789589.019, "dur": 33.696, + "args": { + "External id": 4048309,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 6220 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273789593.964, "dur": 2.353, + "args": { + "External id": 4048310,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6221 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273789601.056, "dur": 0.494, + "args": { + "External id": 4048311,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6222 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273789602.485, "dur": 0.623, + "args": { + "External id": 4048312,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6223 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273789605.646, "dur": 0.483, + "args": { + "External id": 4048313,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6224 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273789608.657, "dur": 0.202, + "args": { + "External id": 4048314,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6225 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273789609.536, "dur": 0.391, + "args": { + "External id": 4048315,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6226 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273789611.813, "dur": 2.911, + "args": { + "External id": 4048316,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6227 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273789615.249, "dur": 0.309, + "args": { + "External id": 4048317,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6228 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273789616.707, "dur": 0.160, + "args": { + "External id": 4048318,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6229 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336756, "tid": 1336756, + "ts": 1655273789634.292, "dur": 38.988, + "args": { + "External id": 4048319,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 6230 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 1336756, "tid": 1336756, + "ts": 1655273789709.663, "dur": 114.496, + "args": { + "External id": 4048320,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "6423040", "8", "3", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [], [], [], [], [], []], "Ev Idx": 6231 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655273789721.360, "dur": 5.145, + "args": { + "External id": 4048321,"Record function id": 0, "Concrete Inputs": ["[51384320]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6232 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 1336756, "tid": 1336756, + "ts": 1655273789731.540, "dur": 10.732, + "args": { + "External id": 4048322,"Record function id": 0, "Concrete Inputs": ["", "0", "19269120", "6423040"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 6233 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1336756, + "ts": 1655273789735.534, "dur": 6.324, + "args": { + "External id": 4048323,"Record function id": 0, "Concrete Inputs": ["", "0", "19269120", "25692160", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[51384320], [], [], [], []], "Ev Idx": 6234 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273789739.885, "dur": 0.606, + "args": { + "External id": 4048324,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "[1]", "19269120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 6235 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336756, "tid": 1336756, + "ts": 1655273789748.540, "dur": 24.522, + "args": { + "External id": 4048325,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 6236 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273789749.720, "dur": 0.483, + "args": { + "External id": 4048326,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "19269120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6237 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273789752.563, "dur": 2.331, + "args": { + "External id": 4048327,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "19269376"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6238 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273789755.578, "dur": 0.529, + "args": { + "External id": 4048328,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "19793664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6239 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273789756.704, "dur": 1.431, + "args": { + "External id": 4048329,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "20317952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6240 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273789762.093, "dur": 0.238, + "args": { + "External id": 4048330,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "20842240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6241 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273789762.987, "dur": 0.311, + "args": { + "External id": 4048331,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "21366528"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6242 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273789763.759, "dur": 0.342, + "args": { + "External id": 4048332,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "21366784"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6243 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273789768.042, "dur": 0.154, + "args": { + "External id": 4048333,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "22808576"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6244 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273789768.916, "dur": 0.145, + "args": { + "External id": 4048334,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "24250368"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6245 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336756, "tid": 1336756, + "ts": 1655273789792.051, "dur": 23.877, + "args": { + "External id": 4048335,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 6246 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 1336756, "tid": 1336756, + "ts": 1655273789877.180, "dur": 421.382, + "args": { + "External id": 4048336,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[51384320], [6423040], [], [], []], "Ev Idx": 6247 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336756, "tid": 1336756, + "ts": 1655273789907.968, "dur": 384.953, + "args": { + "External id": 4048337,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 3, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "3", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 51384320, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[6423040], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 6248, "In msg nelems": 6423040 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 1336756, "tid": 1336756, + "ts": 1655273789920.221, "dur": 366.484, + "args": { + "External id": 4048338,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[6423040]], "Ev Idx": 6249 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336756, "tid": 1336756, + "ts": 1655273790321.924, "dur": 2.285, + "args": { + "External id": 4048339,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "3", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 6250, "In msg nelems": 0, "Rank": 3, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.3)", "pid": 1336756, "tid": 1336756, + "ts": 1655273790413.427, "dur": 17318.038, + "args": { + "External id": 4048340,"Record function id": 0, "Ev Idx": 6251 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655273790527.194, "dur": 6.786, + "args": { + "External id": 4048341,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[51384320], []], "Ev Idx": 6252 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655273790537.592, "dur": 1.023, + "args": { + "External id": 4048342,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 6253 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655273790540.388, "dur": 1.953, + "args": { + "External id": 4048343,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 6254 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655273790543.891, "dur": 0.546, + "args": { + "External id": 4048344,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 6255 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655273790545.770, "dur": 0.816, + "args": { + "External id": 4048345,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 6256 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655273790547.839, "dur": 0.783, + "args": { + "External id": 4048346,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 6257 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655273790551.794, "dur": 0.849, + "args": { + "External id": 4048347,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 6258 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655273790554.313, "dur": 2.183, + "args": { + "External id": 4048348,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 6259 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655273790558.012, "dur": 0.743, + "args": { + "External id": 4048349,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 6260 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655273790561.709, "dur": 0.595, + "args": { + "External id": 4048350,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 6261 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 1336756, "tid": 1336756, + "ts": 1655273790582.005, "dur": 17112.778, + "args": { + "External id": 4048351,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 6262 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 1336756, "tid": 1336756, + "ts": 1655273790596.703, "dur": 17091.736, + "args": { + "External id": 4048352,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 6263 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655273790618.925, "dur": 12.671, + "args": { + "External id": 4048353,"Record function id": 0, "Concrete Inputs": ["[2133]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6264 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655273790634.728, "dur": 17022.006, + "args": { + "External id": 4048354,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], [], []], "Ev Idx": 6265 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336756, "tid": 1336756, + "ts": 1655273790637.555, "dur": 17018.599, + "args": { + "External id": 4048355,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], []], "Ev Idx": 6266 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273790644.677, "dur": 5.358, + "args": { + "External id": 4048356,"Record function id": 0, "Concrete Inputs": ["[2133]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6267 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1336756, + "ts": 1655273790651.708, "dur": 17001.555, + "args": { + "External id": 4048357,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[2133], [2133], []], "Ev Idx": 6268 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 1336756, "tid": 1336756, + "ts": 1655273807853.464, "dur": 37.069, + "args": { + "External id": 4048358,"Sequence number": 40618359, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 6269 + } + }, + { + "ph": "s", "id": 221, "pid": 1336756, "tid": 1336756, "ts": 1655273807853.464, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 1336756, "tid": 1336756, + "ts": 1655273807869.698, "dur": 16.404, + "args": { + "External id": 4048359,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[8388608, 2048, 1], [8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048], [16, 4096, 2048]], "Ev Idx": 6270 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655273807881.931, "dur": 3.876, + "args": { + "External id": 4048360,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 6271 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 1336756, "tid": 1336756, + "ts": 1655273807952.468, "dur": 103.879, + "args": { + "External id": 4048361,"Record function id": 0, "Ev Idx": 6272 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 1336756, "tid": 1336756, + "ts": 1655273808060.683, "dur": 1051.467, + "args": { + "External id": 4048362,"Record function id": 0, "Ev Idx": 6273 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 1336756, "tid": 1336756, + "ts": 1655273808103.030, "dur": 995.799, + "args": { + "External id": 4048363,"Sequence number": 40618360, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[8388608, 2048, 1], [1], [2048, 1], [2048, 1], [2048, 1], [32, 1], [32, 1], [2048, 1], [1], [2048, 1], [2048, 1], [5632, 1]], "Input Dims": [[16, 4096, 2048], [2048], [2048, 2048], [2048, 2048], [2048, 2048], [8192, 32], [8192, 32], [2048, 2048], [2048], [5632, 2048], [5632, 2048], [2048, 5632]], "Ev Idx": 6274 + } + }, + { + "ph": "s", "id": 220, "pid": 1336756, "tid": 1336756, "ts": 1655273808103.030, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 1336756, "tid": 1336756, + "ts": 1655273808166.394, "dur": 42.862, + "args": { + "External id": 4048364,"kernel_hash": "cd26ogptnjelaibpl2zumx5nxdttspqepvjkh7lpmsxbzrrexbxm", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "2048", "1", "9.9999999999999995e-07", "True", "2048", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/d2/cd26ogptnjelaibpl2zumx5nxdttspqepvjkh7lpmsxbzrrexbxm.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [65536, 2048], [2048], [65536], [], [], [], [], [], [], [], [], []], "Ev Idx": 6275 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655273808221.702, "dur": 101.759, + "args": { + "External id": 4048365,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 6276 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655273808335.450, "dur": 40.488, + "args": { + "External id": 4048366,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 6277 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655273808381.955, "dur": 31.131, + "args": { + "External id": 4048367,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 6278 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336756, "tid": 1336756, + "ts": 1655273808458.834, "dur": 27.211, + "args": { + "External id": 4048368,"kernel_hash": "cahe5odluo4swiyj4n2lohwh57qg5lym5qsijyjsjca7pvto5oka", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/ah/cahe5odluo4swiyj4n2lohwh57qg5lym5qsijyjsjca7pvto5oka.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 6279 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336756, "tid": 1336756, + "ts": 1655273808502.696, "dur": 13.620, + "args": { + "External id": 4048369,"kernel_hash": "cahe5odluo4swiyj4n2lohwh57qg5lym5qsijyjsjca7pvto5oka", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/ah/cahe5odluo4swiyj4n2lohwh57qg5lym5qsijyjsjca7pvto5oka.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 6280 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 1336756, "tid": 1336756, + "ts": 1655273808537.191, "dur": 128.643, + "args": { + "External id": 4048370,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.125", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [], [], [], [], [], [], [], []], "Ev Idx": 6281 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336756, "tid": 1336756, + "ts": 1655273808589.898, "dur": 10.240, + "args": { + "External id": 4048371,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[8388608, 2048, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [], [], [], [], []], "Ev Idx": 6282 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273808594.351, "dur": 5.019, + "args": { + "External id": 4048372,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "[8388608, 2048, 64, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6283 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655273808602.375, "dur": 4.410, + "args": { + "External id": 4048373,"Record function id": 0, "Concrete Inputs": ["[16, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6284 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655273808608.114, "dur": 0.962, + "args": { + "External id": 4048374,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6285 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655273808613.113, "dur": 4.237, + "args": { + "External id": 4048375,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6286 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655273808676.000, "dur": 48.931, + "args": { + "External id": 4048376,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 6287 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_2", "pid": 1336756, "tid": 1336756, + "ts": 1655273808754.088, "dur": 27.192, + "args": { + "External id": 4048377,"kernel_hash": "ckbsutlugbs4qoncxuwq6kkwome3xojo3ke4p7z74lcl5h4q62to", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "2048", "1", "9.9999999999999995e-07", "True", "2048", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/kb/ckbsutlugbs4qoncxuwq6kkwome3xojo3ke4p7z74lcl5h4q62to.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [1], [2048, 1], [2048, 1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [65536, 2048], [2048], [65536, 2048], [65536, 2048], [65536], [], [], [], [], [], [], [], [], []], "Ev Idx": 6288 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655273808789.799, "dur": 41.822, + "args": { + "External id": 4048378,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [5632, 1]], "Input Dims": [[65536, 2048], [2048, 5632], [65536, 5632]], "Ev Idx": 6289 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655273808838.314, "dur": 35.171, + "args": { + "External id": 4048379,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [5632, 1]], "Input Dims": [[65536, 2048], [2048, 5632], [65536, 5632]], "Ev Idx": 6290 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 1336756, "tid": 1336756, + "ts": 1655273808893.198, "dur": 24.559, + "args": { + "External id": 4048380,"kernel_hash": "cgh2wg2b6li2ipjwrhdr326ycb37fu4v576nwebfoyhwx5kppapn", "grid": "grid(369098752,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "369098752"], "kernel_file": "/tmp/torchinductor_cvm/gh/cgh2wg2b6li2ipjwrhdr326ycb37fu4v576nwebfoyhwx5kppapn.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[5632, 1], [5632, 1], [23068672, 5632, 1], []], "Input Dims": [[65536, 5632], [65536, 5632], [16, 4096, 5632], []], "Ev Idx": 6291 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655273808923.240, "dur": 34.892, + "args": { + "External id": 4048381,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [1, 5632], [2048, 1]], "Input Dims": [[65536, 5632], [5632, 2048], [65536, 2048]], "Ev Idx": 6292 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 1336756, "tid": 1336756, + "ts": 1655273808976.367, "dur": 56.293, + "args": { + "External id": 4048382,"kernel_hash": "cta7vcczabyyuqarwmn4dcnazkxudhfwrvnick7ql5cmsd5lz4rz", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/ta/cta7vcczabyyuqarwmn4dcnazkxudhfwrvnick7ql5cmsd5lz4rz.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[8388608, 2048, 1], [2048, 1], []], "Input Dims": [[16, 4096, 2048], [65536, 2048], []], "Ev Idx": 6293 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.3)", "pid": 1336756, "tid": 1336756, + "ts": 1655273809174.719, "dur": 72.972, + "args": { + "External id": 4048383,"Record function id": 0, "Ev Idx": 6294 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 1336756, "tid": 1336756, + "ts": 1655273809318.792, "dur": 45.112, + "args": { + "External id": 4048384,"Record function id": 0, "Ev Idx": 6295 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.4)", "pid": 1336756, "tid": 1336756, + "ts": 1655273809395.341, "dur": 17801.099, + "args": { + "External id": 4048385,"Record function id": 0, "Ev Idx": 6296 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.4)", "pid": 1336756, "tid": 1336756, + "ts": 1655273809406.739, "dur": 866.360, + "args": { + "External id": 4048386,"Record function id": 0, "Ev Idx": 6297 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655273809502.130, "dur": 9.809, + "args": { + "External id": 4048387,"Record function id": 0, "Concrete Inputs": ["[6423040]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6298 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336756, "tid": 1336756, + "ts": 1655273809524.599, "dur": 31.877, + "args": { + "External id": 4048388,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 6299 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273809530.669, "dur": 2.240, + "args": { + "External id": 4048389,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6300 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273809536.188, "dur": 0.410, + "args": { + "External id": 4048390,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6301 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273809537.370, "dur": 0.385, + "args": { + "External id": 4048391,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6302 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273809539.662, "dur": 0.973, + "args": { + "External id": 4048392,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6303 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273809541.224, "dur": 0.172, + "args": { + "External id": 4048393,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6304 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273809543.197, "dur": 0.198, + "args": { + "External id": 4048394,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6305 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273809545.919, "dur": 1.093, + "args": { + "External id": 4048395,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6306 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273809547.564, "dur": 0.166, + "args": { + "External id": 4048396,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6307 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273809550.021, "dur": 0.155, + "args": { + "External id": 4048397,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6308 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336756, "tid": 1336756, + "ts": 1655273809566.340, "dur": 39.591, + "args": { + "External id": 4048398,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 6309 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 1336756, "tid": 1336756, + "ts": 1655273809638.202, "dur": 100.396, + "args": { + "External id": 4048399,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "6423040", "8", "3", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [], [], [], [], [], []], "Ev Idx": 6310 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655273809649.976, "dur": 3.151, + "args": { + "External id": 4048400,"Record function id": 0, "Concrete Inputs": ["[51384320]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6311 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 1336756, "tid": 1336756, + "ts": 1655273809658.263, "dur": 11.999, + "args": { + "External id": 4048401,"Record function id": 0, "Concrete Inputs": ["", "0", "19269120", "6423040"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 6312 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1336756, + "ts": 1655273809662.248, "dur": 7.592, + "args": { + "External id": 4048402,"Record function id": 0, "Concrete Inputs": ["", "0", "19269120", "25692160", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[51384320], [], [], [], []], "Ev Idx": 6313 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273809666.486, "dur": 2.181, + "args": { + "External id": 4048403,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "[1]", "19269120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 6314 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336756, "tid": 1336756, + "ts": 1655273809676.349, "dur": 22.073, + "args": { + "External id": 4048404,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 6315 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273809677.515, "dur": 0.209, + "args": { + "External id": 4048405,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "19269120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6316 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273809679.722, "dur": 0.233, + "args": { + "External id": 4048406,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "19269376"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6317 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273809680.561, "dur": 0.202, + "args": { + "External id": 4048407,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "19793664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6318 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273809684.114, "dur": 1.320, + "args": { + "External id": 4048408,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "20317952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6319 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273809685.903, "dur": 0.186, + "args": { + "External id": 4048409,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "20842240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6320 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273809686.710, "dur": 1.840, + "args": { + "External id": 4048410,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "21366528"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6321 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273809690.452, "dur": 0.414, + "args": { + "External id": 4048411,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "21366784"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6322 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273809691.443, "dur": 0.162, + "args": { + "External id": 4048412,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "22808576"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6323 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273809693.668, "dur": 0.201, + "args": { + "External id": 4048413,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "24250368"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6324 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336756, "tid": 1336756, + "ts": 1655273809709.037, "dur": 22.183, + "args": { + "External id": 4048414,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 6325 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 1336756, "tid": 1336756, + "ts": 1655273809790.557, "dur": 389.870, + "args": { + "External id": 4048415,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[51384320], [6423040], [], [], []], "Ev Idx": 6326 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336756, "tid": 1336756, + "ts": 1655273809819.871, "dur": 355.079, + "args": { + "External id": 4048416,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 3, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "3", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 51384320, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[6423040], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 6327, "In msg nelems": 6423040 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 1336756, "tid": 1336756, + "ts": 1655273809830.798, "dur": 338.186, + "args": { + "External id": 4048417,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[6423040]], "Ev Idx": 6328 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336756, "tid": 1336756, + "ts": 1655273810204.307, "dur": 2.513, + "args": { + "External id": 4048418,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "3", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 6329, "In msg nelems": 0, "Rank": 3, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.4)", "pid": 1336756, "tid": 1336756, + "ts": 1655273810292.787, "dur": 16726.131, + "args": { + "External id": 4048419,"Record function id": 0, "Ev Idx": 6330 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655273810379.947, "dur": 6.061, + "args": { + "External id": 4048420,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[51384320], []], "Ev Idx": 6331 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655273810389.219, "dur": 0.928, + "args": { + "External id": 4048421,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 6332 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655273810391.840, "dur": 2.001, + "args": { + "External id": 4048422,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 6333 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655273810395.230, "dur": 0.644, + "args": { + "External id": 4048423,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 6334 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655273810397.163, "dur": 0.684, + "args": { + "External id": 4048424,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 6335 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655273810398.939, "dur": 0.608, + "args": { + "External id": 4048425,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 6336 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655273810403.262, "dur": 0.656, + "args": { + "External id": 4048426,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 6337 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655273810405.159, "dur": 1.850, + "args": { + "External id": 4048427,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 6338 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655273810408.721, "dur": 0.664, + "args": { + "External id": 4048428,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 6339 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655273810410.749, "dur": 0.545, + "args": { + "External id": 4048429,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 6340 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 1336756, "tid": 1336756, + "ts": 1655273810448.325, "dur": 16501.617, + "args": { + "External id": 4048430,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 6341 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 1336756, "tid": 1336756, + "ts": 1655273810464.073, "dur": 16479.108, + "args": { + "External id": 4048431,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 6342 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655273810484.849, "dur": 13.417, + "args": { + "External id": 4048432,"Record function id": 0, "Concrete Inputs": ["[2133]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6343 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655273810501.597, "dur": 16411.028, + "args": { + "External id": 4048433,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], [], []], "Ev Idx": 6344 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336756, "tid": 1336756, + "ts": 1655273810503.930, "dur": 16408.145, + "args": { + "External id": 4048434,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], []], "Ev Idx": 6345 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273810509.583, "dur": 5.981, + "args": { + "External id": 4048435,"Record function id": 0, "Concrete Inputs": ["[2133]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6346 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1336756, + "ts": 1655273810517.010, "dur": 16392.078, + "args": { + "External id": 4048436,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[2133], [2133], []], "Ev Idx": 6347 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 1336756, "tid": 1336756, + "ts": 1655273827145.212, "dur": 27.418, + "args": { + "External id": 4048437,"Sequence number": 40618361, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 6348 + } + }, + { + "ph": "s", "id": 219, "pid": 1336756, "tid": 1336756, "ts": 1655273827145.212, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 1336756, "tid": 1336756, + "ts": 1655273827160.621, "dur": 7.475, + "args": { + "External id": 4048438,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[8388608, 2048, 1], [8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048], [16, 4096, 2048]], "Ev Idx": 6349 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655273827163.586, "dur": 4.241, + "args": { + "External id": 4048439,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 6350 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 1336756, "tid": 1336756, + "ts": 1655273827231.885, "dur": 74.956, + "args": { + "External id": 4048440,"Record function id": 0, "Ev Idx": 6351 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 1336756, "tid": 1336756, + "ts": 1655273827308.484, "dur": 1034.877, + "args": { + "External id": 4048441,"Record function id": 0, "Ev Idx": 6352 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 1336756, "tid": 1336756, + "ts": 1655273827346.878, "dur": 983.724, + "args": { + "External id": 4048442,"Sequence number": 40618362, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[8388608, 2048, 1], [1], [2048, 1], [2048, 1], [2048, 1], [32, 1], [32, 1], [2048, 1], [1], [2048, 1], [2048, 1], [5632, 1]], "Input Dims": [[16, 4096, 2048], [2048], [2048, 2048], [2048, 2048], [2048, 2048], [8192, 32], [8192, 32], [2048, 2048], [2048], [5632, 2048], [5632, 2048], [2048, 5632]], "Ev Idx": 6353 + } + }, + { + "ph": "s", "id": 218, "pid": 1336756, "tid": 1336756, "ts": 1655273827346.878, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 1336756, "tid": 1336756, + "ts": 1655273827408.699, "dur": 53.098, + "args": { + "External id": 4048443,"kernel_hash": "cd26ogptnjelaibpl2zumx5nxdttspqepvjkh7lpmsxbzrrexbxm", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "2048", "1", "9.9999999999999995e-07", "True", "2048", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/d2/cd26ogptnjelaibpl2zumx5nxdttspqepvjkh7lpmsxbzrrexbxm.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [65536, 2048], [2048], [65536], [], [], [], [], [], [], [], [], []], "Ev Idx": 6354 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655273827476.734, "dur": 107.440, + "args": { + "External id": 4048444,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 6355 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655273827592.659, "dur": 38.525, + "args": { + "External id": 4048445,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 6356 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655273827638.710, "dur": 31.550, + "args": { + "External id": 4048446,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 6357 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336756, "tid": 1336756, + "ts": 1655273827695.508, "dur": 24.664, + "args": { + "External id": 4048447,"kernel_hash": "cahe5odluo4swiyj4n2lohwh57qg5lym5qsijyjsjca7pvto5oka", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/ah/cahe5odluo4swiyj4n2lohwh57qg5lym5qsijyjsjca7pvto5oka.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 6358 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336756, "tid": 1336756, + "ts": 1655273827736.578, "dur": 14.002, + "args": { + "External id": 4048448,"kernel_hash": "cahe5odluo4swiyj4n2lohwh57qg5lym5qsijyjsjca7pvto5oka", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/ah/cahe5odluo4swiyj4n2lohwh57qg5lym5qsijyjsjca7pvto5oka.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 6359 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 1336756, "tid": 1336756, + "ts": 1655273827768.198, "dur": 124.047, + "args": { + "External id": 4048449,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.125", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [], [], [], [], [], [], [], []], "Ev Idx": 6360 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336756, "tid": 1336756, + "ts": 1655273827817.322, "dur": 10.434, + "args": { + "External id": 4048450,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[8388608, 2048, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [], [], [], [], []], "Ev Idx": 6361 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273827822.122, "dur": 4.937, + "args": { + "External id": 4048451,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "[8388608, 2048, 64, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6362 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655273827830.574, "dur": 4.139, + "args": { + "External id": 4048452,"Record function id": 0, "Concrete Inputs": ["[16, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6363 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655273827836.070, "dur": 0.976, + "args": { + "External id": 4048453,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6364 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655273827839.459, "dur": 5.061, + "args": { + "External id": 4048454,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6365 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655273827903.278, "dur": 45.111, + "args": { + "External id": 4048455,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 6366 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_2", "pid": 1336756, "tid": 1336756, + "ts": 1655273827975.271, "dur": 67.337, + "args": { + "External id": 4048456,"kernel_hash": "ckbsutlugbs4qoncxuwq6kkwome3xojo3ke4p7z74lcl5h4q62to", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "2048", "1", "9.9999999999999995e-07", "True", "2048", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/kb/ckbsutlugbs4qoncxuwq6kkwome3xojo3ke4p7z74lcl5h4q62to.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [1], [2048, 1], [2048, 1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [65536, 2048], [2048], [65536, 2048], [65536, 2048], [65536], [], [], [], [], [], [], [], [], []], "Ev Idx": 6367 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655273828053.513, "dur": 44.979, + "args": { + "External id": 4048457,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [5632, 1]], "Input Dims": [[65536, 2048], [2048, 5632], [65536, 5632]], "Ev Idx": 6368 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655273828107.088, "dur": 35.632, + "args": { + "External id": 4048458,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [5632, 1]], "Input Dims": [[65536, 2048], [2048, 5632], [65536, 5632]], "Ev Idx": 6369 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 1336756, "tid": 1336756, + "ts": 1655273828162.668, "dur": 24.753, + "args": { + "External id": 4048459,"kernel_hash": "cgh2wg2b6li2ipjwrhdr326ycb37fu4v576nwebfoyhwx5kppapn", "grid": "grid(369098752,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "369098752"], "kernel_file": "/tmp/torchinductor_cvm/gh/cgh2wg2b6li2ipjwrhdr326ycb37fu4v576nwebfoyhwx5kppapn.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[5632, 1], [5632, 1], [23068672, 5632, 1], []], "Input Dims": [[65536, 5632], [65536, 5632], [16, 4096, 5632], []], "Ev Idx": 6370 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655273828192.799, "dur": 34.858, + "args": { + "External id": 4048460,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [1, 5632], [2048, 1]], "Input Dims": [[65536, 5632], [5632, 2048], [65536, 2048]], "Ev Idx": 6371 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 1336756, "tid": 1336756, + "ts": 1655273828247.974, "dur": 16.305, + "args": { + "External id": 4048461,"kernel_hash": "cta7vcczabyyuqarwmn4dcnazkxudhfwrvnick7ql5cmsd5lz4rz", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/ta/cta7vcczabyyuqarwmn4dcnazkxudhfwrvnick7ql5cmsd5lz4rz.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[8388608, 2048, 1], [2048, 1], []], "Input Dims": [[16, 4096, 2048], [65536, 2048], []], "Ev Idx": 6372 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.4)", "pid": 1336756, "tid": 1336756, + "ts": 1655273828409.026, "dur": 90.379, + "args": { + "External id": 4048462,"Record function id": 0, "Ev Idx": 6373 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 1336756, "tid": 1336756, + "ts": 1655273828573.914, "dur": 47.503, + "args": { + "External id": 4048463,"Record function id": 0, "Ev Idx": 6374 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.5)", "pid": 1336756, "tid": 1336756, + "ts": 1655273828630.511, "dur": 18385.226, + "args": { + "External id": 4048464,"Record function id": 0, "Ev Idx": 6375 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.5)", "pid": 1336756, "tid": 1336756, + "ts": 1655273828638.272, "dur": 875.329, + "args": { + "External id": 4048465,"Record function id": 0, "Ev Idx": 6376 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655273828712.813, "dur": 8.555, + "args": { + "External id": 4048466,"Record function id": 0, "Concrete Inputs": ["[6423040]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6377 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336756, "tid": 1336756, + "ts": 1655273828734.004, "dur": 33.798, + "args": { + "External id": 4048467,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 6378 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273828739.314, "dur": 2.190, + "args": { + "External id": 4048468,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6379 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273828745.632, "dur": 0.406, + "args": { + "External id": 4048469,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6380 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273828747.922, "dur": 0.238, + "args": { + "External id": 4048470,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6381 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273828749.358, "dur": 0.363, + "args": { + "External id": 4048471,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6382 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273828752.368, "dur": 0.369, + "args": { + "External id": 4048472,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6383 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273828753.844, "dur": 0.164, + "args": { + "External id": 4048473,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6384 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273828755.847, "dur": 2.517, + "args": { + "External id": 4048474,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6385 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273828759.788, "dur": 0.376, + "args": { + "External id": 4048475,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6386 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273828761.585, "dur": 0.303, + "args": { + "External id": 4048476,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6387 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336756, "tid": 1336756, + "ts": 1655273828777.321, "dur": 37.329, + "args": { + "External id": 4048477,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 6388 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 1336756, "tid": 1336756, + "ts": 1655273828847.114, "dur": 104.938, + "args": { + "External id": 4048478,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "6423040", "8", "3", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [], [], [], [], [], []], "Ev Idx": 6389 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655273828858.310, "dur": 3.389, + "args": { + "External id": 4048479,"Record function id": 0, "Concrete Inputs": ["[51384320]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6390 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 1336756, "tid": 1336756, + "ts": 1655273828866.805, "dur": 9.909, + "args": { + "External id": 4048480,"Record function id": 0, "Concrete Inputs": ["", "0", "19269120", "6423040"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 6391 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1336756, + "ts": 1655273828871.092, "dur": 5.231, + "args": { + "External id": 4048481,"Record function id": 0, "Concrete Inputs": ["", "0", "19269120", "25692160", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[51384320], [], [], [], []], "Ev Idx": 6392 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273828874.713, "dur": 0.479, + "args": { + "External id": 4048482,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "[1]", "19269120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 6393 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336756, "tid": 1336756, + "ts": 1655273828882.931, "dur": 27.527, + "args": { + "External id": 4048483,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 6394 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273828884.807, "dur": 2.029, + "args": { + "External id": 4048484,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "19269120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6395 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273828888.547, "dur": 0.348, + "args": { + "External id": 4048485,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "19269376"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6396 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273828890.183, "dur": 0.192, + "args": { + "External id": 4048486,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "19793664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6397 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273828893.816, "dur": 1.311, + "args": { + "External id": 4048487,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "20317952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6398 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273828896.443, "dur": 0.156, + "args": { + "External id": 4048488,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "20842240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6399 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273828898.016, "dur": 0.313, + "args": { + "External id": 4048489,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "21366528"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6400 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273828901.466, "dur": 0.254, + "args": { + "External id": 4048490,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "21366784"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6401 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273828902.852, "dur": 0.264, + "args": { + "External id": 4048491,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "22808576"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6402 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273828904.363, "dur": 1.875, + "args": { + "External id": 4048492,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "24250368"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6403 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336756, "tid": 1336756, + "ts": 1655273828922.289, "dur": 21.969, + "args": { + "External id": 4048493,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 6404 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 1336756, "tid": 1336756, + "ts": 1655273829049.023, "dur": 353.598, + "args": { + "External id": 4048494,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[51384320], [6423040], [], [], []], "Ev Idx": 6405 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336756, "tid": 1336756, + "ts": 1655273829082.939, "dur": 315.059, + "args": { + "External id": 4048495,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 3, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "3", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 51384320, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[6423040], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 6406, "In msg nelems": 6423040 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 1336756, "tid": 1336756, + "ts": 1655273829099.866, "dur": 293.105, + "args": { + "External id": 4048496,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[6423040]], "Ev Idx": 6407 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336756, "tid": 1336756, + "ts": 1655273829441.401, "dur": 3.305, + "args": { + "External id": 4048497,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "3", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 6408, "In msg nelems": 0, "Rank": 3, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.5)", "pid": 1336756, "tid": 1336756, + "ts": 1655273829533.304, "dur": 17276.778, + "args": { + "External id": 4048498,"Record function id": 0, "Ev Idx": 6409 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655273829622.451, "dur": 6.307, + "args": { + "External id": 4048499,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[51384320], []], "Ev Idx": 6410 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655273829632.624, "dur": 0.954, + "args": { + "External id": 4048500,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 6411 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655273829635.208, "dur": 1.742, + "args": { + "External id": 4048501,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 6412 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655273829638.682, "dur": 0.698, + "args": { + "External id": 4048502,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 6413 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655273829640.687, "dur": 0.939, + "args": { + "External id": 4048503,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 6414 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655273829644.432, "dur": 0.603, + "args": { + "External id": 4048504,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 6415 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655273829646.526, "dur": 0.711, + "args": { + "External id": 4048505,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 6416 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655273829648.719, "dur": 1.722, + "args": { + "External id": 4048506,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 6417 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655273829652.084, "dur": 0.787, + "args": { + "External id": 4048507,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 6418 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655273829655.714, "dur": 0.541, + "args": { + "External id": 4048508,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 6419 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 1336756, "tid": 1336756, + "ts": 1655273829673.946, "dur": 17091.244, + "args": { + "External id": 4048509,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 6420 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 1336756, "tid": 1336756, + "ts": 1655273829695.500, "dur": 17063.133, + "args": { + "External id": 4048510,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 6421 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655273829714.674, "dur": 12.049, + "args": { + "External id": 4048511,"Record function id": 0, "Concrete Inputs": ["[2133]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6422 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655273829729.566, "dur": 16998.019, + "args": { + "External id": 4048512,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], [], []], "Ev Idx": 6423 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336756, "tid": 1336756, + "ts": 1655273829732.083, "dur": 16994.992, + "args": { + "External id": 4048513,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], []], "Ev Idx": 6424 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273829738.184, "dur": 4.447, + "args": { + "External id": 4048514,"Record function id": 0, "Concrete Inputs": ["[2133]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6425 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1336756, + "ts": 1655273829744.359, "dur": 16979.856, + "args": { + "External id": 4048515,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[2133], [2133], []], "Ev Idx": 6426 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 1336756, "tid": 1336756, + "ts": 1655273846934.944, "dur": 26.854, + "args": { + "External id": 4048516,"Sequence number": 40618363, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 6427 + } + }, + { + "ph": "s", "id": 217, "pid": 1336756, "tid": 1336756, "ts": 1655273846934.944, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 1336756, "tid": 1336756, + "ts": 1655273846949.861, "dur": 7.591, + "args": { + "External id": 4048517,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[8388608, 2048, 1], [8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048], [16, 4096, 2048]], "Ev Idx": 6428 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655273846953.005, "dur": 4.170, + "args": { + "External id": 4048518,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 6429 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 1336756, "tid": 1336756, + "ts": 1655273847054.347, "dur": 73.547, + "args": { + "External id": 4048519,"Record function id": 0, "Ev Idx": 6430 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 1336756, "tid": 1336756, + "ts": 1655273847129.630, "dur": 1032.512, + "args": { + "External id": 4048520,"Record function id": 0, "Ev Idx": 6431 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 1336756, "tid": 1336756, + "ts": 1655273847167.350, "dur": 982.508, + "args": { + "External id": 4048521,"Sequence number": 40618364, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[8388608, 2048, 1], [1], [2048, 1], [2048, 1], [2048, 1], [32, 1], [32, 1], [2048, 1], [1], [2048, 1], [2048, 1], [5632, 1]], "Input Dims": [[16, 4096, 2048], [2048], [2048, 2048], [2048, 2048], [2048, 2048], [8192, 32], [8192, 32], [2048, 2048], [2048], [5632, 2048], [5632, 2048], [2048, 5632]], "Ev Idx": 6432 + } + }, + { + "ph": "s", "id": 216, "pid": 1336756, "tid": 1336756, "ts": 1655273847167.350, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 1336756, "tid": 1336756, + "ts": 1655273847229.411, "dur": 42.377, + "args": { + "External id": 4048522,"kernel_hash": "cd26ogptnjelaibpl2zumx5nxdttspqepvjkh7lpmsxbzrrexbxm", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "2048", "1", "9.9999999999999995e-07", "True", "2048", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/d2/cd26ogptnjelaibpl2zumx5nxdttspqepvjkh7lpmsxbzrrexbxm.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [65536, 2048], [2048], [65536], [], [], [], [], [], [], [], [], []], "Ev Idx": 6433 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655273847283.436, "dur": 102.696, + "args": { + "External id": 4048523,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 6434 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655273847395.264, "dur": 53.087, + "args": { + "External id": 4048524,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 6435 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655273847460.683, "dur": 33.877, + "args": { + "External id": 4048525,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 6436 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336756, "tid": 1336756, + "ts": 1655273847517.995, "dur": 25.422, + "args": { + "External id": 4048526,"kernel_hash": "cahe5odluo4swiyj4n2lohwh57qg5lym5qsijyjsjca7pvto5oka", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/ah/cahe5odluo4swiyj4n2lohwh57qg5lym5qsijyjsjca7pvto5oka.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 6437 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336756, "tid": 1336756, + "ts": 1655273847561.397, "dur": 12.847, + "args": { + "External id": 4048527,"kernel_hash": "cahe5odluo4swiyj4n2lohwh57qg5lym5qsijyjsjca7pvto5oka", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/ah/cahe5odluo4swiyj4n2lohwh57qg5lym5qsijyjsjca7pvto5oka.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 6438 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 1336756, "tid": 1336756, + "ts": 1655273847591.957, "dur": 128.417, + "args": { + "External id": 4048528,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.125", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [], [], [], [], [], [], [], []], "Ev Idx": 6439 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336756, "tid": 1336756, + "ts": 1655273847639.525, "dur": 11.451, + "args": { + "External id": 4048529,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[8388608, 2048, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [], [], [], [], []], "Ev Idx": 6440 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273847644.417, "dur": 5.848, + "args": { + "External id": 4048530,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "[8388608, 2048, 64, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6441 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655273847653.650, "dur": 4.272, + "args": { + "External id": 4048531,"Record function id": 0, "Concrete Inputs": ["[16, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6442 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655273847659.271, "dur": 0.864, + "args": { + "External id": 4048532,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6443 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655273847667.623, "dur": 3.253, + "args": { + "External id": 4048533,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6444 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655273847731.066, "dur": 44.270, + "args": { + "External id": 4048534,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 6445 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_2", "pid": 1336756, "tid": 1336756, + "ts": 1655273847804.814, "dur": 26.872, + "args": { + "External id": 4048535,"kernel_hash": "ckbsutlugbs4qoncxuwq6kkwome3xojo3ke4p7z74lcl5h4q62to", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "2048", "1", "9.9999999999999995e-07", "True", "2048", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/kb/ckbsutlugbs4qoncxuwq6kkwome3xojo3ke4p7z74lcl5h4q62to.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [1], [2048, 1], [2048, 1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [65536, 2048], [2048], [65536, 2048], [65536, 2048], [65536], [], [], [], [], [], [], [], [], []], "Ev Idx": 6446 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655273847839.138, "dur": 40.942, + "args": { + "External id": 4048536,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [5632, 1]], "Input Dims": [[65536, 2048], [2048, 5632], [65536, 5632]], "Ev Idx": 6447 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655273847887.841, "dur": 35.384, + "args": { + "External id": 4048537,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [5632, 1]], "Input Dims": [[65536, 2048], [2048, 5632], [65536, 5632]], "Ev Idx": 6448 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 1336756, "tid": 1336756, + "ts": 1655273847943.147, "dur": 21.944, + "args": { + "External id": 4048538,"kernel_hash": "cgh2wg2b6li2ipjwrhdr326ycb37fu4v576nwebfoyhwx5kppapn", "grid": "grid(369098752,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "369098752"], "kernel_file": "/tmp/torchinductor_cvm/gh/cgh2wg2b6li2ipjwrhdr326ycb37fu4v576nwebfoyhwx5kppapn.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[5632, 1], [5632, 1], [23068672, 5632, 1], []], "Input Dims": [[65536, 5632], [65536, 5632], [16, 4096, 5632], []], "Ev Idx": 6449 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655273847970.052, "dur": 73.045, + "args": { + "External id": 4048539,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [1, 5632], [2048, 1]], "Input Dims": [[65536, 5632], [5632, 2048], [65536, 2048]], "Ev Idx": 6450 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 1336756, "tid": 1336756, + "ts": 1655273848067.430, "dur": 19.332, + "args": { + "External id": 4048540,"kernel_hash": "cta7vcczabyyuqarwmn4dcnazkxudhfwrvnick7ql5cmsd5lz4rz", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/ta/cta7vcczabyyuqarwmn4dcnazkxudhfwrvnick7ql5cmsd5lz4rz.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[8388608, 2048, 1], [2048, 1], []], "Input Dims": [[16, 4096, 2048], [65536, 2048], []], "Ev Idx": 6451 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.5)", "pid": 1336756, "tid": 1336756, + "ts": 1655273848224.704, "dur": 70.345, + "args": { + "External id": 4048541,"Record function id": 0, "Ev Idx": 6452 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 1336756, "tid": 1336756, + "ts": 1655273848364.839, "dur": 44.205, + "args": { + "External id": 4048542,"Record function id": 0, "Ev Idx": 6453 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.6)", "pid": 1336756, "tid": 1336756, + "ts": 1655273848434.183, "dur": 17837.512, + "args": { + "External id": 4048543,"Record function id": 0, "Ev Idx": 6454 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.6)", "pid": 1336756, "tid": 1336756, + "ts": 1655273848442.904, "dur": 839.910, + "args": { + "External id": 4048544,"Record function id": 0, "Ev Idx": 6455 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655273848518.465, "dur": 8.142, + "args": { + "External id": 4048545,"Record function id": 0, "Concrete Inputs": ["[6423040]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6456 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336756, "tid": 1336756, + "ts": 1655273848539.741, "dur": 33.155, + "args": { + "External id": 4048546,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 6457 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273848544.704, "dur": 2.133, + "args": { + "External id": 4048547,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6458 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273848550.621, "dur": 0.243, + "args": { + "External id": 4048548,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6459 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273848552.250, "dur": 0.420, + "args": { + "External id": 4048549,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6460 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273848553.998, "dur": 0.301, + "args": { + "External id": 4048550,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6461 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273848557.319, "dur": 0.251, + "args": { + "External id": 4048551,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6462 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273848558.859, "dur": 0.256, + "args": { + "External id": 4048552,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6463 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273848560.736, "dur": 2.611, + "args": { + "External id": 4048553,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6464 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273848564.671, "dur": 0.180, + "args": { + "External id": 4048554,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6465 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273848566.176, "dur": 0.147, + "args": { + "External id": 4048555,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6466 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336756, "tid": 1336756, + "ts": 1655273848582.719, "dur": 37.115, + "args": { + "External id": 4048556,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 6467 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 1336756, "tid": 1336756, + "ts": 1655273848653.294, "dur": 101.259, + "args": { + "External id": 4048557,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "6423040", "8", "3", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [], [], [], [], [], []], "Ev Idx": 6468 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655273848665.102, "dur": 3.362, + "args": { + "External id": 4048558,"Record function id": 0, "Concrete Inputs": ["[51384320]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6469 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 1336756, "tid": 1336756, + "ts": 1655273848673.546, "dur": 9.725, + "args": { + "External id": 4048559,"Record function id": 0, "Concrete Inputs": ["", "0", "19269120", "6423040"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 6470 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1336756, + "ts": 1655273848677.825, "dur": 5.071, + "args": { + "External id": 4048560,"Record function id": 0, "Concrete Inputs": ["", "0", "19269120", "25692160", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[51384320], [], [], [], []], "Ev Idx": 6471 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273848681.463, "dur": 0.336, + "args": { + "External id": 4048561,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "[1]", "19269120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 6472 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336756, "tid": 1336756, + "ts": 1655273848689.188, "dur": 26.588, + "args": { + "External id": 4048562,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 6473 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273848691.145, "dur": 1.932, + "args": { + "External id": 4048563,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "19269120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6474 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273848694.529, "dur": 0.396, + "args": { + "External id": 4048564,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "19269376"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6475 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273848696.291, "dur": 0.371, + "args": { + "External id": 4048565,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "19793664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6476 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273848699.807, "dur": 1.229, + "args": { + "External id": 4048566,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "20317952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6477 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273848702.386, "dur": 0.253, + "args": { + "External id": 4048567,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "20842240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6478 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273848704.329, "dur": 0.275, + "args": { + "External id": 4048568,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "21366528"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6479 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273848707.530, "dur": 0.263, + "args": { + "External id": 4048569,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "21366784"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6480 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273848708.867, "dur": 0.504, + "args": { + "External id": 4048570,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "22808576"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6481 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273848710.409, "dur": 1.786, + "args": { + "External id": 4048571,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "24250368"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6482 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336756, "tid": 1336756, + "ts": 1655273848725.558, "dur": 21.357, + "args": { + "External id": 4048572,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 6483 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 1336756, "tid": 1336756, + "ts": 1655273848805.796, "dur": 382.994, + "args": { + "External id": 4048573,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[51384320], [6423040], [], [], []], "Ev Idx": 6484 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336756, "tid": 1336756, + "ts": 1655273848836.139, "dur": 347.621, + "args": { + "External id": 4048574,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 3, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "3", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 51384320, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[6423040], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 6485, "In msg nelems": 6423040 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 1336756, "tid": 1336756, + "ts": 1655273848847.032, "dur": 330.578, + "args": { + "External id": 4048575,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[6423040]], "Ev Idx": 6486 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336756, "tid": 1336756, + "ts": 1655273849212.325, "dur": 2.716, + "args": { + "External id": 4048576,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "3", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 6487, "In msg nelems": 0, "Rank": 3, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.6)", "pid": 1336756, "tid": 1336756, + "ts": 1655273849302.165, "dur": 16790.727, + "args": { + "External id": 4048577,"Record function id": 0, "Ev Idx": 6488 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655273849393.175, "dur": 5.960, + "args": { + "External id": 4048578,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[51384320], []], "Ev Idx": 6489 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655273849403.115, "dur": 0.840, + "args": { + "External id": 4048579,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 6490 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655273849405.705, "dur": 1.639, + "args": { + "External id": 4048580,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 6491 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655273849408.862, "dur": 0.864, + "args": { + "External id": 4048581,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 6492 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655273849411.152, "dur": 0.606, + "args": { + "External id": 4048582,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 6493 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655273849413.335, "dur": 0.646, + "args": { + "External id": 4048583,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 6494 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655273849435.290, "dur": 1.332, + "args": { + "External id": 4048584,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 6495 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655273849438.933, "dur": 1.525, + "args": { + "External id": 4048585,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 6496 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655273849441.683, "dur": 0.445, + "args": { + "External id": 4048586,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 6497 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655273849443.515, "dur": 0.514, + "args": { + "External id": 4048587,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 6498 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 1336756, "tid": 1336756, + "ts": 1655273849464.776, "dur": 16584.274, + "args": { + "External id": 4048588,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 6499 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 1336756, "tid": 1336756, + "ts": 1655273849479.448, "dur": 16563.263, + "args": { + "External id": 4048589,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 6500 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655273849501.283, "dur": 12.530, + "args": { + "External id": 4048590,"Record function id": 0, "Concrete Inputs": ["[2133]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6501 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655273849516.674, "dur": 16494.459, + "args": { + "External id": 4048591,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], [], []], "Ev Idx": 6502 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336756, "tid": 1336756, + "ts": 1655273849519.096, "dur": 16491.520, + "args": { + "External id": 4048592,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], []], "Ev Idx": 6503 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273849524.669, "dur": 5.495, + "args": { + "External id": 4048593,"Record function id": 0, "Concrete Inputs": ["[2133]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6504 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1336756, + "ts": 1655273849531.706, "dur": 16476.219, + "args": { + "External id": 4048594,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[2133], [2133], []], "Ev Idx": 6505 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 1336756, "tid": 1336756, + "ts": 1655273866220.301, "dur": 26.496, + "args": { + "External id": 4048595,"Sequence number": 40618365, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 6506 + } + }, + { + "ph": "s", "id": 215, "pid": 1336756, "tid": 1336756, "ts": 1655273866220.301, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 1336756, "tid": 1336756, + "ts": 1655273866235.457, "dur": 6.867, + "args": { + "External id": 4048596,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[8388608, 2048, 1], [8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048], [16, 4096, 2048]], "Ev Idx": 6507 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655273866238.383, "dur": 3.680, + "args": { + "External id": 4048597,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 6508 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 1336756, "tid": 1336756, + "ts": 1655273866308.490, "dur": 74.198, + "args": { + "External id": 4048598,"Record function id": 0, "Ev Idx": 6509 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 1336756, "tid": 1336756, + "ts": 1655273866384.245, "dur": 1046.953, + "args": { + "External id": 4048599,"Record function id": 0, "Ev Idx": 6510 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 1336756, "tid": 1336756, + "ts": 1655273866436.894, "dur": 967.549, + "args": { + "External id": 4048600,"Sequence number": 40618366, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[8388608, 2048, 1], [1], [2048, 1], [2048, 1], [2048, 1], [32, 1], [32, 1], [2048, 1], [1], [2048, 1], [2048, 1], [5632, 1]], "Input Dims": [[16, 4096, 2048], [2048], [2048, 2048], [2048, 2048], [2048, 2048], [8192, 32], [8192, 32], [2048, 2048], [2048], [5632, 2048], [5632, 2048], [2048, 5632]], "Ev Idx": 6511 + } + }, + { + "ph": "s", "id": 214, "pid": 1336756, "tid": 1336756, "ts": 1655273866436.894, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 1336756, "tid": 1336756, + "ts": 1655273866501.300, "dur": 41.613, + "args": { + "External id": 4048601,"kernel_hash": "cd26ogptnjelaibpl2zumx5nxdttspqepvjkh7lpmsxbzrrexbxm", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "2048", "1", "9.9999999999999995e-07", "True", "2048", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/d2/cd26ogptnjelaibpl2zumx5nxdttspqepvjkh7lpmsxbzrrexbxm.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [65536, 2048], [2048], [65536], [], [], [], [], [], [], [], [], []], "Ev Idx": 6512 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655273866555.295, "dur": 102.376, + "args": { + "External id": 4048602,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 6513 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655273866666.081, "dur": 38.985, + "args": { + "External id": 4048603,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 6514 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655273866713.065, "dur": 31.595, + "args": { + "External id": 4048604,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 6515 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336756, "tid": 1336756, + "ts": 1655273866767.168, "dur": 22.596, + "args": { + "External id": 4048605,"kernel_hash": "cahe5odluo4swiyj4n2lohwh57qg5lym5qsijyjsjca7pvto5oka", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/ah/cahe5odluo4swiyj4n2lohwh57qg5lym5qsijyjsjca7pvto5oka.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 6516 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336756, "tid": 1336756, + "ts": 1655273866806.250, "dur": 14.093, + "args": { + "External id": 4048606,"kernel_hash": "cahe5odluo4swiyj4n2lohwh57qg5lym5qsijyjsjca7pvto5oka", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/ah/cahe5odluo4swiyj4n2lohwh57qg5lym5qsijyjsjca7pvto5oka.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 6517 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 1336756, "tid": 1336756, + "ts": 1655273866837.694, "dur": 122.755, + "args": { + "External id": 4048607,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.125", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [], [], [], [], [], [], [], []], "Ev Idx": 6518 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336756, "tid": 1336756, + "ts": 1655273866886.321, "dur": 10.025, + "args": { + "External id": 4048608,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[8388608, 2048, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [], [], [], [], []], "Ev Idx": 6519 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273866890.988, "dur": 4.657, + "args": { + "External id": 4048609,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "[8388608, 2048, 64, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6520 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655273866898.808, "dur": 5.504, + "args": { + "External id": 4048610,"Record function id": 0, "Concrete Inputs": ["[16, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6521 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655273866905.648, "dur": 0.962, + "args": { + "External id": 4048611,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6522 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655273866909.014, "dur": 2.997, + "args": { + "External id": 4048612,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6523 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655273866970.260, "dur": 90.554, + "args": { + "External id": 4048613,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 6524 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_2", "pid": 1336756, "tid": 1336756, + "ts": 1655273867094.916, "dur": 28.589, + "args": { + "External id": 4048614,"kernel_hash": "ckbsutlugbs4qoncxuwq6kkwome3xojo3ke4p7z74lcl5h4q62to", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "2048", "1", "9.9999999999999995e-07", "True", "2048", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/kb/ckbsutlugbs4qoncxuwq6kkwome3xojo3ke4p7z74lcl5h4q62to.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [1], [2048, 1], [2048, 1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [65536, 2048], [2048], [65536, 2048], [65536, 2048], [65536], [], [], [], [], [], [], [], [], []], "Ev Idx": 6525 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655273867131.832, "dur": 43.052, + "args": { + "External id": 4048615,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [5632, 1]], "Input Dims": [[65536, 2048], [2048, 5632], [65536, 5632]], "Ev Idx": 6526 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655273867181.990, "dur": 34.819, + "args": { + "External id": 4048616,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [5632, 1]], "Input Dims": [[65536, 2048], [2048, 5632], [65536, 5632]], "Ev Idx": 6527 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 1336756, "tid": 1336756, + "ts": 1655273867238.591, "dur": 25.417, + "args": { + "External id": 4048617,"kernel_hash": "cgh2wg2b6li2ipjwrhdr326ycb37fu4v576nwebfoyhwx5kppapn", "grid": "grid(369098752,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "369098752"], "kernel_file": "/tmp/torchinductor_cvm/gh/cgh2wg2b6li2ipjwrhdr326ycb37fu4v576nwebfoyhwx5kppapn.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[5632, 1], [5632, 1], [23068672, 5632, 1], []], "Input Dims": [[65536, 5632], [65536, 5632], [16, 4096, 5632], []], "Ev Idx": 6528 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655273867269.479, "dur": 33.945, + "args": { + "External id": 4048618,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [1, 5632], [2048, 1]], "Input Dims": [[65536, 5632], [5632, 2048], [65536, 2048]], "Ev Idx": 6529 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 1336756, "tid": 1336756, + "ts": 1655273867321.870, "dur": 16.609, + "args": { + "External id": 4048619,"kernel_hash": "cta7vcczabyyuqarwmn4dcnazkxudhfwrvnick7ql5cmsd5lz4rz", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/ta/cta7vcczabyyuqarwmn4dcnazkxudhfwrvnick7ql5cmsd5lz4rz.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[8388608, 2048, 1], [2048, 1], []], "Input Dims": [[16, 4096, 2048], [65536, 2048], []], "Ev Idx": 6530 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.6)", "pid": 1336756, "tid": 1336756, + "ts": 1655273867497.558, "dur": 71.717, + "args": { + "External id": 4048620,"Record function id": 0, "Ev Idx": 6531 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 1336756, "tid": 1336756, + "ts": 1655273867639.099, "dur": 44.962, + "args": { + "External id": 4048621,"Record function id": 0, "Ev Idx": 6532 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.7)", "pid": 1336756, "tid": 1336756, + "ts": 1655273867692.717, "dur": 17903.448, + "args": { + "External id": 4048622,"Record function id": 0, "Ev Idx": 6533 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.7)", "pid": 1336756, "tid": 1336756, + "ts": 1655273867699.707, "dur": 844.568, + "args": { + "External id": 4048623,"Record function id": 0, "Ev Idx": 6534 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655273867769.857, "dur": 7.722, + "args": { + "External id": 4048624,"Record function id": 0, "Concrete Inputs": ["[6423040]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6535 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336756, "tid": 1336756, + "ts": 1655273867790.522, "dur": 31.812, + "args": { + "External id": 4048625,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 6536 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273867795.489, "dur": 2.286, + "args": { + "External id": 4048626,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6537 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273867801.292, "dur": 0.271, + "args": { + "External id": 4048627,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6538 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273867802.622, "dur": 0.313, + "args": { + "External id": 4048628,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6539 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273867803.854, "dur": 0.436, + "args": { + "External id": 4048629,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6540 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273867807.040, "dur": 0.338, + "args": { + "External id": 4048630,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6541 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273867808.580, "dur": 0.537, + "args": { + "External id": 4048631,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6542 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273867810.622, "dur": 3.019, + "args": { + "External id": 4048632,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6543 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273867814.742, "dur": 0.330, + "args": { + "External id": 4048633,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6544 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273867816.124, "dur": 0.292, + "args": { + "External id": 4048634,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6545 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336756, "tid": 1336756, + "ts": 1655273867832.336, "dur": 36.813, + "args": { + "External id": 4048635,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 6546 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 1336756, "tid": 1336756, + "ts": 1655273867900.758, "dur": 142.974, + "args": { + "External id": 4048636,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "6423040", "8", "3", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [], [], [], [], [], []], "Ev Idx": 6547 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655273867912.648, "dur": 3.305, + "args": { + "External id": 4048637,"Record function id": 0, "Concrete Inputs": ["[51384320]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6548 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 1336756, "tid": 1336756, + "ts": 1655273867920.945, "dur": 9.817, + "args": { + "External id": 4048638,"Record function id": 0, "Concrete Inputs": ["", "0", "19269120", "6423040"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 6549 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1336756, + "ts": 1655273867925.133, "dur": 5.249, + "args": { + "External id": 4048639,"Record function id": 0, "Concrete Inputs": ["", "0", "19269120", "25692160", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[51384320], [], [], [], []], "Ev Idx": 6550 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273867928.601, "dur": 0.565, + "args": { + "External id": 4048640,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "[1]", "19269120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 6551 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336756, "tid": 1336756, + "ts": 1655273867936.819, "dur": 25.344, + "args": { + "External id": 4048641,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 6552 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273867938.366, "dur": 2.104, + "args": { + "External id": 4048642,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "19269120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6553 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273867941.886, "dur": 0.389, + "args": { + "External id": 4048643,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "19269376"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6554 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273867943.425, "dur": 0.320, + "args": { + "External id": 4048644,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "19793664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6555 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273867946.689, "dur": 1.003, + "args": { + "External id": 4048645,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "20317952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6556 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273867948.577, "dur": 0.265, + "args": { + "External id": 4048646,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "20842240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6557 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273867949.914, "dur": 0.332, + "args": { + "External id": 4048647,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "21366528"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6558 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273867953.210, "dur": 0.313, + "args": { + "External id": 4048648,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "21366784"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6559 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273867954.741, "dur": 0.170, + "args": { + "External id": 4048649,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "22808576"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6560 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273867956.718, "dur": 1.683, + "args": { + "External id": 4048650,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "24250368"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6561 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336756, "tid": 1336756, + "ts": 1655273867971.675, "dur": 62.239, + "args": { + "External id": 4048651,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 6562 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 1336756, "tid": 1336756, + "ts": 1655273868101.127, "dur": 349.862, + "args": { + "External id": 4048652,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[51384320], [6423040], [], [], []], "Ev Idx": 6563 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336756, "tid": 1336756, + "ts": 1655273868130.914, "dur": 315.000, + "args": { + "External id": 4048653,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 3, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "3", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 51384320, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[6423040], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 6564, "In msg nelems": 6423040 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 1336756, "tid": 1336756, + "ts": 1655273868141.080, "dur": 298.844, + "args": { + "External id": 4048654,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[6423040]], "Ev Idx": 6565 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336756, "tid": 1336756, + "ts": 1655273868474.556, "dur": 2.622, + "args": { + "External id": 4048655,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "3", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 6566, "In msg nelems": 0, "Rank": 3, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.7)", "pid": 1336756, "tid": 1336756, + "ts": 1655273868564.251, "dur": 16840.057, + "args": { + "External id": 4048656,"Record function id": 0, "Ev Idx": 6567 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655273868655.017, "dur": 5.737, + "args": { + "External id": 4048657,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[51384320], []], "Ev Idx": 6568 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655273868664.745, "dur": 0.885, + "args": { + "External id": 4048658,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 6569 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655273868667.419, "dur": 1.813, + "args": { + "External id": 4048659,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 6570 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655273868676.249, "dur": 0.791, + "args": { + "External id": 4048660,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 6571 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655273868678.501, "dur": 0.936, + "args": { + "External id": 4048661,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 6572 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655273868680.857, "dur": 0.574, + "args": { + "External id": 4048662,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 6573 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655273868684.187, "dur": 0.743, + "args": { + "External id": 4048663,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 6574 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655273868686.203, "dur": 1.689, + "args": { + "External id": 4048664,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 6575 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655273868689.303, "dur": 0.515, + "args": { + "External id": 4048665,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 6576 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655273868691.218, "dur": 0.558, + "args": { + "External id": 4048666,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 6577 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 1336756, "tid": 1336756, + "ts": 1655273868712.092, "dur": 16647.224, + "args": { + "External id": 4048667,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 6578 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 1336756, "tid": 1336756, + "ts": 1655273868726.520, "dur": 16625.991, + "args": { + "External id": 4048668,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 6579 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655273868744.711, "dur": 13.498, + "args": { + "External id": 4048669,"Record function id": 0, "Concrete Inputs": ["[2133]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6580 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655273868761.258, "dur": 16560.828, + "args": { + "External id": 4048670,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], [], []], "Ev Idx": 6581 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336756, "tid": 1336756, + "ts": 1655273868763.454, "dur": 16558.106, + "args": { + "External id": 4048671,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], []], "Ev Idx": 6582 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273868768.374, "dur": 4.553, + "args": { + "External id": 4048672,"Record function id": 0, "Concrete Inputs": ["[2133]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6583 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1336756, + "ts": 1655273868774.489, "dur": 16544.349, + "args": { + "External id": 4048673,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[2133], [2133], []], "Ev Idx": 6584 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 1336756, "tid": 1336756, + "ts": 1655273885543.281, "dur": 27.957, + "args": { + "External id": 4048674,"Sequence number": 40618367, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 6585 + } + }, + { + "ph": "s", "id": 213, "pid": 1336756, "tid": 1336756, "ts": 1655273885543.281, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 1336756, "tid": 1336756, + "ts": 1655273885559.374, "dur": 7.307, + "args": { + "External id": 4048675,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[8388608, 2048, 1], [8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048], [16, 4096, 2048]], "Ev Idx": 6586 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655273885562.162, "dur": 4.123, + "args": { + "External id": 4048676,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 6587 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 1336756, "tid": 1336756, + "ts": 1655273885634.111, "dur": 71.626, + "args": { + "External id": 4048677,"Record function id": 0, "Ev Idx": 6588 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 1336756, "tid": 1336756, + "ts": 1655273885707.563, "dur": 1038.970, + "args": { + "External id": 4048678,"Record function id": 0, "Ev Idx": 6589 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 1336756, "tid": 1336756, + "ts": 1655273885747.251, "dur": 987.093, + "args": { + "External id": 4048679,"Sequence number": 40618368, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[8388608, 2048, 1], [1], [2048, 1], [2048, 1], [2048, 1], [32, 1], [32, 1], [2048, 1], [1], [2048, 1], [2048, 1], [5632, 1]], "Input Dims": [[16, 4096, 2048], [2048], [2048, 2048], [2048, 2048], [2048, 2048], [8192, 32], [8192, 32], [2048, 2048], [2048], [5632, 2048], [5632, 2048], [2048, 5632]], "Ev Idx": 6590 + } + }, + { + "ph": "s", "id": 212, "pid": 1336756, "tid": 1336756, "ts": 1655273885747.251, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 1336756, "tid": 1336756, + "ts": 1655273885809.792, "dur": 40.028, + "args": { + "External id": 4048680,"kernel_hash": "cd26ogptnjelaibpl2zumx5nxdttspqepvjkh7lpmsxbzrrexbxm", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "2048", "1", "9.9999999999999995e-07", "True", "2048", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/d2/cd26ogptnjelaibpl2zumx5nxdttspqepvjkh7lpmsxbzrrexbxm.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [65536, 2048], [2048], [65536], [], [], [], [], [], [], [], [], []], "Ev Idx": 6591 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655273885861.729, "dur": 107.911, + "args": { + "External id": 4048681,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 6592 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655273885977.924, "dur": 76.507, + "args": { + "External id": 4048682,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 6593 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655273886067.670, "dur": 32.729, + "args": { + "External id": 4048683,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 6594 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336756, "tid": 1336756, + "ts": 1655273886125.254, "dur": 23.412, + "args": { + "External id": 4048684,"kernel_hash": "cahe5odluo4swiyj4n2lohwh57qg5lym5qsijyjsjca7pvto5oka", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/ah/cahe5odluo4swiyj4n2lohwh57qg5lym5qsijyjsjca7pvto5oka.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 6595 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336756, "tid": 1336756, + "ts": 1655273886165.287, "dur": 14.938, + "args": { + "External id": 4048685,"kernel_hash": "cahe5odluo4swiyj4n2lohwh57qg5lym5qsijyjsjca7pvto5oka", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/ah/cahe5odluo4swiyj4n2lohwh57qg5lym5qsijyjsjca7pvto5oka.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 6596 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 1336756, "tid": 1336756, + "ts": 1655273886197.509, "dur": 122.693, + "args": { + "External id": 4048686,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.125", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [], [], [], [], [], [], [], []], "Ev Idx": 6597 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336756, "tid": 1336756, + "ts": 1655273886246.627, "dur": 10.005, + "args": { + "External id": 4048687,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[8388608, 2048, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [], [], [], [], []], "Ev Idx": 6598 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273886251.151, "dur": 4.694, + "args": { + "External id": 4048688,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "[8388608, 2048, 64, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6599 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655273886259.132, "dur": 5.645, + "args": { + "External id": 4048689,"Record function id": 0, "Concrete Inputs": ["[16, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6600 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655273886266.007, "dur": 0.993, + "args": { + "External id": 4048690,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6601 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655273886269.240, "dur": 3.198, + "args": { + "External id": 4048691,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6602 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655273886330.942, "dur": 43.457, + "args": { + "External id": 4048692,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 6603 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_2", "pid": 1336756, "tid": 1336756, + "ts": 1655273886402.035, "dur": 42.094, + "args": { + "External id": 4048693,"kernel_hash": "ckbsutlugbs4qoncxuwq6kkwome3xojo3ke4p7z74lcl5h4q62to", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "2048", "1", "9.9999999999999995e-07", "True", "2048", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/kb/ckbsutlugbs4qoncxuwq6kkwome3xojo3ke4p7z74lcl5h4q62to.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [1], [2048, 1], [2048, 1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [65536, 2048], [2048], [65536, 2048], [65536, 2048], [65536], [], [], [], [], [], [], [], [], []], "Ev Idx": 6604 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655273886455.017, "dur": 44.426, + "args": { + "External id": 4048694,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [5632, 1]], "Input Dims": [[65536, 2048], [2048, 5632], [65536, 5632]], "Ev Idx": 6605 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655273886507.161, "dur": 35.222, + "args": { + "External id": 4048695,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [5632, 1]], "Input Dims": [[65536, 2048], [2048, 5632], [65536, 5632]], "Ev Idx": 6606 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 1336756, "tid": 1336756, + "ts": 1655273886570.324, "dur": 23.919, + "args": { + "External id": 4048696,"kernel_hash": "cgh2wg2b6li2ipjwrhdr326ycb37fu4v576nwebfoyhwx5kppapn", "grid": "grid(369098752,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "369098752"], "kernel_file": "/tmp/torchinductor_cvm/gh/cgh2wg2b6li2ipjwrhdr326ycb37fu4v576nwebfoyhwx5kppapn.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[5632, 1], [5632, 1], [23068672, 5632, 1], []], "Input Dims": [[65536, 5632], [65536, 5632], [16, 4096, 5632], []], "Ev Idx": 6607 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655273886601.356, "dur": 35.079, + "args": { + "External id": 4048697,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [1, 5632], [2048, 1]], "Input Dims": [[65536, 5632], [5632, 2048], [65536, 2048]], "Ev Idx": 6608 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 1336756, "tid": 1336756, + "ts": 1655273886653.397, "dur": 17.919, + "args": { + "External id": 4048698,"kernel_hash": "cta7vcczabyyuqarwmn4dcnazkxudhfwrvnick7ql5cmsd5lz4rz", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/ta/cta7vcczabyyuqarwmn4dcnazkxudhfwrvnick7ql5cmsd5lz4rz.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[8388608, 2048, 1], [2048, 1], []], "Input Dims": [[16, 4096, 2048], [65536, 2048], []], "Ev Idx": 6609 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.7)", "pid": 1336756, "tid": 1336756, + "ts": 1655273886807.849, "dur": 69.680, + "args": { + "External id": 4048699,"Record function id": 0, "Ev Idx": 6610 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 1336756, "tid": 1336756, + "ts": 1655273886948.364, "dur": 87.913, + "args": { + "External id": 4048700,"Record function id": 0, "Ev Idx": 6611 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.8)", "pid": 1336756, "tid": 1336756, + "ts": 1655273887046.681, "dur": 18157.976, + "args": { + "External id": 4048701,"Record function id": 0, "Ev Idx": 6612 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.8)", "pid": 1336756, "tid": 1336756, + "ts": 1655273887055.727, "dur": 841.354, + "args": { + "External id": 4048702,"Record function id": 0, "Ev Idx": 6613 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655273887129.478, "dur": 8.787, + "args": { + "External id": 4048703,"Record function id": 0, "Concrete Inputs": ["[6423040]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6614 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336756, "tid": 1336756, + "ts": 1655273887151.143, "dur": 30.648, + "args": { + "External id": 4048704,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 6615 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273887155.973, "dur": 2.079, + "args": { + "External id": 4048705,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6616 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273887162.239, "dur": 0.271, + "args": { + "External id": 4048706,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6617 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273887163.725, "dur": 0.324, + "args": { + "External id": 4048707,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6618 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273887165.422, "dur": 0.345, + "args": { + "External id": 4048708,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6619 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273887168.375, "dur": 0.138, + "args": { + "External id": 4048709,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6620 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273887169.576, "dur": 0.235, + "args": { + "External id": 4048710,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6621 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273887170.671, "dur": 2.955, + "args": { + "External id": 4048711,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6622 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273887174.663, "dur": 0.171, + "args": { + "External id": 4048712,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6623 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273887175.708, "dur": 0.651, + "args": { + "External id": 4048713,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6624 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336756, "tid": 1336756, + "ts": 1655273887191.636, "dur": 37.931, + "args": { + "External id": 4048714,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 6625 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 1336756, "tid": 1336756, + "ts": 1655273887262.309, "dur": 96.954, + "args": { + "External id": 4048715,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "6423040", "8", "3", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [], [], [], [], [], []], "Ev Idx": 6626 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655273887274.292, "dur": 3.642, + "args": { + "External id": 4048716,"Record function id": 0, "Concrete Inputs": ["[51384320]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6627 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 1336756, "tid": 1336756, + "ts": 1655273887283.048, "dur": 9.685, + "args": { + "External id": 4048717,"Record function id": 0, "Concrete Inputs": ["", "0", "19269120", "6423040"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 6628 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1336756, + "ts": 1655273887287.256, "dur": 5.042, + "args": { + "External id": 4048718,"Record function id": 0, "Concrete Inputs": ["", "0", "19269120", "25692160", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[51384320], [], [], [], []], "Ev Idx": 6629 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273887290.469, "dur": 0.630, + "args": { + "External id": 4048719,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "[1]", "19269120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 6630 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336756, "tid": 1336756, + "ts": 1655273887298.838, "dur": 23.460, + "args": { + "External id": 4048720,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 6631 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273887300.425, "dur": 2.153, + "args": { + "External id": 4048721,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "19269120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6632 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273887303.519, "dur": 0.206, + "args": { + "External id": 4048722,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "19269376"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6633 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273887304.704, "dur": 0.620, + "args": { + "External id": 4048723,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "19793664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6634 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273887308.066, "dur": 1.103, + "args": { + "External id": 4048724,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "20317952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6635 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273887310.343, "dur": 0.327, + "args": { + "External id": 4048725,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "20842240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6636 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273887311.696, "dur": 0.359, + "args": { + "External id": 4048726,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "21366528"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6637 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273887314.142, "dur": 0.421, + "args": { + "External id": 4048727,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "21366784"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6638 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273887315.516, "dur": 0.382, + "args": { + "External id": 4048728,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "22808576"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6639 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273887316.626, "dur": 1.936, + "args": { + "External id": 4048729,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "24250368"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6640 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336756, "tid": 1336756, + "ts": 1655273887330.891, "dur": 20.831, + "args": { + "External id": 4048730,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 6641 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 1336756, "tid": 1336756, + "ts": 1655273887410.819, "dur": 397.259, + "args": { + "External id": 4048731,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[51384320], [6423040], [], [], []], "Ev Idx": 6642 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336756, "tid": 1336756, + "ts": 1655273887456.311, "dur": 346.676, + "args": { + "External id": 4048732,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 3, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "3", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 51384320, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[6423040], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 6643, "In msg nelems": 6423040 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 1336756, "tid": 1336756, + "ts": 1655273887468.163, "dur": 327.700, + "args": { + "External id": 4048733,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[6423040]], "Ev Idx": 6644 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336756, "tid": 1336756, + "ts": 1655273887828.707, "dur": 2.395, + "args": { + "External id": 4048734,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "3", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 6645, "In msg nelems": 0, "Rank": 3, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.8)", "pid": 1336756, "tid": 1336756, + "ts": 1655273887917.150, "dur": 17110.787, + "args": { + "External id": 4048735,"Record function id": 0, "Ev Idx": 6646 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655273888045.647, "dur": 6.772, + "args": { + "External id": 4048736,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[51384320], []], "Ev Idx": 6647 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655273888056.552, "dur": 0.948, + "args": { + "External id": 4048737,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 6648 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655273888058.885, "dur": 1.783, + "args": { + "External id": 4048738,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 6649 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655273888062.508, "dur": 0.809, + "args": { + "External id": 4048739,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 6650 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655273888064.626, "dur": 0.688, + "args": { + "External id": 4048740,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 6651 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655273888066.905, "dur": 0.734, + "args": { + "External id": 4048741,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 6652 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655273888070.744, "dur": 0.624, + "args": { + "External id": 4048742,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 6653 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655273888072.539, "dur": 1.773, + "args": { + "External id": 4048743,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 6654 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655273888075.878, "dur": 0.607, + "args": { + "External id": 4048744,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 6655 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655273888078.048, "dur": 0.489, + "args": { + "External id": 4048745,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 6656 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 1336756, "tid": 1336756, + "ts": 1655273888098.839, "dur": 16863.256, + "args": { + "External id": 4048746,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 6657 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 1336756, "tid": 1336756, + "ts": 1655273888113.816, "dur": 16841.789, + "args": { + "External id": 4048747,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 6658 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655273888136.168, "dur": 13.239, + "args": { + "External id": 4048748,"Record function id": 0, "Concrete Inputs": ["[2133]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6659 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655273888152.480, "dur": 16773.064, + "args": { + "External id": 4048749,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], [], []], "Ev Idx": 6660 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336756, "tid": 1336756, + "ts": 1655273888154.889, "dur": 16770.176, + "args": { + "External id": 4048750,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], []], "Ev Idx": 6661 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273888160.173, "dur": 4.668, + "args": { + "External id": 4048751,"Record function id": 0, "Concrete Inputs": ["[2133]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6662 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1336756, + "ts": 1655273888166.465, "dur": 16755.613, + "args": { + "External id": 4048752,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[2133], [2133], []], "Ev Idx": 6663 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 1336756, "tid": 1336756, + "ts": 1655273905154.507, "dur": 27.185, + "args": { + "External id": 4048753,"Sequence number": 40618369, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 6664 + } + }, + { + "ph": "s", "id": 211, "pid": 1336756, "tid": 1336756, "ts": 1655273905154.507, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 1336756, "tid": 1336756, + "ts": 1655273905169.638, "dur": 7.536, + "args": { + "External id": 4048754,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[8388608, 2048, 1], [8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048], [16, 4096, 2048]], "Ev Idx": 6665 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655273905172.846, "dur": 4.067, + "args": { + "External id": 4048755,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 6666 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 1336756, "tid": 1336756, + "ts": 1655273905241.209, "dur": 74.261, + "args": { + "External id": 4048756,"Record function id": 0, "Ev Idx": 6667 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 1336756, "tid": 1336756, + "ts": 1655273905317.287, "dur": 1031.376, + "args": { + "External id": 4048757,"Record function id": 0, "Ev Idx": 6668 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 1336756, "tid": 1336756, + "ts": 1655273905354.841, "dur": 981.215, + "args": { + "External id": 4048758,"Sequence number": 40618370, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[8388608, 2048, 1], [1], [2048, 1], [2048, 1], [2048, 1], [32, 1], [32, 1], [2048, 1], [1], [2048, 1], [2048, 1], [5632, 1]], "Input Dims": [[16, 4096, 2048], [2048], [2048, 2048], [2048, 2048], [2048, 2048], [8192, 32], [8192, 32], [2048, 2048], [2048], [5632, 2048], [5632, 2048], [2048, 5632]], "Ev Idx": 6669 + } + }, + { + "ph": "s", "id": 210, "pid": 1336756, "tid": 1336756, "ts": 1655273905354.841, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 1336756, "tid": 1336756, + "ts": 1655273905440.070, "dur": 40.883, + "args": { + "External id": 4048759,"kernel_hash": "cd26ogptnjelaibpl2zumx5nxdttspqepvjkh7lpmsxbzrrexbxm", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "2048", "1", "9.9999999999999995e-07", "True", "2048", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/d2/cd26ogptnjelaibpl2zumx5nxdttspqepvjkh7lpmsxbzrrexbxm.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [65536, 2048], [2048], [65536], [], [], [], [], [], [], [], [], []], "Ev Idx": 6670 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655273905497.082, "dur": 105.082, + "args": { + "External id": 4048760,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 6671 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655273905611.362, "dur": 38.875, + "args": { + "External id": 4048761,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 6672 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655273905655.590, "dur": 30.940, + "args": { + "External id": 4048762,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 6673 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336756, "tid": 1336756, + "ts": 1655273905712.766, "dur": 24.030, + "args": { + "External id": 4048763,"kernel_hash": "cahe5odluo4swiyj4n2lohwh57qg5lym5qsijyjsjca7pvto5oka", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/ah/cahe5odluo4swiyj4n2lohwh57qg5lym5qsijyjsjca7pvto5oka.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 6674 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336756, "tid": 1336756, + "ts": 1655273905751.719, "dur": 16.460, + "args": { + "External id": 4048764,"kernel_hash": "cahe5odluo4swiyj4n2lohwh57qg5lym5qsijyjsjca7pvto5oka", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/ah/cahe5odluo4swiyj4n2lohwh57qg5lym5qsijyjsjca7pvto5oka.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 6675 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 1336756, "tid": 1336756, + "ts": 1655273905783.549, "dur": 122.462, + "args": { + "External id": 4048765,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.125", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [], [], [], [], [], [], [], []], "Ev Idx": 6676 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336756, "tid": 1336756, + "ts": 1655273905830.824, "dur": 10.120, + "args": { + "External id": 4048766,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[8388608, 2048, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [], [], [], [], []], "Ev Idx": 6677 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273905835.487, "dur": 4.770, + "args": { + "External id": 4048767,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "[8388608, 2048, 64, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6678 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655273905843.437, "dur": 4.857, + "args": { + "External id": 4048768,"Record function id": 0, "Concrete Inputs": ["[16, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6679 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655273905849.389, "dur": 2.414, + "args": { + "External id": 4048769,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6680 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655273905854.108, "dur": 4.158, + "args": { + "External id": 4048770,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6681 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655273905916.041, "dur": 44.097, + "args": { + "External id": 4048771,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 6682 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_2", "pid": 1336756, "tid": 1336756, + "ts": 1655273906027.027, "dur": 28.715, + "args": { + "External id": 4048772,"kernel_hash": "ckbsutlugbs4qoncxuwq6kkwome3xojo3ke4p7z74lcl5h4q62to", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "2048", "1", "9.9999999999999995e-07", "True", "2048", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/kb/ckbsutlugbs4qoncxuwq6kkwome3xojo3ke4p7z74lcl5h4q62to.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [1], [2048, 1], [2048, 1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [65536, 2048], [2048], [65536, 2048], [65536, 2048], [65536], [], [], [], [], [], [], [], [], []], "Ev Idx": 6683 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655273906065.796, "dur": 45.951, + "args": { + "External id": 4048773,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [5632, 1]], "Input Dims": [[65536, 2048], [2048, 5632], [65536, 5632]], "Ev Idx": 6684 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655273906118.464, "dur": 35.510, + "args": { + "External id": 4048774,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [5632, 1]], "Input Dims": [[65536, 2048], [2048, 5632], [65536, 5632]], "Ev Idx": 6685 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 1336756, "tid": 1336756, + "ts": 1655273906177.408, "dur": 22.753, + "args": { + "External id": 4048775,"kernel_hash": "cgh2wg2b6li2ipjwrhdr326ycb37fu4v576nwebfoyhwx5kppapn", "grid": "grid(369098752,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "369098752"], "kernel_file": "/tmp/torchinductor_cvm/gh/cgh2wg2b6li2ipjwrhdr326ycb37fu4v576nwebfoyhwx5kppapn.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[5632, 1], [5632, 1], [23068672, 5632, 1], []], "Input Dims": [[65536, 5632], [65536, 5632], [16, 4096, 5632], []], "Ev Idx": 6686 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655273906205.265, "dur": 33.550, + "args": { + "External id": 4048776,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [1, 5632], [2048, 1]], "Input Dims": [[65536, 5632], [5632, 2048], [65536, 2048]], "Ev Idx": 6687 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 1336756, "tid": 1336756, + "ts": 1655273906255.633, "dur": 18.415, + "args": { + "External id": 4048777,"kernel_hash": "cta7vcczabyyuqarwmn4dcnazkxudhfwrvnick7ql5cmsd5lz4rz", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/ta/cta7vcczabyyuqarwmn4dcnazkxudhfwrvnick7ql5cmsd5lz4rz.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[8388608, 2048, 1], [2048, 1], []], "Input Dims": [[16, 4096, 2048], [65536, 2048], []], "Ev Idx": 6688 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.8)", "pid": 1336756, "tid": 1336756, + "ts": 1655273906410.331, "dur": 91.855, + "args": { + "External id": 4048778,"Record function id": 0, "Ev Idx": 6689 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 1336756, "tid": 1336756, + "ts": 1655273906575.899, "dur": 46.260, + "args": { + "External id": 4048779,"Record function id": 0, "Ev Idx": 6690 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.9)", "pid": 1336756, "tid": 1336756, + "ts": 1655273906630.869, "dur": 18054.881, + "args": { + "External id": 4048780,"Record function id": 0, "Ev Idx": 6691 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.9)", "pid": 1336756, "tid": 1336756, + "ts": 1655273906639.058, "dur": 865.271, + "args": { + "External id": 4048781,"Record function id": 0, "Ev Idx": 6692 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655273906713.591, "dur": 7.815, + "args": { + "External id": 4048782,"Record function id": 0, "Concrete Inputs": ["[6423040]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6693 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336756, "tid": 1336756, + "ts": 1655273906734.139, "dur": 31.314, + "args": { + "External id": 4048783,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 6694 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273906738.646, "dur": 2.517, + "args": { + "External id": 4048784,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6695 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273906745.405, "dur": 0.406, + "args": { + "External id": 4048785,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6696 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273906746.929, "dur": 0.350, + "args": { + "External id": 4048786,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6697 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273906748.206, "dur": 0.327, + "args": { + "External id": 4048787,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6698 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273906751.271, "dur": 0.312, + "args": { + "External id": 4048788,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6699 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273906752.783, "dur": 0.288, + "args": { + "External id": 4048789,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6700 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273906754.066, "dur": 3.331, + "args": { + "External id": 4048790,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6701 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273906758.364, "dur": 0.427, + "args": { + "External id": 4048791,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6702 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273906759.750, "dur": 0.223, + "args": { + "External id": 4048792,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6703 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336756, "tid": 1336756, + "ts": 1655273906775.424, "dur": 37.333, + "args": { + "External id": 4048793,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 6704 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 1336756, "tid": 1336756, + "ts": 1655273906844.851, "dur": 114.363, + "args": { + "External id": 4048794,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "6423040", "8", "3", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [], [], [], [], [], []], "Ev Idx": 6705 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655273906856.845, "dur": 3.739, + "args": { + "External id": 4048795,"Record function id": 0, "Concrete Inputs": ["[51384320]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6706 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 1336756, "tid": 1336756, + "ts": 1655273906865.597, "dur": 10.279, + "args": { + "External id": 4048796,"Record function id": 0, "Concrete Inputs": ["", "0", "19269120", "6423040"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 6707 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1336756, + "ts": 1655273906869.866, "dur": 5.635, + "args": { + "External id": 4048797,"Record function id": 0, "Concrete Inputs": ["", "0", "19269120", "25692160", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[51384320], [], [], [], []], "Ev Idx": 6708 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273906873.801, "dur": 0.548, + "args": { + "External id": 4048798,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "[1]", "19269120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 6709 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336756, "tid": 1336756, + "ts": 1655273906882.672, "dur": 27.643, + "args": { + "External id": 4048799,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 6710 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273906884.982, "dur": 2.089, + "args": { + "External id": 4048800,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "19269120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6711 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273906888.493, "dur": 0.294, + "args": { + "External id": 4048801,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "19269376"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6712 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273906889.922, "dur": 0.240, + "args": { + "External id": 4048802,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "19793664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6713 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273906893.482, "dur": 0.940, + "args": { + "External id": 4048803,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "20317952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6714 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273906898.212, "dur": 0.184, + "args": { + "External id": 4048804,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "20842240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6715 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273906899.267, "dur": 0.145, + "args": { + "External id": 4048805,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "21366528"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6716 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273906901.788, "dur": 0.160, + "args": { + "External id": 4048806,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "21366784"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6717 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273906902.583, "dur": 0.373, + "args": { + "External id": 4048807,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "22808576"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6718 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273906904.208, "dur": 1.987, + "args": { + "External id": 4048808,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "24250368"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6719 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336756, "tid": 1336756, + "ts": 1655273906929.676, "dur": 21.858, + "args": { + "External id": 4048809,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 6720 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 1336756, "tid": 1336756, + "ts": 1655273907054.148, "dur": 341.301, + "args": { + "External id": 4048810,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[51384320], [6423040], [], [], []], "Ev Idx": 6721 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336756, "tid": 1336756, + "ts": 1655273907084.565, "dur": 306.062, + "args": { + "External id": 4048811,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 3, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "3", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 51384320, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[6423040], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 6722, "In msg nelems": 6423040 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 1336756, "tid": 1336756, + "ts": 1655273907097.338, "dur": 288.068, + "args": { + "External id": 4048812,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[6423040]], "Ev Idx": 6723 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336756, "tid": 1336756, + "ts": 1655273907433.264, "dur": 3.817, + "args": { + "External id": 4048813,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "3", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 6724, "In msg nelems": 0, "Rank": 3, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.9)", "pid": 1336756, "tid": 1336756, + "ts": 1655273907524.004, "dur": 16981.275, + "args": { + "External id": 4048814,"Record function id": 0, "Ev Idx": 6725 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655273907612.151, "dur": 6.250, + "args": { + "External id": 4048815,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[51384320], []], "Ev Idx": 6726 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655273907621.541, "dur": 0.956, + "args": { + "External id": 4048816,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 6727 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655273907624.080, "dur": 2.134, + "args": { + "External id": 4048817,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 6728 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655273907627.883, "dur": 0.734, + "args": { + "External id": 4048818,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 6729 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655273907629.906, "dur": 0.784, + "args": { + "External id": 4048819,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 6730 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655273907631.804, "dur": 0.701, + "args": { + "External id": 4048820,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 6731 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655273907636.061, "dur": 0.580, + "args": { + "External id": 4048821,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 6732 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655273907638.091, "dur": 1.788, + "args": { + "External id": 4048822,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 6733 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655273907641.443, "dur": 0.568, + "args": { + "External id": 4048823,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 6734 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655273907643.585, "dur": 0.822, + "args": { + "External id": 4048824,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 6735 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 1336756, "tid": 1336756, + "ts": 1655273907664.538, "dur": 16802.308, + "args": { + "External id": 4048825,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 6736 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 1336756, "tid": 1336756, + "ts": 1655273907680.067, "dur": 16780.589, + "args": { + "External id": 4048826,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 6737 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655273907698.918, "dur": 12.495, + "args": { + "External id": 4048827,"Record function id": 0, "Concrete Inputs": ["[2133]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6738 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655273907714.427, "dur": 16714.863, + "args": { + "External id": 4048828,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], [], []], "Ev Idx": 6739 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336756, "tid": 1336756, + "ts": 1655273907716.856, "dur": 16711.894, + "args": { + "External id": 4048829,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], []], "Ev Idx": 6740 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273907722.678, "dur": 5.612, + "args": { + "External id": 4048830,"Record function id": 0, "Concrete Inputs": ["[2133]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6741 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1336756, + "ts": 1655273907729.945, "dur": 16684.374, + "args": { + "External id": 4048831,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[2133], [2133], []], "Ev Idx": 6742 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 1336756, "tid": 1336756, + "ts": 1655273924627.573, "dur": 34.293, + "args": { + "External id": 4048832,"Sequence number": 40618371, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 6743 + } + }, + { + "ph": "s", "id": 209, "pid": 1336756, "tid": 1336756, "ts": 1655273924627.573, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 1336756, "tid": 1336756, + "ts": 1655273924650.450, "dur": 6.957, + "args": { + "External id": 4048833,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[8388608, 2048, 1], [8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048], [16, 4096, 2048]], "Ev Idx": 6744 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655273924653.408, "dur": 3.713, + "args": { + "External id": 4048834,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 6745 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 1336756, "tid": 1336756, + "ts": 1655273924723.537, "dur": 71.618, + "args": { + "External id": 4048835,"Record function id": 0, "Ev Idx": 6746 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 1336756, "tid": 1336756, + "ts": 1655273924797.038, "dur": 1015.494, + "args": { + "External id": 4048836,"Record function id": 0, "Ev Idx": 6747 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 1336756, "tid": 1336756, + "ts": 1655273924834.747, "dur": 965.541, + "args": { + "External id": 4048837,"Sequence number": 40618372, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[8388608, 2048, 1], [1], [2048, 1], [2048, 1], [2048, 1], [32, 1], [32, 1], [2048, 1], [1], [2048, 1], [2048, 1], [5632, 1]], "Input Dims": [[16, 4096, 2048], [2048], [2048, 2048], [2048, 2048], [2048, 2048], [8192, 32], [8192, 32], [2048, 2048], [2048], [5632, 2048], [5632, 2048], [2048, 5632]], "Ev Idx": 6748 + } + }, + { + "ph": "s", "id": 208, "pid": 1336756, "tid": 1336756, "ts": 1655273924834.747, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 1336756, "tid": 1336756, + "ts": 1655273924896.567, "dur": 39.150, + "args": { + "External id": 4048838,"kernel_hash": "cd26ogptnjelaibpl2zumx5nxdttspqepvjkh7lpmsxbzrrexbxm", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "2048", "1", "9.9999999999999995e-07", "True", "2048", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/d2/cd26ogptnjelaibpl2zumx5nxdttspqepvjkh7lpmsxbzrrexbxm.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [65536, 2048], [2048], [65536], [], [], [], [], [], [], [], [], []], "Ev Idx": 6749 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655273924947.032, "dur": 133.618, + "args": { + "External id": 4048839,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 6750 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655273925093.998, "dur": 40.914, + "args": { + "External id": 4048840,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 6751 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655273925142.317, "dur": 31.170, + "args": { + "External id": 4048841,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 6752 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336756, "tid": 1336756, + "ts": 1655273925200.231, "dur": 25.897, + "args": { + "External id": 4048842,"kernel_hash": "cahe5odluo4swiyj4n2lohwh57qg5lym5qsijyjsjca7pvto5oka", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/ah/cahe5odluo4swiyj4n2lohwh57qg5lym5qsijyjsjca7pvto5oka.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 6753 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336756, "tid": 1336756, + "ts": 1655273925242.531, "dur": 13.762, + "args": { + "External id": 4048843,"kernel_hash": "cahe5odluo4swiyj4n2lohwh57qg5lym5qsijyjsjca7pvto5oka", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/ah/cahe5odluo4swiyj4n2lohwh57qg5lym5qsijyjsjca7pvto5oka.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 6754 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 1336756, "tid": 1336756, + "ts": 1655273925274.606, "dur": 122.891, + "args": { + "External id": 4048844,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.125", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [], [], [], [], [], [], [], []], "Ev Idx": 6755 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336756, "tid": 1336756, + "ts": 1655273925321.269, "dur": 10.529, + "args": { + "External id": 4048845,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[8388608, 2048, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [], [], [], [], []], "Ev Idx": 6756 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273925325.989, "dur": 5.028, + "args": { + "External id": 4048846,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "[8388608, 2048, 64, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6757 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655273925334.393, "dur": 4.900, + "args": { + "External id": 4048847,"Record function id": 0, "Concrete Inputs": ["[16, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6758 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655273925340.814, "dur": 0.996, + "args": { + "External id": 4048848,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6759 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655273925344.323, "dur": 4.840, + "args": { + "External id": 4048849,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6760 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655273925407.705, "dur": 62.413, + "args": { + "External id": 4048850,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 6761 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_2", "pid": 1336756, "tid": 1336756, + "ts": 1655273925499.891, "dur": 26.665, + "args": { + "External id": 4048851,"kernel_hash": "ckbsutlugbs4qoncxuwq6kkwome3xojo3ke4p7z74lcl5h4q62to", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "2048", "1", "9.9999999999999995e-07", "True", "2048", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/kb/ckbsutlugbs4qoncxuwq6kkwome3xojo3ke4p7z74lcl5h4q62to.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [1], [2048, 1], [2048, 1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [65536, 2048], [2048], [65536, 2048], [65536, 2048], [65536], [], [], [], [], [], [], [], [], []], "Ev Idx": 6762 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655273925535.128, "dur": 41.456, + "args": { + "External id": 4048852,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [5632, 1]], "Input Dims": [[65536, 2048], [2048, 5632], [65536, 5632]], "Ev Idx": 6763 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655273925583.815, "dur": 34.627, + "args": { + "External id": 4048853,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [5632, 1]], "Input Dims": [[65536, 2048], [2048, 5632], [65536, 5632]], "Ev Idx": 6764 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 1336756, "tid": 1336756, + "ts": 1655273925639.329, "dur": 22.537, + "args": { + "External id": 4048854,"kernel_hash": "cgh2wg2b6li2ipjwrhdr326ycb37fu4v576nwebfoyhwx5kppapn", "grid": "grid(369098752,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "369098752"], "kernel_file": "/tmp/torchinductor_cvm/gh/cgh2wg2b6li2ipjwrhdr326ycb37fu4v576nwebfoyhwx5kppapn.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[5632, 1], [5632, 1], [23068672, 5632, 1], []], "Input Dims": [[65536, 5632], [65536, 5632], [16, 4096, 5632], []], "Ev Idx": 6765 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655273925666.829, "dur": 34.289, + "args": { + "External id": 4048855,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [1, 5632], [2048, 1]], "Input Dims": [[65536, 5632], [5632, 2048], [65536, 2048]], "Ev Idx": 6766 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 1336756, "tid": 1336756, + "ts": 1655273925720.287, "dur": 17.311, + "args": { + "External id": 4048856,"kernel_hash": "cta7vcczabyyuqarwmn4dcnazkxudhfwrvnick7ql5cmsd5lz4rz", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/ta/cta7vcczabyyuqarwmn4dcnazkxudhfwrvnick7ql5cmsd5lz4rz.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[8388608, 2048, 1], [2048, 1], []], "Input Dims": [[16, 4096, 2048], [65536, 2048], []], "Ev Idx": 6767 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.9)", "pid": 1336756, "tid": 1336756, + "ts": 1655273925874.677, "dur": 71.044, + "args": { + "External id": 4048857,"Record function id": 0, "Ev Idx": 6768 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 1336756, "tid": 1336756, + "ts": 1655273926054.572, "dur": 47.585, + "args": { + "External id": 4048858,"Record function id": 0, "Ev Idx": 6769 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.10)", "pid": 1336756, "tid": 1336756, + "ts": 1655273926111.058, "dur": 18119.468, + "args": { + "External id": 4048859,"Record function id": 0, "Ev Idx": 6770 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.10)", "pid": 1336756, "tid": 1336756, + "ts": 1655273926119.164, "dur": 809.712, + "args": { + "External id": 4048860,"Record function id": 0, "Ev Idx": 6771 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655273926193.037, "dur": 8.034, + "args": { + "External id": 4048861,"Record function id": 0, "Concrete Inputs": ["[6423040]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6772 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336756, "tid": 1336756, + "ts": 1655273926214.158, "dur": 34.093, + "args": { + "External id": 4048862,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 6773 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273926220.685, "dur": 2.250, + "args": { + "External id": 4048863,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6774 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273926226.764, "dur": 0.491, + "args": { + "External id": 4048864,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6775 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273926228.501, "dur": 0.197, + "args": { + "External id": 4048865,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6776 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273926230.259, "dur": 2.185, + "args": { + "External id": 4048866,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6777 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273926233.658, "dur": 0.313, + "args": { + "External id": 4048867,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6778 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273926235.226, "dur": 0.313, + "args": { + "External id": 4048868,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6779 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273926238.358, "dur": 1.274, + "args": { + "External id": 4048869,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6780 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273926240.784, "dur": 0.170, + "args": { + "External id": 4048870,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6781 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273926242.308, "dur": 0.136, + "args": { + "External id": 4048871,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6782 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336756, "tid": 1336756, + "ts": 1655273926259.000, "dur": 37.839, + "args": { + "External id": 4048872,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 6783 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 1336756, "tid": 1336756, + "ts": 1655273926328.675, "dur": 123.207, + "args": { + "External id": 4048873,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "6423040", "8", "3", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [], [], [], [], [], []], "Ev Idx": 6784 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655273926340.302, "dur": 3.600, + "args": { + "External id": 4048874,"Record function id": 0, "Concrete Inputs": ["[51384320]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6785 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 1336756, "tid": 1336756, + "ts": 1655273926348.700, "dur": 11.344, + "args": { + "External id": 4048875,"Record function id": 0, "Concrete Inputs": ["", "0", "19269120", "6423040"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 6786 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1336756, + "ts": 1655273926352.665, "dur": 6.973, + "args": { + "External id": 4048876,"Record function id": 0, "Concrete Inputs": ["", "0", "19269120", "25692160", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[51384320], [], [], [], []], "Ev Idx": 6787 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273926356.352, "dur": 1.964, + "args": { + "External id": 4048877,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "[1]", "19269120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 6788 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336756, "tid": 1336756, + "ts": 1655273926366.870, "dur": 25.137, + "args": { + "External id": 4048878,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 6789 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273926368.964, "dur": 0.401, + "args": { + "External id": 4048879,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "19269120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6790 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273926370.720, "dur": 0.494, + "args": { + "External id": 4048880,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "19269376"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6791 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273926372.751, "dur": 0.157, + "args": { + "External id": 4048881,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "19793664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6792 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273926375.858, "dur": 1.133, + "args": { + "External id": 4048882,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "20317952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6793 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273926378.182, "dur": 0.308, + "args": { + "External id": 4048883,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "20842240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6794 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273926379.718, "dur": 1.832, + "args": { + "External id": 4048884,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "21366528"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6795 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273926382.593, "dur": 0.391, + "args": { + "External id": 4048885,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "21366784"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6796 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273926384.330, "dur": 0.332, + "args": { + "External id": 4048886,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "22808576"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6797 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273926388.243, "dur": 0.267, + "args": { + "External id": 4048887,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "24250368"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6798 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336756, "tid": 1336756, + "ts": 1655273926401.480, "dur": 40.987, + "args": { + "External id": 4048888,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 6799 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 1336756, "tid": 1336756, + "ts": 1655273926504.169, "dur": 339.135, + "args": { + "External id": 4048889,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[51384320], [6423040], [], [], []], "Ev Idx": 6800 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336756, "tid": 1336756, + "ts": 1655273926532.591, "dur": 306.221, + "args": { + "External id": 4048890,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 3, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "3", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 51384320, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[6423040], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 6801, "In msg nelems": 6423040 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 1336756, "tid": 1336756, + "ts": 1655273926543.764, "dur": 289.524, + "args": { + "External id": 4048891,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[6423040]], "Ev Idx": 6802 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336756, "tid": 1336756, + "ts": 1655273926864.562, "dur": 2.202, + "args": { + "External id": 4048892,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "3", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 6803, "In msg nelems": 0, "Rank": 3, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.10)", "pid": 1336756, "tid": 1336756, + "ts": 1655273926949.143, "dur": 17092.471, + "args": { + "External id": 4048893,"Record function id": 0, "Ev Idx": 6804 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655273927077.684, "dur": 6.541, + "args": { + "External id": 4048894,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[51384320], []], "Ev Idx": 6805 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655273927087.527, "dur": 0.959, + "args": { + "External id": 4048895,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 6806 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655273927090.329, "dur": 1.791, + "args": { + "External id": 4048896,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 6807 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655273927120.972, "dur": 0.692, + "args": { + "External id": 4048897,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 6808 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655273927123.151, "dur": 0.759, + "args": { + "External id": 4048898,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 6809 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655273927125.278, "dur": 0.541, + "args": { + "External id": 4048899,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 6810 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655273927129.264, "dur": 0.830, + "args": { + "External id": 4048900,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 6811 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655273927131.336, "dur": 1.678, + "args": { + "External id": 4048901,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 6812 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655273927134.292, "dur": 0.589, + "args": { + "External id": 4048902,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 6813 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655273927136.195, "dur": 0.405, + "args": { + "External id": 4048903,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 6814 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 1336756, "tid": 1336756, + "ts": 1655273927159.486, "dur": 16815.396, + "args": { + "External id": 4048904,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 6815 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 1336756, "tid": 1336756, + "ts": 1655273927175.635, "dur": 16792.453, + "args": { + "External id": 4048905,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 6816 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655273927189.355, "dur": 14.462, + "args": { + "External id": 4048906,"Record function id": 0, "Concrete Inputs": ["[2133]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6817 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655273927206.764, "dur": 16730.492, + "args": { + "External id": 4048907,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], [], []], "Ev Idx": 6818 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336756, "tid": 1336756, + "ts": 1655273927209.002, "dur": 16727.780, + "args": { + "External id": 4048908,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], []], "Ev Idx": 6819 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273927214.454, "dur": 5.421, + "args": { + "External id": 4048909,"Record function id": 0, "Concrete Inputs": ["[2133]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6820 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1336756, + "ts": 1655273927221.428, "dur": 16712.421, + "args": { + "External id": 4048910,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[2133], [2133], []], "Ev Idx": 6821 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 1336756, "tid": 1336756, + "ts": 1655273944170.039, "dur": 36.794, + "args": { + "External id": 4048911,"Sequence number": 40618373, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 6822 + } + }, + { + "ph": "s", "id": 207, "pid": 1336756, "tid": 1336756, "ts": 1655273944170.039, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 1336756, "tid": 1336756, + "ts": 1655273944194.589, "dur": 7.417, + "args": { + "External id": 4048912,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[8388608, 2048, 1], [8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048], [16, 4096, 2048]], "Ev Idx": 6823 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655273944197.907, "dur": 3.813, + "args": { + "External id": 4048913,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 6824 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 1336756, "tid": 1336756, + "ts": 1655273944268.807, "dur": 72.086, + "args": { + "External id": 4048914,"Record function id": 0, "Ev Idx": 6825 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 1336756, "tid": 1336756, + "ts": 1655273944342.582, "dur": 1021.579, + "args": { + "External id": 4048915,"Record function id": 0, "Ev Idx": 6826 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 1336756, "tid": 1336756, + "ts": 1655273944378.836, "dur": 973.126, + "args": { + "External id": 4048916,"Sequence number": 40618374, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[8388608, 2048, 1], [1], [2048, 1], [2048, 1], [2048, 1], [32, 1], [32, 1], [2048, 1], [1], [2048, 1], [2048, 1], [5632, 1]], "Input Dims": [[16, 4096, 2048], [2048], [2048, 2048], [2048, 2048], [2048, 2048], [8192, 32], [8192, 32], [2048, 2048], [2048], [5632, 2048], [5632, 2048], [2048, 5632]], "Ev Idx": 6827 + } + }, + { + "ph": "s", "id": 206, "pid": 1336756, "tid": 1336756, "ts": 1655273944378.836, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 1336756, "tid": 1336756, + "ts": 1655273944454.999, "dur": 40.802, + "args": { + "External id": 4048917,"kernel_hash": "cd26ogptnjelaibpl2zumx5nxdttspqepvjkh7lpmsxbzrrexbxm", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "2048", "1", "9.9999999999999995e-07", "True", "2048", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/d2/cd26ogptnjelaibpl2zumx5nxdttspqepvjkh7lpmsxbzrrexbxm.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [65536, 2048], [2048], [65536], [], [], [], [], [], [], [], [], []], "Ev Idx": 6828 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655273944509.992, "dur": 101.786, + "args": { + "External id": 4048918,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 6829 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655273944620.498, "dur": 40.126, + "args": { + "External id": 4048919,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 6830 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655273944667.850, "dur": 32.126, + "args": { + "External id": 4048920,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 6831 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336756, "tid": 1336756, + "ts": 1655273944724.097, "dur": 22.700, + "args": { + "External id": 4048921,"kernel_hash": "cahe5odluo4swiyj4n2lohwh57qg5lym5qsijyjsjca7pvto5oka", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/ah/cahe5odluo4swiyj4n2lohwh57qg5lym5qsijyjsjca7pvto5oka.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 6832 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336756, "tid": 1336756, + "ts": 1655273944764.350, "dur": 13.919, + "args": { + "External id": 4048922,"kernel_hash": "cahe5odluo4swiyj4n2lohwh57qg5lym5qsijyjsjca7pvto5oka", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/ah/cahe5odluo4swiyj4n2lohwh57qg5lym5qsijyjsjca7pvto5oka.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 6833 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 1336756, "tid": 1336756, + "ts": 1655273944794.879, "dur": 121.758, + "args": { + "External id": 4048923,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.125", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [], [], [], [], [], [], [], []], "Ev Idx": 6834 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336756, "tid": 1336756, + "ts": 1655273944841.858, "dur": 10.017, + "args": { + "External id": 4048924,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[8388608, 2048, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [], [], [], [], []], "Ev Idx": 6835 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273944846.502, "dur": 4.663, + "args": { + "External id": 4048925,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "[8388608, 2048, 64, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6836 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655273944854.592, "dur": 4.891, + "args": { + "External id": 4048926,"Record function id": 0, "Concrete Inputs": ["[16, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6837 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655273944860.939, "dur": 0.971, + "args": { + "External id": 4048927,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6838 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655273944864.339, "dur": 4.305, + "args": { + "External id": 4048928,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6839 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655273944926.781, "dur": 44.058, + "args": { + "External id": 4048929,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 6840 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_2", "pid": 1336756, "tid": 1336756, + "ts": 1655273945034.246, "dur": 29.269, + "args": { + "External id": 4048930,"kernel_hash": "ckbsutlugbs4qoncxuwq6kkwome3xojo3ke4p7z74lcl5h4q62to", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "2048", "1", "9.9999999999999995e-07", "True", "2048", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/kb/ckbsutlugbs4qoncxuwq6kkwome3xojo3ke4p7z74lcl5h4q62to.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [1], [2048, 1], [2048, 1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [65536, 2048], [2048], [65536, 2048], [65536, 2048], [65536], [], [], [], [], [], [], [], [], []], "Ev Idx": 6841 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655273945074.473, "dur": 45.990, + "args": { + "External id": 4048931,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [5632, 1]], "Input Dims": [[65536, 2048], [2048, 5632], [65536, 5632]], "Ev Idx": 6842 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655273945128.527, "dur": 34.624, + "args": { + "External id": 4048932,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [5632, 1]], "Input Dims": [[65536, 2048], [2048, 5632], [65536, 5632]], "Ev Idx": 6843 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 1336756, "tid": 1336756, + "ts": 1655273945185.714, "dur": 24.429, + "args": { + "External id": 4048933,"kernel_hash": "cgh2wg2b6li2ipjwrhdr326ycb37fu4v576nwebfoyhwx5kppapn", "grid": "grid(369098752,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "369098752"], "kernel_file": "/tmp/torchinductor_cvm/gh/cgh2wg2b6li2ipjwrhdr326ycb37fu4v576nwebfoyhwx5kppapn.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[5632, 1], [5632, 1], [23068672, 5632, 1], []], "Input Dims": [[65536, 5632], [65536, 5632], [16, 4096, 5632], []], "Ev Idx": 6844 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655273945215.373, "dur": 35.206, + "args": { + "External id": 4048934,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [1, 5632], [2048, 1]], "Input Dims": [[65536, 5632], [5632, 2048], [65536, 2048]], "Ev Idx": 6845 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 1336756, "tid": 1336756, + "ts": 1655273945269.359, "dur": 17.890, + "args": { + "External id": 4048935,"kernel_hash": "cta7vcczabyyuqarwmn4dcnazkxudhfwrvnick7ql5cmsd5lz4rz", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/ta/cta7vcczabyyuqarwmn4dcnazkxudhfwrvnick7ql5cmsd5lz4rz.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[8388608, 2048, 1], [2048, 1], []], "Input Dims": [[16, 4096, 2048], [65536, 2048], []], "Ev Idx": 6846 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.10)", "pid": 1336756, "tid": 1336756, + "ts": 1655273945445.521, "dur": 73.470, + "args": { + "External id": 4048936,"Record function id": 0, "Ev Idx": 6847 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 1336756, "tid": 1336756, + "ts": 1655273945591.973, "dur": 46.331, + "args": { + "External id": 4048937,"Record function id": 0, "Ev Idx": 6848 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.11)", "pid": 1336756, "tid": 1336756, + "ts": 1655273945647.445, "dur": 17990.160, + "args": { + "External id": 4048938,"Record function id": 0, "Ev Idx": 6849 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.11)", "pid": 1336756, "tid": 1336756, + "ts": 1655273945654.076, "dur": 857.256, + "args": { + "External id": 4048939,"Record function id": 0, "Ev Idx": 6850 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655273945727.437, "dur": 8.628, + "args": { + "External id": 4048940,"Record function id": 0, "Concrete Inputs": ["[6423040]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6851 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336756, "tid": 1336756, + "ts": 1655273945749.137, "dur": 35.017, + "args": { + "External id": 4048941,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 6852 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273945755.197, "dur": 2.121, + "args": { + "External id": 4048942,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6853 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273945761.488, "dur": 0.566, + "args": { + "External id": 4048943,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6854 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273945763.322, "dur": 0.310, + "args": { + "External id": 4048944,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6855 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273945764.840, "dur": 0.490, + "args": { + "External id": 4048945,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6856 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273945768.370, "dur": 0.477, + "args": { + "External id": 4048946,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6857 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273945770.050, "dur": 0.438, + "args": { + "External id": 4048947,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6858 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273945771.833, "dur": 2.902, + "args": { + "External id": 4048948,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6859 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273945776.157, "dur": 0.278, + "args": { + "External id": 4048949,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6860 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273945778.024, "dur": 0.173, + "args": { + "External id": 4048950,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6861 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336756, "tid": 1336756, + "ts": 1655273945796.470, "dur": 40.312, + "args": { + "External id": 4048951,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 6862 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 1336756, "tid": 1336756, + "ts": 1655273945868.977, "dur": 106.227, + "args": { + "External id": 4048952,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "6423040", "8", "3", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [], [], [], [], [], []], "Ev Idx": 6863 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655273945881.496, "dur": 5.148, + "args": { + "External id": 4048953,"Record function id": 0, "Concrete Inputs": ["[51384320]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6864 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 1336756, "tid": 1336756, + "ts": 1655273945891.658, "dur": 10.172, + "args": { + "External id": 4048954,"Record function id": 0, "Concrete Inputs": ["", "0", "19269120", "6423040"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 6865 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1336756, + "ts": 1655273945895.856, "dur": 5.367, + "args": { + "External id": 4048955,"Record function id": 0, "Concrete Inputs": ["", "0", "19269120", "25692160", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[51384320], [], [], [], []], "Ev Idx": 6866 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273945899.483, "dur": 0.522, + "args": { + "External id": 4048956,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "[1]", "19269120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 6867 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336756, "tid": 1336756, + "ts": 1655273945908.429, "dur": 24.842, + "args": { + "External id": 4048957,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 6868 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273945910.409, "dur": 0.338, + "args": { + "External id": 4048958,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "19269120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6869 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273945912.223, "dur": 2.071, + "args": { + "External id": 4048959,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "19269376"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6870 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273945915.801, "dur": 0.194, + "args": { + "External id": 4048960,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "19793664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6871 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273945917.376, "dur": 1.577, + "args": { + "External id": 4048961,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "20317952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6872 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273945921.754, "dur": 0.197, + "args": { + "External id": 4048962,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "20842240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6873 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273945923.282, "dur": 0.138, + "args": { + "External id": 4048963,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "21366528"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6874 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273945924.639, "dur": 0.150, + "args": { + "External id": 4048964,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "21366784"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6875 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273945927.641, "dur": 0.245, + "args": { + "External id": 4048965,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "22808576"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6876 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273945929.309, "dur": 0.414, + "args": { + "External id": 4048966,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "24250368"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6877 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336756, "tid": 1336756, + "ts": 1655273945945.240, "dur": 22.599, + "args": { + "External id": 4048967,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 6878 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 1336756, "tid": 1336756, + "ts": 1655273946069.411, "dur": 334.793, + "args": { + "External id": 4048968,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[51384320], [6423040], [], [], []], "Ev Idx": 6879 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336756, "tid": 1336756, + "ts": 1655273946098.249, "dur": 301.606, + "args": { + "External id": 4048969,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 3, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "3", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 51384320, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[6423040], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 6880, "In msg nelems": 6423040 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 1336756, "tid": 1336756, + "ts": 1655273946109.045, "dur": 285.727, + "args": { + "External id": 4048970,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[6423040]], "Ev Idx": 6881 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336756, "tid": 1336756, + "ts": 1655273946440.581, "dur": 3.697, + "args": { + "External id": 4048971,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "3", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 6882, "In msg nelems": 0, "Rank": 3, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.11)", "pid": 1336756, "tid": 1336756, + "ts": 1655273946531.172, "dur": 16924.919, + "args": { + "External id": 4048972,"Record function id": 0, "Ev Idx": 6883 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655273946622.633, "dur": 6.031, + "args": { + "External id": 4048973,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[51384320], []], "Ev Idx": 6884 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655273946631.725, "dur": 1.043, + "args": { + "External id": 4048974,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 6885 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655273946634.422, "dur": 1.939, + "args": { + "External id": 4048975,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 6886 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655273946638.133, "dur": 0.743, + "args": { + "External id": 4048976,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 6887 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655273946640.102, "dur": 0.762, + "args": { + "External id": 4048977,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 6888 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655273946642.177, "dur": 0.808, + "args": { + "External id": 4048978,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 6889 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655273946645.947, "dur": 0.749, + "args": { + "External id": 4048979,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 6890 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655273946647.957, "dur": 1.467, + "args": { + "External id": 4048980,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 6891 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655273946650.748, "dur": 0.633, + "args": { + "External id": 4048981,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 6892 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655273946653.122, "dur": 0.552, + "args": { + "External id": 4048982,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 6893 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 1336756, "tid": 1336756, + "ts": 1655273946673.657, "dur": 16735.670, + "args": { + "External id": 4048983,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 6894 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 1336756, "tid": 1336756, + "ts": 1655273946689.572, "dur": 16712.965, + "args": { + "External id": 4048984,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 6895 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655273946713.001, "dur": 12.990, + "args": { + "External id": 4048985,"Record function id": 0, "Concrete Inputs": ["[2133]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6896 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655273946728.841, "dur": 16642.103, + "args": { + "External id": 4048986,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], [], []], "Ev Idx": 6897 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336756, "tid": 1336756, + "ts": 1655273946731.228, "dur": 16639.037, + "args": { + "External id": 4048987,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], []], "Ev Idx": 6898 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273946736.717, "dur": 5.975, + "args": { + "External id": 4048988,"Record function id": 0, "Concrete Inputs": ["[2133]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6899 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1336756, + "ts": 1655273946744.193, "dur": 16623.225, + "args": { + "External id": 4048989,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[2133], [2133], []], "Ev Idx": 6900 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 1336756, "tid": 1336756, + "ts": 1655273963578.839, "dur": 35.388, + "args": { + "External id": 4048990,"Sequence number": 40618375, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 6901 + } + }, + { + "ph": "s", "id": 205, "pid": 1336756, "tid": 1336756, "ts": 1655273963578.839, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 1336756, "tid": 1336756, + "ts": 1655273963602.746, "dur": 7.010, + "args": { + "External id": 4048991,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[8388608, 2048, 1], [8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048], [16, 4096, 2048]], "Ev Idx": 6902 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655273963605.729, "dur": 3.805, + "args": { + "External id": 4048992,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 6903 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 1336756, "tid": 1336756, + "ts": 1655273963675.090, "dur": 69.640, + "args": { + "External id": 4048993,"Record function id": 0, "Ev Idx": 6904 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 1336756, "tid": 1336756, + "ts": 1655273963746.270, "dur": 1020.609, + "args": { + "External id": 4048994,"Record function id": 0, "Ev Idx": 6905 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 1336756, "tid": 1336756, + "ts": 1655273963786.557, "dur": 967.488, + "args": { + "External id": 4048995,"Sequence number": 40618376, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[8388608, 2048, 1], [1], [2048, 1], [2048, 1], [2048, 1], [32, 1], [32, 1], [2048, 1], [1], [2048, 1], [2048, 1], [5632, 1]], "Input Dims": [[16, 4096, 2048], [2048], [2048, 2048], [2048, 2048], [2048, 2048], [8192, 32], [8192, 32], [2048, 2048], [2048], [5632, 2048], [5632, 2048], [2048, 5632]], "Ev Idx": 6906 + } + }, + { + "ph": "s", "id": 204, "pid": 1336756, "tid": 1336756, "ts": 1655273963786.557, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 1336756, "tid": 1336756, + "ts": 1655273963851.145, "dur": 38.425, + "args": { + "External id": 4048996,"kernel_hash": "cd26ogptnjelaibpl2zumx5nxdttspqepvjkh7lpmsxbzrrexbxm", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "2048", "1", "9.9999999999999995e-07", "True", "2048", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/d2/cd26ogptnjelaibpl2zumx5nxdttspqepvjkh7lpmsxbzrrexbxm.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [65536, 2048], [2048], [65536], [], [], [], [], [], [], [], [], []], "Ev Idx": 6907 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655273963901.444, "dur": 124.979, + "args": { + "External id": 4048997,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 6908 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655273964039.201, "dur": 43.164, + "args": { + "External id": 4048998,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 6909 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655273964090.223, "dur": 30.928, + "args": { + "External id": 4048999,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 6910 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336756, "tid": 1336756, + "ts": 1655273964147.756, "dur": 25.528, + "args": { + "External id": 4049000,"kernel_hash": "cahe5odluo4swiyj4n2lohwh57qg5lym5qsijyjsjca7pvto5oka", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/ah/cahe5odluo4swiyj4n2lohwh57qg5lym5qsijyjsjca7pvto5oka.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 6911 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336756, "tid": 1336756, + "ts": 1655273964190.506, "dur": 14.082, + "args": { + "External id": 4049001,"kernel_hash": "cahe5odluo4swiyj4n2lohwh57qg5lym5qsijyjsjca7pvto5oka", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/ah/cahe5odluo4swiyj4n2lohwh57qg5lym5qsijyjsjca7pvto5oka.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 6912 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 1336756, "tid": 1336756, + "ts": 1655273964221.981, "dur": 123.498, + "args": { + "External id": 4049002,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.125", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [], [], [], [], [], [], [], []], "Ev Idx": 6913 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336756, "tid": 1336756, + "ts": 1655273964270.954, "dur": 10.318, + "args": { + "External id": 4049003,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[8388608, 2048, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [], [], [], [], []], "Ev Idx": 6914 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273964275.996, "dur": 4.631, + "args": { + "External id": 4049004,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "[8388608, 2048, 64, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6915 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655273964283.819, "dur": 4.918, + "args": { + "External id": 4049005,"Record function id": 0, "Concrete Inputs": ["[16, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6916 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655273964290.380, "dur": 1.078, + "args": { + "External id": 4049006,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6917 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655273964293.766, "dur": 4.450, + "args": { + "External id": 4049007,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6918 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655273964355.390, "dur": 45.495, + "args": { + "External id": 4049008,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 6919 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_2", "pid": 1336756, "tid": 1336756, + "ts": 1655273964443.982, "dur": 27.985, + "args": { + "External id": 4049009,"kernel_hash": "ckbsutlugbs4qoncxuwq6kkwome3xojo3ke4p7z74lcl5h4q62to", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "2048", "1", "9.9999999999999995e-07", "True", "2048", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/kb/ckbsutlugbs4qoncxuwq6kkwome3xojo3ke4p7z74lcl5h4q62to.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [1], [2048, 1], [2048, 1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [65536, 2048], [2048], [65536, 2048], [65536, 2048], [65536], [], [], [], [], [], [], [], [], []], "Ev Idx": 6920 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655273964481.343, "dur": 45.301, + "args": { + "External id": 4049010,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [5632, 1]], "Input Dims": [[65536, 2048], [2048, 5632], [65536, 5632]], "Ev Idx": 6921 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655273964535.650, "dur": 34.898, + "args": { + "External id": 4049011,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [5632, 1]], "Input Dims": [[65536, 2048], [2048, 5632], [65536, 5632]], "Ev Idx": 6922 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 1336756, "tid": 1336756, + "ts": 1655273964590.645, "dur": 23.300, + "args": { + "External id": 4049012,"kernel_hash": "cgh2wg2b6li2ipjwrhdr326ycb37fu4v576nwebfoyhwx5kppapn", "grid": "grid(369098752,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "369098752"], "kernel_file": "/tmp/torchinductor_cvm/gh/cgh2wg2b6li2ipjwrhdr326ycb37fu4v576nwebfoyhwx5kppapn.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[5632, 1], [5632, 1], [23068672, 5632, 1], []], "Input Dims": [[65536, 5632], [65536, 5632], [16, 4096, 5632], []], "Ev Idx": 6923 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655273964619.597, "dur": 34.315, + "args": { + "External id": 4049013,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [1, 5632], [2048, 1]], "Input Dims": [[65536, 5632], [5632, 2048], [65536, 2048]], "Ev Idx": 6924 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 1336756, "tid": 1336756, + "ts": 1655273964673.782, "dur": 17.126, + "args": { + "External id": 4049014,"kernel_hash": "cta7vcczabyyuqarwmn4dcnazkxudhfwrvnick7ql5cmsd5lz4rz", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/ta/cta7vcczabyyuqarwmn4dcnazkxudhfwrvnick7ql5cmsd5lz4rz.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[8388608, 2048, 1], [2048, 1], []], "Input Dims": [[16, 4096, 2048], [65536, 2048], []], "Ev Idx": 6925 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.11)", "pid": 1336756, "tid": 1336756, + "ts": 1655273964830.864, "dur": 69.991, + "args": { + "External id": 4049015,"Record function id": 0, "Ev Idx": 6926 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 1336756, "tid": 1336756, + "ts": 1655273964972.417, "dur": 90.531, + "args": { + "External id": 4049016,"Record function id": 0, "Ev Idx": 6927 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.12)", "pid": 1336756, "tid": 1336756, + "ts": 1655273965073.725, "dur": 18011.040, + "args": { + "External id": 4049017,"Record function id": 0, "Ev Idx": 6928 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.12)", "pid": 1336756, "tid": 1336756, + "ts": 1655273965083.109, "dur": 820.998, + "args": { + "External id": 4049018,"Record function id": 0, "Ev Idx": 6929 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655273965158.361, "dur": 8.349, + "args": { + "External id": 4049019,"Record function id": 0, "Concrete Inputs": ["[6423040]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6930 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336756, "tid": 1336756, + "ts": 1655273965180.425, "dur": 36.478, + "args": { + "External id": 4049020,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 6931 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273965185.536, "dur": 2.287, + "args": { + "External id": 4049021,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6932 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273965191.869, "dur": 0.214, + "args": { + "External id": 4049022,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6933 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273965193.724, "dur": 0.424, + "args": { + "External id": 4049023,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6934 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273965195.845, "dur": 0.478, + "args": { + "External id": 4049024,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6935 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273965199.177, "dur": 0.369, + "args": { + "External id": 4049025,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6936 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273965201.085, "dur": 0.314, + "args": { + "External id": 4049026,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6937 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273965202.780, "dur": 3.103, + "args": { + "External id": 4049027,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6938 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273965209.518, "dur": 0.258, + "args": { + "External id": 4049028,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6939 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273965210.975, "dur": 0.201, + "args": { + "External id": 4049029,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6940 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336756, "tid": 1336756, + "ts": 1655273965227.927, "dur": 39.625, + "args": { + "External id": 4049030,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 6941 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 1336756, "tid": 1336756, + "ts": 1655273965299.049, "dur": 107.343, + "args": { + "External id": 4049031,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "6423040", "8", "3", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [], [], [], [], [], []], "Ev Idx": 6942 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655273965311.205, "dur": 3.649, + "args": { + "External id": 4049032,"Record function id": 0, "Concrete Inputs": ["[51384320]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6943 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 1336756, "tid": 1336756, + "ts": 1655273965320.294, "dur": 11.761, + "args": { + "External id": 4049033,"Record function id": 0, "Concrete Inputs": ["", "0", "19269120", "6423040"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 6944 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1336756, + "ts": 1655273965324.886, "dur": 6.729, + "args": { + "External id": 4049034,"Record function id": 0, "Concrete Inputs": ["", "0", "19269120", "25692160", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[51384320], [], [], [], []], "Ev Idx": 6945 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273965328.395, "dur": 2.063, + "args": { + "External id": 4049035,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "[1]", "19269120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 6946 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336756, "tid": 1336756, + "ts": 1655273965339.255, "dur": 24.687, + "args": { + "External id": 4049036,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 6947 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273965341.315, "dur": 0.362, + "args": { + "External id": 4049037,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "19269120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6948 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273965343.050, "dur": 0.412, + "args": { + "External id": 4049038,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "19269376"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6949 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273965344.787, "dur": 0.220, + "args": { + "External id": 4049039,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "19793664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6950 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273965347.823, "dur": 1.271, + "args": { + "External id": 4049040,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "20317952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6951 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273965350.301, "dur": 0.348, + "args": { + "External id": 4049041,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "20842240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6952 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273965352.202, "dur": 1.629, + "args": { + "External id": 4049042,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "21366528"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6953 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273965355.084, "dur": 0.185, + "args": { + "External id": 4049043,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "21366784"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6954 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273965356.757, "dur": 0.281, + "args": { + "External id": 4049044,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "22808576"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6955 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273965359.885, "dur": 0.307, + "args": { + "External id": 4049045,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "24250368"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 6956 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336756, "tid": 1336756, + "ts": 1655273965374.401, "dur": 24.562, + "args": { + "External id": 4049046,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 6957 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 1336756, "tid": 1336756, + "ts": 1655273965477.643, "dur": 341.565, + "args": { + "External id": 4049047,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[51384320], [6423040], [], [], []], "Ev Idx": 6958 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336756, "tid": 1336756, + "ts": 1655273965506.686, "dur": 308.157, + "args": { + "External id": 4049048,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 3, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "3", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 51384320, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[6423040], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 6959, "In msg nelems": 6423040 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 1336756, "tid": 1336756, + "ts": 1655273965519.134, "dur": 290.298, + "args": { + "External id": 4049049,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[6423040]], "Ev Idx": 6960 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336756, "tid": 1336756, + "ts": 1655273965839.707, "dur": 2.658, + "args": { + "External id": 4049050,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "3", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 6961, "In msg nelems": 0, "Rank": 3, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.12)", "pid": 1336756, "tid": 1336756, + "ts": 1655273965922.994, "dur": 16949.168, + "args": { + "External id": 4049051,"Record function id": 0, "Ev Idx": 6962 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655273966046.650, "dur": 6.221, + "args": { + "External id": 4049052,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[51384320], []], "Ev Idx": 6963 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655273966056.508, "dur": 0.864, + "args": { + "External id": 4049053,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 6964 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655273966059.135, "dur": 2.241, + "args": { + "External id": 4049054,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 6965 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655273966063.057, "dur": 0.767, + "args": { + "External id": 4049055,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 6966 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655273966065.359, "dur": 0.838, + "args": { + "External id": 4049056,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 6967 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655273966067.526, "dur": 0.769, + "args": { + "External id": 4049057,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 6968 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655273966072.228, "dur": 0.691, + "args": { + "External id": 4049058,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 6969 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655273966074.388, "dur": 1.835, + "args": { + "External id": 4049059,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 6970 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655273966077.956, "dur": 0.633, + "args": { + "External id": 4049060,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 6971 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655273966080.017, "dur": 0.632, + "args": { + "External id": 4049061,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 6972 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 1336756, "tid": 1336756, + "ts": 1655273966102.008, "dur": 16734.080, + "args": { + "External id": 4049062,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 6973 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 1336756, "tid": 1336756, + "ts": 1655273966117.792, "dur": 16712.091, + "args": { + "External id": 4049063,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 6974 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655273966141.343, "dur": 12.185, + "args": { + "External id": 4049064,"Record function id": 0, "Concrete Inputs": ["[2133]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6975 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655273966156.664, "dur": 16642.660, + "args": { + "External id": 4049065,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], [], []], "Ev Idx": 6976 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336756, "tid": 1336756, + "ts": 1655273966159.018, "dur": 16639.750, + "args": { + "External id": 4049066,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], []], "Ev Idx": 6977 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273966164.650, "dur": 6.298, + "args": { + "External id": 4049067,"Record function id": 0, "Concrete Inputs": ["[2133]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6978 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1336756, + "ts": 1655273966172.827, "dur": 16623.330, + "args": { + "External id": 4049068,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[2133], [2133], []], "Ev Idx": 6979 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 1336756, "tid": 1336756, + "ts": 1655273983021.509, "dur": 36.036, + "args": { + "External id": 4049069,"Sequence number": 40618377, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 6980 + } + }, + { + "ph": "s", "id": 203, "pid": 1336756, "tid": 1336756, "ts": 1655273983021.509, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 1336756, "tid": 1336756, + "ts": 1655273983045.252, "dur": 7.551, + "args": { + "External id": 4049070,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[8388608, 2048, 1], [8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048], [16, 4096, 2048]], "Ev Idx": 6981 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655273983048.639, "dur": 3.819, + "args": { + "External id": 4049071,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 6982 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 1336756, "tid": 1336756, + "ts": 1655273983123.374, "dur": 70.559, + "args": { + "External id": 4049072,"Record function id": 0, "Ev Idx": 6983 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 1336756, "tid": 1336756, + "ts": 1655273983195.389, "dur": 1042.499, + "args": { + "External id": 4049073,"Record function id": 0, "Ev Idx": 6984 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 1336756, "tid": 1336756, + "ts": 1655273983235.841, "dur": 989.150, + "args": { + "External id": 4049074,"Sequence number": 40618378, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[8388608, 2048, 1], [1], [2048, 1], [2048, 1], [2048, 1], [32, 1], [32, 1], [2048, 1], [1], [2048, 1], [2048, 1], [5632, 1]], "Input Dims": [[16, 4096, 2048], [2048], [2048, 2048], [2048, 2048], [2048, 2048], [8192, 32], [8192, 32], [2048, 2048], [2048], [5632, 2048], [5632, 2048], [2048, 5632]], "Ev Idx": 6985 + } + }, + { + "ph": "s", "id": 202, "pid": 1336756, "tid": 1336756, "ts": 1655273983235.841, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 1336756, "tid": 1336756, + "ts": 1655273983299.172, "dur": 40.013, + "args": { + "External id": 4049075,"kernel_hash": "cd26ogptnjelaibpl2zumx5nxdttspqepvjkh7lpmsxbzrrexbxm", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "2048", "1", "9.9999999999999995e-07", "True", "2048", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/d2/cd26ogptnjelaibpl2zumx5nxdttspqepvjkh7lpmsxbzrrexbxm.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [65536, 2048], [2048], [65536], [], [], [], [], [], [], [], [], []], "Ev Idx": 6986 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655273983351.889, "dur": 119.965, + "args": { + "External id": 4049076,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 6987 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655273983484.269, "dur": 41.737, + "args": { + "External id": 4049077,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 6988 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655273983534.187, "dur": 30.737, + "args": { + "External id": 4049078,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 6989 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336756, "tid": 1336756, + "ts": 1655273983589.558, "dur": 24.123, + "args": { + "External id": 4049079,"kernel_hash": "cahe5odluo4swiyj4n2lohwh57qg5lym5qsijyjsjca7pvto5oka", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/ah/cahe5odluo4swiyj4n2lohwh57qg5lym5qsijyjsjca7pvto5oka.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 6990 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336756, "tid": 1336756, + "ts": 1655273983631.928, "dur": 13.662, + "args": { + "External id": 4049080,"kernel_hash": "cahe5odluo4swiyj4n2lohwh57qg5lym5qsijyjsjca7pvto5oka", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/ah/cahe5odluo4swiyj4n2lohwh57qg5lym5qsijyjsjca7pvto5oka.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 6991 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 1336756, "tid": 1336756, + "ts": 1655273983663.040, "dur": 121.569, + "args": { + "External id": 4049081,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.125", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [], [], [], [], [], [], [], []], "Ev Idx": 6992 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336756, "tid": 1336756, + "ts": 1655273983710.028, "dur": 10.547, + "args": { + "External id": 4049082,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[8388608, 2048, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [], [], [], [], []], "Ev Idx": 6993 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273983714.972, "dur": 4.917, + "args": { + "External id": 4049083,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "[8388608, 2048, 64, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6994 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655273983723.501, "dur": 5.044, + "args": { + "External id": 4049084,"Record function id": 0, "Concrete Inputs": ["[16, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6995 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655273983729.890, "dur": 1.215, + "args": { + "External id": 4049085,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6996 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655273983733.616, "dur": 3.709, + "args": { + "External id": 4049086,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 6997 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655273983794.885, "dur": 43.494, + "args": { + "External id": 4049087,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 6998 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_2", "pid": 1336756, "tid": 1336756, + "ts": 1655273983866.664, "dur": 24.940, + "args": { + "External id": 4049088,"kernel_hash": "ckbsutlugbs4qoncxuwq6kkwome3xojo3ke4p7z74lcl5h4q62to", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "2048", "1", "9.9999999999999995e-07", "True", "2048", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/kb/ckbsutlugbs4qoncxuwq6kkwome3xojo3ke4p7z74lcl5h4q62to.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [1], [2048, 1], [2048, 1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [65536, 2048], [2048], [65536, 2048], [65536, 2048], [65536], [], [], [], [], [], [], [], [], []], "Ev Idx": 6999 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655273983899.796, "dur": 41.373, + "args": { + "External id": 4049089,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [5632, 1]], "Input Dims": [[65536, 2048], [2048, 5632], [65536, 5632]], "Ev Idx": 7000 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655273983949.336, "dur": 70.380, + "args": { + "External id": 4049090,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [5632, 1]], "Input Dims": [[65536, 2048], [2048, 5632], [65536, 5632]], "Ev Idx": 7001 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 1336756, "tid": 1336756, + "ts": 1655273984050.945, "dur": 29.524, + "args": { + "External id": 4049091,"kernel_hash": "cgh2wg2b6li2ipjwrhdr326ycb37fu4v576nwebfoyhwx5kppapn", "grid": "grid(369098752,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "369098752"], "kernel_file": "/tmp/torchinductor_cvm/gh/cgh2wg2b6li2ipjwrhdr326ycb37fu4v576nwebfoyhwx5kppapn.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[5632, 1], [5632, 1], [23068672, 5632, 1], []], "Input Dims": [[65536, 5632], [65536, 5632], [16, 4096, 5632], []], "Ev Idx": 7002 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655273984088.470, "dur": 38.461, + "args": { + "External id": 4049092,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [1, 5632], [2048, 1]], "Input Dims": [[65536, 5632], [5632, 2048], [65536, 2048]], "Ev Idx": 7003 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 1336756, "tid": 1336756, + "ts": 1655273984145.161, "dur": 17.018, + "args": { + "External id": 4049093,"kernel_hash": "cta7vcczabyyuqarwmn4dcnazkxudhfwrvnick7ql5cmsd5lz4rz", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/ta/cta7vcczabyyuqarwmn4dcnazkxudhfwrvnick7ql5cmsd5lz4rz.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[8388608, 2048, 1], [2048, 1], []], "Input Dims": [[16, 4096, 2048], [65536, 2048], []], "Ev Idx": 7004 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.12)", "pid": 1336756, "tid": 1336756, + "ts": 1655273984298.651, "dur": 69.040, + "args": { + "External id": 4049094,"Record function id": 0, "Ev Idx": 7005 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 1336756, "tid": 1336756, + "ts": 1655273984456.944, "dur": 46.349, + "args": { + "External id": 4049095,"Record function id": 0, "Ev Idx": 7006 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.13)", "pid": 1336756, "tid": 1336756, + "ts": 1655273984512.688, "dur": 18109.146, + "args": { + "External id": 4049096,"Record function id": 0, "Ev Idx": 7007 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.13)", "pid": 1336756, "tid": 1336756, + "ts": 1655273984522.492, "dur": 846.469, + "args": { + "External id": 4049097,"Record function id": 0, "Ev Idx": 7008 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655273984596.255, "dur": 8.520, + "args": { + "External id": 4049098,"Record function id": 0, "Concrete Inputs": ["[6423040]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7009 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336756, "tid": 1336756, + "ts": 1655273984617.608, "dur": 33.489, + "args": { + "External id": 4049099,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 7010 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273984622.730, "dur": 2.257, + "args": { + "External id": 4049100,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7011 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273984629.200, "dur": 0.332, + "args": { + "External id": 4049101,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7012 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273984631.036, "dur": 0.251, + "args": { + "External id": 4049102,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7013 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273984632.826, "dur": 0.163, + "args": { + "External id": 4049103,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7014 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273984635.460, "dur": 0.559, + "args": { + "External id": 4049104,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7015 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273984637.410, "dur": 0.175, + "args": { + "External id": 4049105,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7016 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273984639.283, "dur": 3.095, + "args": { + "External id": 4049106,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7017 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273984643.928, "dur": 0.178, + "args": { + "External id": 4049107,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7018 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273984645.555, "dur": 0.140, + "args": { + "External id": 4049108,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7019 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336756, "tid": 1336756, + "ts": 1655273984661.475, "dur": 39.115, + "args": { + "External id": 4049109,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 7020 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 1336756, "tid": 1336756, + "ts": 1655273984732.042, "dur": 106.881, + "args": { + "External id": 4049110,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "6423040", "8", "3", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [], [], [], [], [], []], "Ev Idx": 7021 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655273984742.520, "dur": 3.406, + "args": { + "External id": 4049111,"Record function id": 0, "Concrete Inputs": ["[51384320]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7022 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 1336756, "tid": 1336756, + "ts": 1655273984750.944, "dur": 9.485, + "args": { + "External id": 4049112,"Record function id": 0, "Concrete Inputs": ["", "0", "19269120", "6423040"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 7023 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1336756, + "ts": 1655273984754.862, "dur": 5.154, + "args": { + "External id": 4049113,"Record function id": 0, "Concrete Inputs": ["", "0", "19269120", "25692160", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[51384320], [], [], [], []], "Ev Idx": 7024 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273984758.374, "dur": 0.393, + "args": { + "External id": 4049114,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "[1]", "19269120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 7025 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336756, "tid": 1336756, + "ts": 1655273984767.407, "dur": 26.935, + "args": { + "External id": 4049115,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 7026 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273984769.321, "dur": 2.045, + "args": { + "External id": 4049116,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "19269120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7027 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273984772.649, "dur": 0.407, + "args": { + "External id": 4049117,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "19269376"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7028 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273984774.410, "dur": 0.396, + "args": { + "External id": 4049118,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "19793664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7029 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273984777.971, "dur": 1.440, + "args": { + "External id": 4049119,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "20317952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7030 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273984780.693, "dur": 0.232, + "args": { + "External id": 4049120,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "20842240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7031 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273984782.172, "dur": 0.244, + "args": { + "External id": 4049121,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "21366528"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7032 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273984785.409, "dur": 0.335, + "args": { + "External id": 4049122,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "21366784"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7033 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273984786.960, "dur": 0.178, + "args": { + "External id": 4049123,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "22808576"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7034 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273984788.452, "dur": 1.757, + "args": { + "External id": 4049124,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "24250368"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7035 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336756, "tid": 1336756, + "ts": 1655273984806.111, "dur": 25.299, + "args": { + "External id": 4049125,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 7036 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 1336756, "tid": 1336756, + "ts": 1655273984891.100, "dur": 384.007, + "args": { + "External id": 4049126,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[51384320], [6423040], [], [], []], "Ev Idx": 7037 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336756, "tid": 1336756, + "ts": 1655273984921.125, "dur": 348.740, + "args": { + "External id": 4049127,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 3, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "3", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 51384320, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[6423040], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 7038, "In msg nelems": 6423040 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 1336756, "tid": 1336756, + "ts": 1655273984930.682, "dur": 332.776, + "args": { + "External id": 4049128,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[6423040]], "Ev Idx": 7039 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336756, "tid": 1336756, + "ts": 1655273985299.041, "dur": 2.604, + "args": { + "External id": 4049129,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "3", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 7040, "In msg nelems": 0, "Rank": 3, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.13)", "pid": 1336756, "tid": 1336756, + "ts": 1655273985390.160, "dur": 17042.293, + "args": { + "External id": 4049130,"Record function id": 0, "Ev Idx": 7041 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655273985501.590, "dur": 6.359, + "args": { + "External id": 4049131,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[51384320], []], "Ev Idx": 7042 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655273985511.901, "dur": 0.797, + "args": { + "External id": 4049132,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 7043 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655273985514.171, "dur": 1.902, + "args": { + "External id": 4049133,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 7044 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655273985517.735, "dur": 0.786, + "args": { + "External id": 4049134,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 7045 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655273985519.838, "dur": 0.688, + "args": { + "External id": 4049135,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 7046 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655273985521.870, "dur": 0.763, + "args": { + "External id": 4049136,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 7047 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655273985525.746, "dur": 0.721, + "args": { + "External id": 4049137,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 7048 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655273985528.306, "dur": 1.820, + "args": { + "External id": 4049138,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 7049 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655273985531.590, "dur": 0.577, + "args": { + "External id": 4049139,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 7050 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655273985533.558, "dur": 0.475, + "args": { + "External id": 4049140,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 7051 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 1336756, "tid": 1336756, + "ts": 1655273985554.292, "dur": 16831.052, + "args": { + "External id": 4049141,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 7052 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 1336756, "tid": 1336756, + "ts": 1655273985569.640, "dur": 16809.363, + "args": { + "External id": 4049142,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 7053 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655273985592.376, "dur": 12.316, + "args": { + "External id": 4049143,"Record function id": 0, "Concrete Inputs": ["[2133]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7054 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655273985607.586, "dur": 16740.256, + "args": { + "External id": 4049144,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], [], []], "Ev Idx": 7055 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336756, "tid": 1336756, + "ts": 1655273985609.797, "dur": 16737.518, + "args": { + "External id": 4049145,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], []], "Ev Idx": 7056 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655273985614.835, "dur": 5.133, + "args": { + "External id": 4049146,"Record function id": 0, "Concrete Inputs": ["[2133]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7057 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1336756, + "ts": 1655273985621.764, "dur": 16722.985, + "args": { + "External id": 4049147,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[2133], [2133], []], "Ev Idx": 7058 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 1336756, "tid": 1336756, + "ts": 1655274002562.200, "dur": 34.834, + "args": { + "External id": 4049148,"Sequence number": 40618379, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 7059 + } + }, + { + "ph": "s", "id": 201, "pid": 1336756, "tid": 1336756, "ts": 1655274002562.200, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 1336756, "tid": 1336756, + "ts": 1655274002585.006, "dur": 7.483, + "args": { + "External id": 4049149,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[8388608, 2048, 1], [8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048], [16, 4096, 2048]], "Ev Idx": 7060 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274002588.215, "dur": 4.004, + "args": { + "External id": 4049150,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 7061 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 1336756, "tid": 1336756, + "ts": 1655274002657.973, "dur": 68.924, + "args": { + "External id": 4049151,"Record function id": 0, "Ev Idx": 7062 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 1336756, "tid": 1336756, + "ts": 1655274002728.543, "dur": 1042.072, + "args": { + "External id": 4049152,"Record function id": 0, "Ev Idx": 7063 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 1336756, "tid": 1336756, + "ts": 1655274002766.627, "dur": 991.554, + "args": { + "External id": 4049153,"Sequence number": 40618380, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[8388608, 2048, 1], [1], [2048, 1], [2048, 1], [2048, 1], [32, 1], [32, 1], [2048, 1], [1], [2048, 1], [2048, 1], [5632, 1]], "Input Dims": [[16, 4096, 2048], [2048], [2048, 2048], [2048, 2048], [2048, 2048], [8192, 32], [8192, 32], [2048, 2048], [2048], [5632, 2048], [5632, 2048], [2048, 5632]], "Ev Idx": 7064 + } + }, + { + "ph": "s", "id": 200, "pid": 1336756, "tid": 1336756, "ts": 1655274002766.627, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 1336756, "tid": 1336756, + "ts": 1655274002829.755, "dur": 39.432, + "args": { + "External id": 4049154,"kernel_hash": "cd26ogptnjelaibpl2zumx5nxdttspqepvjkh7lpmsxbzrrexbxm", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "2048", "1", "9.9999999999999995e-07", "True", "2048", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/d2/cd26ogptnjelaibpl2zumx5nxdttspqepvjkh7lpmsxbzrrexbxm.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [65536, 2048], [2048], [65536], [], [], [], [], [], [], [], [], []], "Ev Idx": 7065 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274002880.039, "dur": 138.233, + "args": { + "External id": 4049155,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 7066 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274003031.766, "dur": 44.695, + "args": { + "External id": 4049156,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 7067 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274003084.823, "dur": 31.949, + "args": { + "External id": 4049157,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 7068 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336756, "tid": 1336756, + "ts": 1655274003142.688, "dur": 26.476, + "args": { + "External id": 4049158,"kernel_hash": "cahe5odluo4swiyj4n2lohwh57qg5lym5qsijyjsjca7pvto5oka", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/ah/cahe5odluo4swiyj4n2lohwh57qg5lym5qsijyjsjca7pvto5oka.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 7069 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336756, "tid": 1336756, + "ts": 1655274003185.375, "dur": 13.929, + "args": { + "External id": 4049159,"kernel_hash": "cahe5odluo4swiyj4n2lohwh57qg5lym5qsijyjsjca7pvto5oka", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/ah/cahe5odluo4swiyj4n2lohwh57qg5lym5qsijyjsjca7pvto5oka.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 7070 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 1336756, "tid": 1336756, + "ts": 1655274003217.396, "dur": 124.071, + "args": { + "External id": 4049160,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.125", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [], [], [], [], [], [], [], []], "Ev Idx": 7071 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336756, "tid": 1336756, + "ts": 1655274003266.462, "dur": 10.484, + "args": { + "External id": 4049161,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[8388608, 2048, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [], [], [], [], []], "Ev Idx": 7072 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274003271.338, "dur": 4.853, + "args": { + "External id": 4049162,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "[8388608, 2048, 64, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7073 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274003279.620, "dur": 4.816, + "args": { + "External id": 4049163,"Record function id": 0, "Concrete Inputs": ["[16, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7074 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274003286.029, "dur": 1.149, + "args": { + "External id": 4049164,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7075 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274003289.539, "dur": 3.787, + "args": { + "External id": 4049165,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7076 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274003352.157, "dur": 44.445, + "args": { + "External id": 4049166,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 7077 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_2", "pid": 1336756, "tid": 1336756, + "ts": 1655274003440.936, "dur": 27.730, + "args": { + "External id": 4049167,"kernel_hash": "ckbsutlugbs4qoncxuwq6kkwome3xojo3ke4p7z74lcl5h4q62to", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "2048", "1", "9.9999999999999995e-07", "True", "2048", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/kb/ckbsutlugbs4qoncxuwq6kkwome3xojo3ke4p7z74lcl5h4q62to.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [1], [2048, 1], [2048, 1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [65536, 2048], [2048], [65536, 2048], [65536, 2048], [65536], [], [], [], [], [], [], [], [], []], "Ev Idx": 7078 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274003479.031, "dur": 44.629, + "args": { + "External id": 4049168,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [5632, 1]], "Input Dims": [[65536, 2048], [2048, 5632], [65536, 5632]], "Ev Idx": 7079 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274003531.793, "dur": 35.105, + "args": { + "External id": 4049169,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [5632, 1]], "Input Dims": [[65536, 2048], [2048, 5632], [65536, 5632]], "Ev Idx": 7080 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 1336756, "tid": 1336756, + "ts": 1655274003589.631, "dur": 24.657, + "args": { + "External id": 4049170,"kernel_hash": "cgh2wg2b6li2ipjwrhdr326ycb37fu4v576nwebfoyhwx5kppapn", "grid": "grid(369098752,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "369098752"], "kernel_file": "/tmp/torchinductor_cvm/gh/cgh2wg2b6li2ipjwrhdr326ycb37fu4v576nwebfoyhwx5kppapn.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[5632, 1], [5632, 1], [23068672, 5632, 1], []], "Input Dims": [[65536, 5632], [65536, 5632], [16, 4096, 5632], []], "Ev Idx": 7081 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274003619.695, "dur": 34.086, + "args": { + "External id": 4049171,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [1, 5632], [2048, 1]], "Input Dims": [[65536, 5632], [5632, 2048], [65536, 2048]], "Ev Idx": 7082 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 1336756, "tid": 1336756, + "ts": 1655274003672.475, "dur": 17.067, + "args": { + "External id": 4049172,"kernel_hash": "cta7vcczabyyuqarwmn4dcnazkxudhfwrvnick7ql5cmsd5lz4rz", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/ta/cta7vcczabyyuqarwmn4dcnazkxudhfwrvnick7ql5cmsd5lz4rz.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[8388608, 2048, 1], [2048, 1], []], "Input Dims": [[16, 4096, 2048], [65536, 2048], []], "Ev Idx": 7083 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.13)", "pid": 1336756, "tid": 1336756, + "ts": 1655274003833.140, "dur": 69.666, + "args": { + "External id": 4049173,"Record function id": 0, "Ev Idx": 7084 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 1336756, "tid": 1336756, + "ts": 1655274003972.523, "dur": 88.533, + "args": { + "External id": 4049174,"Record function id": 0, "Ev Idx": 7085 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.14)", "pid": 1336756, "tid": 1336756, + "ts": 1655274004071.852, "dur": 18221.700, + "args": { + "External id": 4049175,"Record function id": 0, "Ev Idx": 7086 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.14)", "pid": 1336756, "tid": 1336756, + "ts": 1655274004079.921, "dur": 869.399, + "args": { + "External id": 4049176,"Record function id": 0, "Ev Idx": 7087 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274004154.823, "dur": 9.377, + "args": { + "External id": 4049177,"Record function id": 0, "Concrete Inputs": ["[6423040]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7088 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336756, "tid": 1336756, + "ts": 1655274004177.703, "dur": 38.866, + "args": { + "External id": 4049178,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 7089 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274004182.727, "dur": 2.336, + "args": { + "External id": 4049179,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7090 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274004189.499, "dur": 0.264, + "args": { + "External id": 4049180,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7091 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274004190.870, "dur": 0.342, + "args": { + "External id": 4049181,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7092 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274004192.718, "dur": 0.511, + "args": { + "External id": 4049182,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7093 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274004196.245, "dur": 0.435, + "args": { + "External id": 4049183,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7094 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274004197.912, "dur": 0.308, + "args": { + "External id": 4049184,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7095 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274004204.201, "dur": 3.416, + "args": { + "External id": 4049185,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7096 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274004209.352, "dur": 0.292, + "args": { + "External id": 4049186,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7097 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274004211.004, "dur": 0.213, + "args": { + "External id": 4049187,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7098 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336756, "tid": 1336756, + "ts": 1655274004228.800, "dur": 40.233, + "args": { + "External id": 4049188,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 7099 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 1336756, "tid": 1336756, + "ts": 1655274004300.271, "dur": 103.152, + "args": { + "External id": 4049189,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "6423040", "8", "3", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [], [], [], [], [], []], "Ev Idx": 7100 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274004310.787, "dur": 5.537, + "args": { + "External id": 4049190,"Record function id": 0, "Concrete Inputs": ["[51384320]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7101 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 1336756, "tid": 1336756, + "ts": 1655274004321.478, "dur": 10.259, + "args": { + "External id": 4049191,"Record function id": 0, "Concrete Inputs": ["", "0", "19269120", "6423040"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 7102 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1336756, + "ts": 1655274004326.019, "dur": 5.331, + "args": { + "External id": 4049192,"Record function id": 0, "Concrete Inputs": ["", "0", "19269120", "25692160", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[51384320], [], [], [], []], "Ev Idx": 7103 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274004329.580, "dur": 0.551, + "args": { + "External id": 4049193,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "[1]", "19269120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 7104 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336756, "tid": 1336756, + "ts": 1655274004339.367, "dur": 26.067, + "args": { + "External id": 4049194,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 7105 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274004341.295, "dur": 0.444, + "args": { + "External id": 4049195,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "19269120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7106 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274004343.135, "dur": 2.104, + "args": { + "External id": 4049196,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "19269376"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7107 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274004346.570, "dur": 0.380, + "args": { + "External id": 4049197,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "19793664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7108 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274004348.317, "dur": 1.302, + "args": { + "External id": 4049198,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "20317952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7109 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274004352.710, "dur": 0.362, + "args": { + "External id": 4049199,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "20842240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7110 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274004354.422, "dur": 0.317, + "args": { + "External id": 4049200,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "21366528"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7111 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274004355.962, "dur": 0.268, + "args": { + "External id": 4049201,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "21366784"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7112 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274004359.637, "dur": 0.286, + "args": { + "External id": 4049202,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "22808576"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7113 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274004361.076, "dur": 0.255, + "args": { + "External id": 4049203,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "24250368"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7114 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336756, "tid": 1336756, + "ts": 1655274004374.388, "dur": 21.498, + "args": { + "External id": 4049204,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 7115 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 1336756, "tid": 1336756, + "ts": 1655274004474.495, "dur": 384.988, + "args": { + "External id": 4049205,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[51384320], [6423040], [], [], []], "Ev Idx": 7116 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336756, "tid": 1336756, + "ts": 1655274004504.615, "dur": 350.128, + "args": { + "External id": 4049206,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 3, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "3", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 51384320, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[6423040], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 7117, "In msg nelems": 6423040 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 1336756, "tid": 1336756, + "ts": 1655274004514.942, "dur": 334.062, + "args": { + "External id": 4049207,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[6423040]], "Ev Idx": 7118 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336756, "tid": 1336756, + "ts": 1655274004881.264, "dur": 2.395, + "args": { + "External id": 4049208,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "3", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 7119, "In msg nelems": 0, "Rank": 3, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.14)", "pid": 1336756, "tid": 1336756, + "ts": 1655274004968.808, "dur": 17143.909, + "args": { + "External id": 4049209,"Record function id": 0, "Ev Idx": 7120 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274005104.678, "dur": 6.446, + "args": { + "External id": 4049210,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[51384320], []], "Ev Idx": 7121 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274005114.739, "dur": 0.976, + "args": { + "External id": 4049211,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 7122 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274005117.463, "dur": 2.088, + "args": { + "External id": 4049212,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 7123 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274005121.582, "dur": 0.761, + "args": { + "External id": 4049213,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 7124 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274005123.803, "dur": 0.746, + "args": { + "External id": 4049214,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 7125 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274005125.844, "dur": 0.859, + "args": { + "External id": 4049215,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 7126 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274005130.220, "dur": 0.802, + "args": { + "External id": 4049216,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 7127 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274005132.385, "dur": 1.636, + "args": { + "External id": 4049217,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 7128 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274005135.273, "dur": 0.965, + "args": { + "External id": 4049218,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 7129 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274005137.907, "dur": 0.585, + "args": { + "External id": 4049219,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 7130 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 1336756, "tid": 1336756, + "ts": 1655274005159.157, "dur": 16916.687, + "args": { + "External id": 4049220,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 7131 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 1336756, "tid": 1336756, + "ts": 1655274005174.120, "dur": 16895.309, + "args": { + "External id": 4049221,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 7132 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274005199.250, "dur": 12.695, + "args": { + "External id": 4049222,"Record function id": 0, "Concrete Inputs": ["[2133]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7133 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655274005214.979, "dur": 16823.133, + "args": { + "External id": 4049223,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], [], []], "Ev Idx": 7134 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336756, "tid": 1336756, + "ts": 1655274005217.568, "dur": 16819.928, + "args": { + "External id": 4049224,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], []], "Ev Idx": 7135 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274005223.291, "dur": 5.528, + "args": { + "External id": 4049225,"Record function id": 0, "Concrete Inputs": ["[2133]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7136 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1336756, + "ts": 1655274005230.491, "dur": 16804.150, + "args": { + "External id": 4049226,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[2133], [2133], []], "Ev Idx": 7137 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 1336756, "tid": 1336756, + "ts": 1655274022235.570, "dur": 34.651, + "args": { + "External id": 4049227,"Sequence number": 40618381, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 7138 + } + }, + { + "ph": "s", "id": 199, "pid": 1336756, "tid": 1336756, "ts": 1655274022235.570, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 1336756, "tid": 1336756, + "ts": 1655274022259.121, "dur": 6.708, + "args": { + "External id": 4049228,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[8388608, 2048, 1], [8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048], [16, 4096, 2048]], "Ev Idx": 7139 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274022262.105, "dur": 3.543, + "args": { + "External id": 4049229,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 7140 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 1336756, "tid": 1336756, + "ts": 1655274022328.179, "dur": 72.105, + "args": { + "External id": 4049230,"Record function id": 0, "Ev Idx": 7141 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 1336756, "tid": 1336756, + "ts": 1655274022402.007, "dur": 1072.601, + "args": { + "External id": 4049231,"Record function id": 0, "Ev Idx": 7142 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 1336756, "tid": 1336756, + "ts": 1655274022455.997, "dur": 1004.841, + "args": { + "External id": 4049232,"Sequence number": 40618382, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[8388608, 2048, 1], [1], [2048, 1], [2048, 1], [2048, 1], [32, 1], [32, 1], [2048, 1], [1], [2048, 1], [2048, 1], [5632, 1]], "Input Dims": [[16, 4096, 2048], [2048], [2048, 2048], [2048, 2048], [2048, 2048], [8192, 32], [8192, 32], [2048, 2048], [2048], [5632, 2048], [5632, 2048], [2048, 5632]], "Ev Idx": 7143 + } + }, + { + "ph": "s", "id": 198, "pid": 1336756, "tid": 1336756, "ts": 1655274022455.997, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 1336756, "tid": 1336756, + "ts": 1655274022520.506, "dur": 39.944, + "args": { + "External id": 4049233,"kernel_hash": "cd26ogptnjelaibpl2zumx5nxdttspqepvjkh7lpmsxbzrrexbxm", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "2048", "1", "9.9999999999999995e-07", "True", "2048", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/d2/cd26ogptnjelaibpl2zumx5nxdttspqepvjkh7lpmsxbzrrexbxm.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [65536, 2048], [2048], [65536], [], [], [], [], [], [], [], [], []], "Ev Idx": 7144 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274022572.906, "dur": 103.287, + "args": { + "External id": 4049234,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 7145 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274022685.726, "dur": 39.198, + "args": { + "External id": 4049235,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 7146 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274022733.344, "dur": 31.010, + "args": { + "External id": 4049236,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 7147 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336756, "tid": 1336756, + "ts": 1655274022788.542, "dur": 25.007, + "args": { + "External id": 4049237,"kernel_hash": "cahe5odluo4swiyj4n2lohwh57qg5lym5qsijyjsjca7pvto5oka", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/ah/cahe5odluo4swiyj4n2lohwh57qg5lym5qsijyjsjca7pvto5oka.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 7148 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336756, "tid": 1336756, + "ts": 1655274022830.872, "dur": 15.245, + "args": { + "External id": 4049238,"kernel_hash": "cahe5odluo4swiyj4n2lohwh57qg5lym5qsijyjsjca7pvto5oka", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/ah/cahe5odluo4swiyj4n2lohwh57qg5lym5qsijyjsjca7pvto5oka.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 7149 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 1336756, "tid": 1336756, + "ts": 1655274022863.454, "dur": 163.071, + "args": { + "External id": 4049239,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.125", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [], [], [], [], [], [], [], []], "Ev Idx": 7150 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336756, "tid": 1336756, + "ts": 1655274022910.485, "dur": 10.512, + "args": { + "External id": 4049240,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[8388608, 2048, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [], [], [], [], []], "Ev Idx": 7151 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274022915.579, "dur": 4.730, + "args": { + "External id": 4049241,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "[8388608, 2048, 64, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7152 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274022923.820, "dur": 5.326, + "args": { + "External id": 4049242,"Record function id": 0, "Concrete Inputs": ["[16, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7153 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274022930.559, "dur": 1.049, + "args": { + "External id": 4049243,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7154 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274022934.141, "dur": 3.591, + "args": { + "External id": 4049244,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7155 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274023047.544, "dur": 55.503, + "args": { + "External id": 4049245,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 7156 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_2", "pid": 1336756, "tid": 1336756, + "ts": 1655274023138.873, "dur": 27.794, + "args": { + "External id": 4049246,"kernel_hash": "ckbsutlugbs4qoncxuwq6kkwome3xojo3ke4p7z74lcl5h4q62to", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "2048", "1", "9.9999999999999995e-07", "True", "2048", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/kb/ckbsutlugbs4qoncxuwq6kkwome3xojo3ke4p7z74lcl5h4q62to.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [1], [2048, 1], [2048, 1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [65536, 2048], [2048], [65536, 2048], [65536, 2048], [65536], [], [], [], [], [], [], [], [], []], "Ev Idx": 7157 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274023175.509, "dur": 41.963, + "args": { + "External id": 4049247,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [5632, 1]], "Input Dims": [[65536, 2048], [2048, 5632], [65536, 5632]], "Ev Idx": 7158 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274023225.343, "dur": 34.979, + "args": { + "External id": 4049248,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [5632, 1]], "Input Dims": [[65536, 2048], [2048, 5632], [65536, 5632]], "Ev Idx": 7159 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 1336756, "tid": 1336756, + "ts": 1655274023281.652, "dur": 23.720, + "args": { + "External id": 4049249,"kernel_hash": "cgh2wg2b6li2ipjwrhdr326ycb37fu4v576nwebfoyhwx5kppapn", "grid": "grid(369098752,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "369098752"], "kernel_file": "/tmp/torchinductor_cvm/gh/cgh2wg2b6li2ipjwrhdr326ycb37fu4v576nwebfoyhwx5kppapn.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[5632, 1], [5632, 1], [23068672, 5632, 1], []], "Input Dims": [[65536, 5632], [65536, 5632], [16, 4096, 5632], []], "Ev Idx": 7160 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274023310.973, "dur": 33.626, + "args": { + "External id": 4049250,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [1, 5632], [2048, 1]], "Input Dims": [[65536, 5632], [5632, 2048], [65536, 2048]], "Ev Idx": 7161 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 1336756, "tid": 1336756, + "ts": 1655274023365.432, "dur": 16.403, + "args": { + "External id": 4049251,"kernel_hash": "cta7vcczabyyuqarwmn4dcnazkxudhfwrvnick7ql5cmsd5lz4rz", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/ta/cta7vcczabyyuqarwmn4dcnazkxudhfwrvnick7ql5cmsd5lz4rz.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[8388608, 2048, 1], [2048, 1], []], "Input Dims": [[16, 4096, 2048], [65536, 2048], []], "Ev Idx": 7162 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.14)", "pid": 1336756, "tid": 1336756, + "ts": 1655274023538.696, "dur": 71.421, + "args": { + "External id": 4049252,"Record function id": 0, "Ev Idx": 7163 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 1336756, "tid": 1336756, + "ts": 1655274023681.051, "dur": 46.649, + "args": { + "External id": 4049253,"Record function id": 0, "Ev Idx": 7164 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.15)", "pid": 1336756, "tid": 1336756, + "ts": 1655274023736.359, "dur": 18115.882, + "args": { + "External id": 4049254,"Record function id": 0, "Ev Idx": 7165 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.15)", "pid": 1336756, "tid": 1336756, + "ts": 1655274023744.583, "dur": 872.853, + "args": { + "External id": 4049255,"Record function id": 0, "Ev Idx": 7166 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274023818.673, "dur": 8.367, + "args": { + "External id": 4049256,"Record function id": 0, "Concrete Inputs": ["[6423040]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7167 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336756, "tid": 1336756, + "ts": 1655274023840.757, "dur": 34.617, + "args": { + "External id": 4049257,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 7168 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274023845.870, "dur": 2.134, + "args": { + "External id": 4049258,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7169 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274023852.101, "dur": 0.250, + "args": { + "External id": 4049259,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7170 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274023854.016, "dur": 0.441, + "args": { + "External id": 4049260,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7171 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274023856.151, "dur": 0.420, + "args": { + "External id": 4049261,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7172 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274023859.852, "dur": 0.289, + "args": { + "External id": 4049262,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7173 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274023861.592, "dur": 0.458, + "args": { + "External id": 4049263,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7174 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274023863.906, "dur": 2.641, + "args": { + "External id": 4049264,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7175 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274023867.637, "dur": 0.337, + "args": { + "External id": 4049265,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7176 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274023869.484, "dur": 0.483, + "args": { + "External id": 4049266,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7177 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336756, "tid": 1336756, + "ts": 1655274023885.184, "dur": 37.961, + "args": { + "External id": 4049267,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 7178 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 1336756, "tid": 1336756, + "ts": 1655274023955.199, "dur": 161.271, + "args": { + "External id": 4049268,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "6423040", "8", "3", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [], [], [], [], [], []], "Ev Idx": 7179 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274023965.739, "dur": 3.425, + "args": { + "External id": 4049269,"Record function id": 0, "Concrete Inputs": ["[51384320]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7180 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 1336756, "tid": 1336756, + "ts": 1655274023974.016, "dur": 48.086, + "args": { + "External id": 4049270,"Record function id": 0, "Concrete Inputs": ["", "0", "19269120", "6423040"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 7181 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1336756, + "ts": 1655274023978.071, "dur": 43.564, + "args": { + "External id": 4049271,"Record function id": 0, "Concrete Inputs": ["", "0", "19269120", "25692160", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[51384320], [], [], [], []], "Ev Idx": 7182 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274024018.226, "dur": 1.185, + "args": { + "External id": 4049272,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "[1]", "19269120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 7183 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336756, "tid": 1336756, + "ts": 1655274024031.762, "dur": 29.233, + "args": { + "External id": 4049273,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 7184 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274024034.621, "dur": 2.288, + "args": { + "External id": 4049274,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "19269120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7185 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274024038.338, "dur": 0.282, + "args": { + "External id": 4049275,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "19269376"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7186 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274024040.053, "dur": 0.378, + "args": { + "External id": 4049276,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "19793664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7187 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274024043.428, "dur": 1.346, + "args": { + "External id": 4049277,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "20317952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7188 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274024046.560, "dur": 0.271, + "args": { + "External id": 4049278,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "20842240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7189 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274024048.159, "dur": 0.138, + "args": { + "External id": 4049279,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "21366528"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7190 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274024051.604, "dur": 0.308, + "args": { + "External id": 4049280,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "21366784"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7191 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274024053.357, "dur": 0.512, + "args": { + "External id": 4049281,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "22808576"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7192 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274024055.464, "dur": 1.642, + "args": { + "External id": 4049282,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "24250368"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7193 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336756, "tid": 1336756, + "ts": 1655274024081.474, "dur": 26.797, + "args": { + "External id": 4049283,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 7194 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 1336756, "tid": 1336756, + "ts": 1655274024171.761, "dur": 354.132, + "args": { + "External id": 4049284,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[51384320], [6423040], [], [], []], "Ev Idx": 7195 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336756, "tid": 1336756, + "ts": 1655274024202.236, "dur": 318.600, + "args": { + "External id": 4049285,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 3, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "3", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 51384320, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[6423040], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 7196, "In msg nelems": 6423040 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 1336756, "tid": 1336756, + "ts": 1655274024214.399, "dur": 300.386, + "args": { + "External id": 4049286,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[6423040]], "Ev Idx": 7197 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336756, "tid": 1336756, + "ts": 1655274024549.572, "dur": 2.242, + "args": { + "External id": 4049287,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "3", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 7198, "In msg nelems": 0, "Rank": 3, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.15)", "pid": 1336756, "tid": 1336756, + "ts": 1655274024637.636, "dur": 17027.298, + "args": { + "External id": 4049288,"Record function id": 0, "Ev Idx": 7199 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274024727.123, "dur": 5.942, + "args": { + "External id": 4049289,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[51384320], []], "Ev Idx": 7200 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274024736.614, "dur": 0.765, + "args": { + "External id": 4049290,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 7201 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274024739.055, "dur": 2.356, + "args": { + "External id": 4049291,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 7202 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274024743.043, "dur": 0.696, + "args": { + "External id": 4049292,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 7203 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274024745.263, "dur": 0.612, + "args": { + "External id": 4049293,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 7204 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274024747.313, "dur": 0.674, + "args": { + "External id": 4049294,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 7205 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274024751.028, "dur": 0.734, + "args": { + "External id": 4049295,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 7206 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274024753.764, "dur": 1.561, + "args": { + "External id": 4049296,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 7207 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274024756.793, "dur": 0.653, + "args": { + "External id": 4049297,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 7208 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274024759.163, "dur": 0.592, + "args": { + "External id": 4049298,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 7209 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 1336756, "tid": 1336756, + "ts": 1655274024779.269, "dur": 16847.781, + "args": { + "External id": 4049299,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 7210 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 1336756, "tid": 1336756, + "ts": 1655274024794.507, "dur": 16825.606, + "args": { + "External id": 4049300,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 7211 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274024815.893, "dur": 12.438, + "args": { + "External id": 4049301,"Record function id": 0, "Concrete Inputs": ["[2133]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7212 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655274024831.453, "dur": 16757.819, + "args": { + "External id": 4049302,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], [], []], "Ev Idx": 7213 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336756, "tid": 1336756, + "ts": 1655274024834.044, "dur": 16754.749, + "args": { + "External id": 4049303,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], []], "Ev Idx": 7214 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274024839.646, "dur": 5.325, + "args": { + "External id": 4049304,"Record function id": 0, "Concrete Inputs": ["[2133]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7215 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1336756, + "ts": 1655274024846.750, "dur": 16738.695, + "args": { + "External id": 4049305,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[2133], [2133], []], "Ev Idx": 7216 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 1336756, "tid": 1336756, + "ts": 1655274041789.288, "dur": 38.244, + "args": { + "External id": 4049306,"Sequence number": 40618383, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 7217 + } + }, + { + "ph": "s", "id": 197, "pid": 1336756, "tid": 1336756, "ts": 1655274041789.288, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 1336756, "tid": 1336756, + "ts": 1655274041815.448, "dur": 7.641, + "args": { + "External id": 4049307,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[8388608, 2048, 1], [8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048], [16, 4096, 2048]], "Ev Idx": 7218 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274041818.705, "dur": 4.208, + "args": { + "External id": 4049308,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 7219 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 1336756, "tid": 1336756, + "ts": 1655274041889.270, "dur": 69.743, + "args": { + "External id": 4049309,"Record function id": 0, "Ev Idx": 7220 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 1336756, "tid": 1336756, + "ts": 1655274041960.556, "dur": 1058.235, + "args": { + "External id": 4049310,"Record function id": 0, "Ev Idx": 7221 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 1336756, "tid": 1336756, + "ts": 1655274042031.214, "dur": 941.933, + "args": { + "External id": 4049311,"Sequence number": 40618384, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[8388608, 2048, 1], [1], [2048, 1], [2048, 1], [2048, 1], [32, 1], [32, 1], [2048, 1], [1], [2048, 1], [2048, 1], [5632, 1]], "Input Dims": [[16, 4096, 2048], [2048], [2048, 2048], [2048, 2048], [2048, 2048], [8192, 32], [8192, 32], [2048, 2048], [2048], [5632, 2048], [5632, 2048], [2048, 5632]], "Ev Idx": 7222 + } + }, + { + "ph": "s", "id": 196, "pid": 1336756, "tid": 1336756, "ts": 1655274042031.214, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 1336756, "tid": 1336756, + "ts": 1655274042100.160, "dur": 40.709, + "args": { + "External id": 4049312,"kernel_hash": "cd26ogptnjelaibpl2zumx5nxdttspqepvjkh7lpmsxbzrrexbxm", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "2048", "1", "9.9999999999999995e-07", "True", "2048", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/d2/cd26ogptnjelaibpl2zumx5nxdttspqepvjkh7lpmsxbzrrexbxm.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [65536, 2048], [2048], [65536], [], [], [], [], [], [], [], [], []], "Ev Idx": 7223 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274042153.337, "dur": 102.329, + "args": { + "External id": 4049313,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 7224 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274042264.901, "dur": 38.526, + "args": { + "External id": 4049314,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 7225 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274042311.139, "dur": 32.064, + "args": { + "External id": 4049315,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 7226 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336756, "tid": 1336756, + "ts": 1655274042366.214, "dur": 23.044, + "args": { + "External id": 4049316,"kernel_hash": "cahe5odluo4swiyj4n2lohwh57qg5lym5qsijyjsjca7pvto5oka", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/ah/cahe5odluo4swiyj4n2lohwh57qg5lym5qsijyjsjca7pvto5oka.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 7227 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336756, "tid": 1336756, + "ts": 1655274042407.009, "dur": 30.195, + "args": { + "External id": 4049317,"kernel_hash": "cahe5odluo4swiyj4n2lohwh57qg5lym5qsijyjsjca7pvto5oka", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/ah/cahe5odluo4swiyj4n2lohwh57qg5lym5qsijyjsjca7pvto5oka.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 7228 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 1336756, "tid": 1336756, + "ts": 1655274042457.219, "dur": 124.415, + "args": { + "External id": 4049318,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.125", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [], [], [], [], [], [], [], []], "Ev Idx": 7229 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336756, "tid": 1336756, + "ts": 1655274042504.857, "dur": 11.717, + "args": { + "External id": 4049319,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[8388608, 2048, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [], [], [], [], []], "Ev Idx": 7230 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274042510.120, "dur": 5.715, + "args": { + "External id": 4049320,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "[8388608, 2048, 64, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7231 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274042519.464, "dur": 5.076, + "args": { + "External id": 4049321,"Record function id": 0, "Concrete Inputs": ["[16, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7232 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274042525.853, "dur": 1.144, + "args": { + "External id": 4049322,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7233 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274042529.250, "dur": 3.419, + "args": { + "External id": 4049323,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7234 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274042591.884, "dur": 49.158, + "args": { + "External id": 4049324,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 7235 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_2", "pid": 1336756, "tid": 1336756, + "ts": 1655274042668.248, "dur": 25.957, + "args": { + "External id": 4049325,"kernel_hash": "ckbsutlugbs4qoncxuwq6kkwome3xojo3ke4p7z74lcl5h4q62to", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "2048", "1", "9.9999999999999995e-07", "True", "2048", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/kb/ckbsutlugbs4qoncxuwq6kkwome3xojo3ke4p7z74lcl5h4q62to.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [1], [2048, 1], [2048, 1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [65536, 2048], [2048], [65536, 2048], [65536, 2048], [65536], [], [], [], [], [], [], [], [], []], "Ev Idx": 7236 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274042701.779, "dur": 40.527, + "args": { + "External id": 4049326,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [5632, 1]], "Input Dims": [[65536, 2048], [2048, 5632], [65536, 5632]], "Ev Idx": 7237 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274042749.858, "dur": 35.051, + "args": { + "External id": 4049327,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [5632, 1]], "Input Dims": [[65536, 2048], [2048, 5632], [65536, 5632]], "Ev Idx": 7238 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 1336756, "tid": 1336756, + "ts": 1655274042807.048, "dur": 22.856, + "args": { + "External id": 4049328,"kernel_hash": "cgh2wg2b6li2ipjwrhdr326ycb37fu4v576nwebfoyhwx5kppapn", "grid": "grid(369098752,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "369098752"], "kernel_file": "/tmp/torchinductor_cvm/gh/cgh2wg2b6li2ipjwrhdr326ycb37fu4v576nwebfoyhwx5kppapn.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[5632, 1], [5632, 1], [23068672, 5632, 1], []], "Input Dims": [[65536, 5632], [65536, 5632], [16, 4096, 5632], []], "Ev Idx": 7239 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274042835.410, "dur": 34.068, + "args": { + "External id": 4049329,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [1, 5632], [2048, 1]], "Input Dims": [[65536, 5632], [5632, 2048], [65536, 2048]], "Ev Idx": 7240 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 1336756, "tid": 1336756, + "ts": 1655274042888.170, "dur": 16.740, + "args": { + "External id": 4049330,"kernel_hash": "cta7vcczabyyuqarwmn4dcnazkxudhfwrvnick7ql5cmsd5lz4rz", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/ta/cta7vcczabyyuqarwmn4dcnazkxudhfwrvnick7ql5cmsd5lz4rz.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[8388608, 2048, 1], [2048, 1], []], "Input Dims": [[16, 4096, 2048], [65536, 2048], []], "Ev Idx": 7241 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.15)", "pid": 1336756, "tid": 1336756, + "ts": 1655274043083.880, "dur": 71.765, + "args": { + "External id": 4049331,"Record function id": 0, "Ev Idx": 7242 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 1336756, "tid": 1336756, + "ts": 1655274043227.650, "dur": 45.359, + "args": { + "External id": 4049332,"Record function id": 0, "Ev Idx": 7243 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.16)", "pid": 1336756, "tid": 1336756, + "ts": 1655274043281.915, "dur": 18309.938, + "args": { + "External id": 4049333,"Record function id": 0, "Ev Idx": 7244 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.16)", "pid": 1336756, "tid": 1336756, + "ts": 1655274043290.487, "dur": 869.212, + "args": { + "External id": 4049334,"Record function id": 0, "Ev Idx": 7245 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274043363.858, "dur": 7.968, + "args": { + "External id": 4049335,"Record function id": 0, "Concrete Inputs": ["[6423040]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7246 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336756, "tid": 1336756, + "ts": 1655274043385.120, "dur": 47.173, + "args": { + "External id": 4049336,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 7247 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274043390.482, "dur": 2.395, + "args": { + "External id": 4049337,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7248 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274043396.687, "dur": 0.430, + "args": { + "External id": 4049338,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7249 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274043398.527, "dur": 0.341, + "args": { + "External id": 4049339,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7250 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274043400.769, "dur": 0.472, + "args": { + "External id": 4049340,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7251 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274043404.318, "dur": 0.291, + "args": { + "External id": 4049341,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7252 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274043405.975, "dur": 0.301, + "args": { + "External id": 4049342,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7253 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274043407.444, "dur": 2.752, + "args": { + "External id": 4049343,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7254 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274043411.706, "dur": 0.135, + "args": { + "External id": 4049344,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7255 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274043413.136, "dur": 0.147, + "args": { + "External id": 4049345,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7256 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336756, "tid": 1336756, + "ts": 1655274043444.315, "dur": 40.406, + "args": { + "External id": 4049346,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 7257 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 1336756, "tid": 1336756, + "ts": 1655274043518.417, "dur": 112.948, + "args": { + "External id": 4049347,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "6423040", "8", "3", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [], [], [], [], [], []], "Ev Idx": 7258 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274043529.564, "dur": 4.773, + "args": { + "External id": 4049348,"Record function id": 0, "Concrete Inputs": ["[51384320]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7259 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 1336756, "tid": 1336756, + "ts": 1655274043539.543, "dur": 13.330, + "args": { + "External id": 4049349,"Record function id": 0, "Concrete Inputs": ["", "0", "19269120", "6423040"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 7260 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1336756, + "ts": 1655274043546.922, "dur": 5.564, + "args": { + "External id": 4049350,"Record function id": 0, "Concrete Inputs": ["", "0", "19269120", "25692160", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[51384320], [], [], [], []], "Ev Idx": 7261 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274043550.812, "dur": 0.547, + "args": { + "External id": 4049351,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "[1]", "19269120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 7262 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336756, "tid": 1336756, + "ts": 1655274043559.903, "dur": 28.183, + "args": { + "External id": 4049352,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 7263 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274043562.054, "dur": 2.153, + "args": { + "External id": 4049353,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "19269120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7264 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274043565.994, "dur": 0.364, + "args": { + "External id": 4049354,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "19269376"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7265 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274043568.146, "dur": 0.167, + "args": { + "External id": 4049355,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "19793664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7266 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274043571.577, "dur": 1.040, + "args": { + "External id": 4049356,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "20317952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7267 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274043573.691, "dur": 0.242, + "args": { + "External id": 4049357,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "20842240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7268 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274043575.042, "dur": 0.246, + "args": { + "External id": 4049358,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "21366528"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7269 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274043579.081, "dur": 0.311, + "args": { + "External id": 4049359,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "21366784"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7270 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274043580.822, "dur": 0.274, + "args": { + "External id": 4049360,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "22808576"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7271 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274043582.186, "dur": 1.916, + "args": { + "External id": 4049361,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "24250368"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7272 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336756, "tid": 1336756, + "ts": 1655274043598.473, "dur": 24.868, + "args": { + "External id": 4049362,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 7273 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 1336756, "tid": 1336756, + "ts": 1655274043686.373, "dur": 377.549, + "args": { + "External id": 4049363,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[51384320], [6423040], [], [], []], "Ev Idx": 7274 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336756, "tid": 1336756, + "ts": 1655274043717.286, "dur": 341.443, + "args": { + "External id": 4049364,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 3, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "3", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 51384320, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[6423040], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 7275, "In msg nelems": 6423040 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 1336756, "tid": 1336756, + "ts": 1655274043727.099, "dur": 324.439, + "args": { + "External id": 4049365,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[6423040]], "Ev Idx": 7276 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336756, "tid": 1336756, + "ts": 1655274044088.104, "dur": 2.574, + "args": { + "External id": 4049366,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "3", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 7277, "In msg nelems": 0, "Rank": 3, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.16)", "pid": 1336756, "tid": 1336756, + "ts": 1655274044180.089, "dur": 17211.250, + "args": { + "External id": 4049367,"Record function id": 0, "Ev Idx": 7278 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274044274.235, "dur": 6.272, + "args": { + "External id": 4049368,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[51384320], []], "Ev Idx": 7279 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274044283.901, "dur": 0.974, + "args": { + "External id": 4049369,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 7280 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274044286.861, "dur": 1.804, + "args": { + "External id": 4049370,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 7281 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274044290.137, "dur": 0.695, + "args": { + "External id": 4049371,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 7282 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274044292.261, "dur": 0.576, + "args": { + "External id": 4049372,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 7283 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274044294.017, "dur": 0.695, + "args": { + "External id": 4049373,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 7284 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274044297.955, "dur": 0.734, + "args": { + "External id": 4049374,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 7285 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274044300.140, "dur": 1.436, + "args": { + "External id": 4049375,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 7286 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274044303.003, "dur": 0.581, + "args": { + "External id": 4049376,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 7287 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274044305.244, "dur": 0.618, + "args": { + "External id": 4049377,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 7288 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 1336756, "tid": 1336756, + "ts": 1655274044325.777, "dur": 17027.534, + "args": { + "External id": 4049378,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 7289 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 1336756, "tid": 1336756, + "ts": 1655274044341.917, "dur": 17004.927, + "args": { + "External id": 4049379,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 7290 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274044364.508, "dur": 12.056, + "args": { + "External id": 4049380,"Record function id": 0, "Concrete Inputs": ["[2133]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7291 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655274044379.747, "dur": 16935.786, + "args": { + "External id": 4049381,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], [], []], "Ev Idx": 7292 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336756, "tid": 1336756, + "ts": 1655274044382.053, "dur": 16932.898, + "args": { + "External id": 4049382,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], []], "Ev Idx": 7293 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274044387.763, "dur": 5.461, + "args": { + "External id": 4049383,"Record function id": 0, "Concrete Inputs": ["[2133]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7294 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1336756, + "ts": 1655274044395.317, "dur": 16916.963, + "args": { + "External id": 4049384,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[2133], [2133], []], "Ev Idx": 7295 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 1336756, "tid": 1336756, + "ts": 1655274061531.130, "dur": 35.376, + "args": { + "External id": 4049385,"Sequence number": 40618385, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 7296 + } + }, + { + "ph": "s", "id": 195, "pid": 1336756, "tid": 1336756, "ts": 1655274061531.130, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 1336756, "tid": 1336756, + "ts": 1655274061553.576, "dur": 7.888, + "args": { + "External id": 4049386,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[8388608, 2048, 1], [8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048], [16, 4096, 2048]], "Ev Idx": 7297 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274061557.149, "dur": 3.948, + "args": { + "External id": 4049387,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 7298 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 1336756, "tid": 1336756, + "ts": 1655274061629.373, "dur": 72.773, + "args": { + "External id": 4049388,"Record function id": 0, "Ev Idx": 7299 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 1336756, "tid": 1336756, + "ts": 1655274061703.757, "dur": 1065.476, + "args": { + "External id": 4049389,"Record function id": 0, "Ev Idx": 7300 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 1336756, "tid": 1336756, + "ts": 1655274061743.291, "dur": 1013.191, + "args": { + "External id": 4049390,"Sequence number": 40618386, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[8388608, 2048, 1], [1], [2048, 1], [2048, 1], [2048, 1], [32, 1], [32, 1], [2048, 1], [1], [2048, 1], [2048, 1], [5632, 1]], "Input Dims": [[16, 4096, 2048], [2048], [2048, 2048], [2048, 2048], [2048, 2048], [8192, 32], [8192, 32], [2048, 2048], [2048], [5632, 2048], [5632, 2048], [2048, 5632]], "Ev Idx": 7301 + } + }, + { + "ph": "s", "id": 194, "pid": 1336756, "tid": 1336756, "ts": 1655274061743.291, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 1336756, "tid": 1336756, + "ts": 1655274061804.615, "dur": 38.327, + "args": { + "External id": 4049391,"kernel_hash": "cd26ogptnjelaibpl2zumx5nxdttspqepvjkh7lpmsxbzrrexbxm", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "2048", "1", "9.9999999999999995e-07", "True", "2048", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/d2/cd26ogptnjelaibpl2zumx5nxdttspqepvjkh7lpmsxbzrrexbxm.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [65536, 2048], [2048], [65536], [], [], [], [], [], [], [], [], []], "Ev Idx": 7302 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274061855.136, "dur": 101.416, + "args": { + "External id": 4049392,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 7303 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274061965.330, "dur": 74.571, + "args": { + "External id": 4049393,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 7304 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274062052.940, "dur": 34.214, + "args": { + "External id": 4049394,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 7305 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336756, "tid": 1336756, + "ts": 1655274062117.814, "dur": 27.505, + "args": { + "External id": 4049395,"kernel_hash": "cahe5odluo4swiyj4n2lohwh57qg5lym5qsijyjsjca7pvto5oka", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/ah/cahe5odluo4swiyj4n2lohwh57qg5lym5qsijyjsjca7pvto5oka.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 7306 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336756, "tid": 1336756, + "ts": 1655274062161.116, "dur": 14.061, + "args": { + "External id": 4049396,"kernel_hash": "cahe5odluo4swiyj4n2lohwh57qg5lym5qsijyjsjca7pvto5oka", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/ah/cahe5odluo4swiyj4n2lohwh57qg5lym5qsijyjsjca7pvto5oka.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 7307 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 1336756, "tid": 1336756, + "ts": 1655274062193.278, "dur": 130.059, + "args": { + "External id": 4049397,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.125", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [], [], [], [], [], [], [], []], "Ev Idx": 7308 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336756, "tid": 1336756, + "ts": 1655274062244.233, "dur": 11.166, + "args": { + "External id": 4049398,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[8388608, 2048, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [], [], [], [], []], "Ev Idx": 7309 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274062249.659, "dur": 4.981, + "args": { + "External id": 4049399,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "[8388608, 2048, 64, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7310 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274062258.422, "dur": 5.571, + "args": { + "External id": 4049400,"Record function id": 0, "Concrete Inputs": ["[16, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7311 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274062265.488, "dur": 1.267, + "args": { + "External id": 4049401,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7312 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274062269.120, "dur": 5.356, + "args": { + "External id": 4049402,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7313 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274062333.479, "dur": 44.793, + "args": { + "External id": 4049403,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 7314 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_2", "pid": 1336756, "tid": 1336756, + "ts": 1655274062406.874, "dur": 42.474, + "args": { + "External id": 4049404,"kernel_hash": "ckbsutlugbs4qoncxuwq6kkwome3xojo3ke4p7z74lcl5h4q62to", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "2048", "1", "9.9999999999999995e-07", "True", "2048", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/kb/ckbsutlugbs4qoncxuwq6kkwome3xojo3ke4p7z74lcl5h4q62to.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [1], [2048, 1], [2048, 1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [65536, 2048], [2048], [65536, 2048], [65536, 2048], [65536], [], [], [], [], [], [], [], [], []], "Ev Idx": 7315 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274062461.022, "dur": 44.502, + "args": { + "External id": 4049405,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [5632, 1]], "Input Dims": [[65536, 2048], [2048, 5632], [65536, 5632]], "Ev Idx": 7316 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274062512.036, "dur": 34.835, + "args": { + "External id": 4049406,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [5632, 1]], "Input Dims": [[65536, 2048], [2048, 5632], [65536, 5632]], "Ev Idx": 7317 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 1336756, "tid": 1336756, + "ts": 1655274062570.381, "dur": 24.110, + "args": { + "External id": 4049407,"kernel_hash": "cgh2wg2b6li2ipjwrhdr326ycb37fu4v576nwebfoyhwx5kppapn", "grid": "grid(369098752,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "369098752"], "kernel_file": "/tmp/torchinductor_cvm/gh/cgh2wg2b6li2ipjwrhdr326ycb37fu4v576nwebfoyhwx5kppapn.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[5632, 1], [5632, 1], [23068672, 5632, 1], []], "Input Dims": [[65536, 5632], [65536, 5632], [16, 4096, 5632], []], "Ev Idx": 7318 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274062601.024, "dur": 34.594, + "args": { + "External id": 4049408,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [1, 5632], [2048, 1]], "Input Dims": [[65536, 5632], [5632, 2048], [65536, 2048]], "Ev Idx": 7319 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 1336756, "tid": 1336756, + "ts": 1655274062675.190, "dur": 19.205, + "args": { + "External id": 4049409,"kernel_hash": "cta7vcczabyyuqarwmn4dcnazkxudhfwrvnick7ql5cmsd5lz4rz", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/ta/cta7vcczabyyuqarwmn4dcnazkxudhfwrvnick7ql5cmsd5lz4rz.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[8388608, 2048, 1], [2048, 1], []], "Input Dims": [[16, 4096, 2048], [65536, 2048], []], "Ev Idx": 7320 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.16)", "pid": 1336756, "tid": 1336756, + "ts": 1655274062833.209, "dur": 72.428, + "args": { + "External id": 4049410,"Record function id": 0, "Ev Idx": 7321 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 1336756, "tid": 1336756, + "ts": 1655274062977.240, "dur": 86.229, + "args": { + "External id": 4049411,"Record function id": 0, "Ev Idx": 7322 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.17)", "pid": 1336756, "tid": 1336756, + "ts": 1655274063073.943, "dur": 18226.567, + "args": { + "External id": 4049412,"Record function id": 0, "Ev Idx": 7323 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.17)", "pid": 1336756, "tid": 1336756, + "ts": 1655274063082.773, "dur": 815.165, + "args": { + "External id": 4049413,"Record function id": 0, "Ev Idx": 7324 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274063159.958, "dur": 9.233, + "args": { + "External id": 4049414,"Record function id": 0, "Concrete Inputs": ["[6423040]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7325 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336756, "tid": 1336756, + "ts": 1655274063182.859, "dur": 35.330, + "args": { + "External id": 4049415,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 7326 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274063188.725, "dur": 2.491, + "args": { + "External id": 4049416,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7327 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274063195.149, "dur": 0.278, + "args": { + "External id": 4049417,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7328 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274063196.673, "dur": 0.269, + "args": { + "External id": 4049418,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7329 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274063198.213, "dur": 0.291, + "args": { + "External id": 4049419,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7330 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274063201.591, "dur": 0.304, + "args": { + "External id": 4049420,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7331 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274063203.277, "dur": 0.263, + "args": { + "External id": 4049421,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7332 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274063204.770, "dur": 3.238, + "args": { + "External id": 4049422,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7333 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274063209.472, "dur": 0.348, + "args": { + "External id": 4049423,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7334 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274063211.533, "dur": 0.260, + "args": { + "External id": 4049424,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7335 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336756, "tid": 1336756, + "ts": 1655274063228.442, "dur": 39.703, + "args": { + "External id": 4049425,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 7336 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 1336756, "tid": 1336756, + "ts": 1655274063299.286, "dur": 104.785, + "args": { + "External id": 4049426,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "6423040", "8", "3", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [], [], [], [], [], []], "Ev Idx": 7337 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274063309.857, "dur": 3.465, + "args": { + "External id": 4049427,"Record function id": 0, "Concrete Inputs": ["[51384320]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7338 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 1336756, "tid": 1336756, + "ts": 1655274063318.423, "dur": 9.892, + "args": { + "External id": 4049428,"Record function id": 0, "Concrete Inputs": ["", "0", "19269120", "6423040"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 7339 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1336756, + "ts": 1655274063322.765, "dur": 5.142, + "args": { + "External id": 4049429,"Record function id": 0, "Concrete Inputs": ["", "0", "19269120", "25692160", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[51384320], [], [], [], []], "Ev Idx": 7340 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274063326.323, "dur": 0.505, + "args": { + "External id": 4049430,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "[1]", "19269120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 7341 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336756, "tid": 1336756, + "ts": 1655274063335.078, "dur": 27.696, + "args": { + "External id": 4049431,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 7342 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274063336.997, "dur": 2.215, + "args": { + "External id": 4049432,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "19269120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7343 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274063340.653, "dur": 0.207, + "args": { + "External id": 4049433,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "19269376"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7344 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274063342.301, "dur": 0.179, + "args": { + "External id": 4049434,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "19793664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7345 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274063345.758, "dur": 1.121, + "args": { + "External id": 4049435,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "20317952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7346 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274063348.577, "dur": 0.244, + "args": { + "External id": 4049436,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "20842240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7347 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274063350.135, "dur": 0.285, + "args": { + "External id": 4049437,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "21366528"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7348 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274063353.591, "dur": 0.388, + "args": { + "External id": 4049438,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "21366784"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7349 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274063355.494, "dur": 0.340, + "args": { + "External id": 4049439,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "22808576"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7350 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274063357.238, "dur": 1.628, + "args": { + "External id": 4049440,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "24250368"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7351 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336756, "tid": 1336756, + "ts": 1655274063373.670, "dur": 22.725, + "args": { + "External id": 4049441,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 7352 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 1336756, "tid": 1336756, + "ts": 1655274063475.488, "dur": 337.355, + "args": { + "External id": 4049442,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[51384320], [6423040], [], [], []], "Ev Idx": 7353 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336756, "tid": 1336756, + "ts": 1655274063506.430, "dur": 301.668, + "args": { + "External id": 4049443,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 3, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "3", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 51384320, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[6423040], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 7354, "In msg nelems": 6423040 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 1336756, "tid": 1336756, + "ts": 1655274063516.126, "dur": 286.414, + "args": { + "External id": 4049444,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[6423040]], "Ev Idx": 7355 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336756, "tid": 1336756, + "ts": 1655274063834.064, "dur": 2.811, + "args": { + "External id": 4049445,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "3", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 7356, "In msg nelems": 0, "Rank": 3, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.17)", "pid": 1336756, "tid": 1336756, + "ts": 1655274063916.968, "dur": 17200.459, + "args": { + "External id": 4049446,"Record function id": 0, "Ev Idx": 7357 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274064042.918, "dur": 6.678, + "args": { + "External id": 4049447,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[51384320], []], "Ev Idx": 7358 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274064053.263, "dur": 1.288, + "args": { + "External id": 4049448,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 7359 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274064056.184, "dur": 1.734, + "args": { + "External id": 4049449,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 7360 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274064059.475, "dur": 0.724, + "args": { + "External id": 4049450,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 7361 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274064061.914, "dur": 0.621, + "args": { + "External id": 4049451,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 7362 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274064063.630, "dur": 0.707, + "args": { + "External id": 4049452,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 7363 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274064067.694, "dur": 0.671, + "args": { + "External id": 4049453,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 7364 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274064069.763, "dur": 1.640, + "args": { + "External id": 4049454,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 7365 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274064072.841, "dur": 0.611, + "args": { + "External id": 4049455,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 7366 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274064075.064, "dur": 0.679, + "args": { + "External id": 4049456,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 7367 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 1336756, "tid": 1336756, + "ts": 1655274064097.295, "dur": 16982.813, + "args": { + "External id": 4049457,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 7368 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 1336756, "tid": 1336756, + "ts": 1655274064113.318, "dur": 16960.184, + "args": { + "External id": 4049458,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 7369 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274064137.922, "dur": 13.270, + "args": { + "External id": 4049459,"Record function id": 0, "Concrete Inputs": ["[2133]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7370 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655274064154.125, "dur": 16886.797, + "args": { + "External id": 4049460,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], [], []], "Ev Idx": 7371 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336756, "tid": 1336756, + "ts": 1655274064156.707, "dur": 16883.736, + "args": { + "External id": 4049461,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], []], "Ev Idx": 7372 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274064161.872, "dur": 4.884, + "args": { + "External id": 4049462,"Record function id": 0, "Concrete Inputs": ["[2133]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7373 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1336756, + "ts": 1655274064168.693, "dur": 16869.120, + "args": { + "External id": 4049463,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[2133], [2133], []], "Ev Idx": 7374 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 1336756, "tid": 1336756, + "ts": 1655274081242.275, "dur": 34.756, + "args": { + "External id": 4049464,"Sequence number": 40618387, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 7375 + } + }, + { + "ph": "s", "id": 193, "pid": 1336756, "tid": 1336756, "ts": 1655274081242.275, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 1336756, "tid": 1336756, + "ts": 1655274081264.828, "dur": 7.497, + "args": { + "External id": 4049465,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[8388608, 2048, 1], [8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048], [16, 4096, 2048]], "Ev Idx": 7376 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274081268.112, "dur": 3.993, + "args": { + "External id": 4049466,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 7377 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 1336756, "tid": 1336756, + "ts": 1655274081337.133, "dur": 72.328, + "args": { + "External id": 4049467,"Record function id": 0, "Ev Idx": 7378 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 1336756, "tid": 1336756, + "ts": 1655274081411.300, "dur": 1060.188, + "args": { + "External id": 4049468,"Record function id": 0, "Ev Idx": 7379 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 1336756, "tid": 1336756, + "ts": 1655274081466.568, "dur": 991.527, + "args": { + "External id": 4049469,"Sequence number": 40618388, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[8388608, 2048, 1], [1], [2048, 1], [2048, 1], [2048, 1], [32, 1], [32, 1], [2048, 1], [1], [2048, 1], [2048, 1], [5632, 1]], "Input Dims": [[16, 4096, 2048], [2048], [2048, 2048], [2048, 2048], [2048, 2048], [8192, 32], [8192, 32], [2048, 2048], [2048], [5632, 2048], [5632, 2048], [2048, 5632]], "Ev Idx": 7380 + } + }, + { + "ph": "s", "id": 192, "pid": 1336756, "tid": 1336756, "ts": 1655274081466.568, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 1336756, "tid": 1336756, + "ts": 1655274081531.112, "dur": 42.183, + "args": { + "External id": 4049470,"kernel_hash": "cd26ogptnjelaibpl2zumx5nxdttspqepvjkh7lpmsxbzrrexbxm", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "2048", "1", "9.9999999999999995e-07", "True", "2048", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/d2/cd26ogptnjelaibpl2zumx5nxdttspqepvjkh7lpmsxbzrrexbxm.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [65536, 2048], [2048], [65536], [], [], [], [], [], [], [], [], []], "Ev Idx": 7381 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274081586.348, "dur": 105.975, + "args": { + "External id": 4049471,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 7382 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274081701.998, "dur": 38.817, + "args": { + "External id": 4049472,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 7383 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274081748.555, "dur": 31.456, + "args": { + "External id": 4049473,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 7384 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336756, "tid": 1336756, + "ts": 1655274081803.161, "dur": 23.540, + "args": { + "External id": 4049474,"kernel_hash": "cahe5odluo4swiyj4n2lohwh57qg5lym5qsijyjsjca7pvto5oka", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/ah/cahe5odluo4swiyj4n2lohwh57qg5lym5qsijyjsjca7pvto5oka.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 7385 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336756, "tid": 1336756, + "ts": 1655274081843.607, "dur": 13.405, + "args": { + "External id": 4049475,"kernel_hash": "cahe5odluo4swiyj4n2lohwh57qg5lym5qsijyjsjca7pvto5oka", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/ah/cahe5odluo4swiyj4n2lohwh57qg5lym5qsijyjsjca7pvto5oka.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 7386 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 1336756, "tid": 1336756, + "ts": 1655274081874.266, "dur": 164.460, + "args": { + "External id": 4049476,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.125", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [], [], [], [], [], [], [], []], "Ev Idx": 7387 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336756, "tid": 1336756, + "ts": 1655274081924.308, "dur": 10.774, + "args": { + "External id": 4049477,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[8388608, 2048, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [], [], [], [], []], "Ev Idx": 7388 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274081929.345, "dur": 5.038, + "args": { + "External id": 4049478,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "[8388608, 2048, 64, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7389 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274081938.133, "dur": 5.238, + "args": { + "External id": 4049479,"Record function id": 0, "Concrete Inputs": ["[16, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7390 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274081944.708, "dur": 1.192, + "args": { + "External id": 4049480,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7391 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274081948.546, "dur": 3.472, + "args": { + "External id": 4049481,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7392 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274082051.093, "dur": 52.181, + "args": { + "External id": 4049482,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 7393 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_2", "pid": 1336756, "tid": 1336756, + "ts": 1655274082133.366, "dur": 26.031, + "args": { + "External id": 4049483,"kernel_hash": "ckbsutlugbs4qoncxuwq6kkwome3xojo3ke4p7z74lcl5h4q62to", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "2048", "1", "9.9999999999999995e-07", "True", "2048", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/kb/ckbsutlugbs4qoncxuwq6kkwome3xojo3ke4p7z74lcl5h4q62to.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [1], [2048, 1], [2048, 1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [65536, 2048], [2048], [65536, 2048], [65536, 2048], [65536], [], [], [], [], [], [], [], [], []], "Ev Idx": 7394 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274082168.333, "dur": 42.146, + "args": { + "External id": 4049484,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [5632, 1]], "Input Dims": [[65536, 2048], [2048, 5632], [65536, 5632]], "Ev Idx": 7395 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274082218.352, "dur": 36.042, + "args": { + "External id": 4049485,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [5632, 1]], "Input Dims": [[65536, 2048], [2048, 5632], [65536, 5632]], "Ev Idx": 7396 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 1336756, "tid": 1336756, + "ts": 1655274082276.496, "dur": 23.366, + "args": { + "External id": 4049486,"kernel_hash": "cgh2wg2b6li2ipjwrhdr326ycb37fu4v576nwebfoyhwx5kppapn", "grid": "grid(369098752,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "369098752"], "kernel_file": "/tmp/torchinductor_cvm/gh/cgh2wg2b6li2ipjwrhdr326ycb37fu4v576nwebfoyhwx5kppapn.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[5632, 1], [5632, 1], [23068672, 5632, 1], []], "Input Dims": [[65536, 5632], [65536, 5632], [16, 4096, 5632], []], "Ev Idx": 7397 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274082305.190, "dur": 34.102, + "args": { + "External id": 4049487,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [1, 5632], [2048, 1]], "Input Dims": [[65536, 5632], [5632, 2048], [65536, 2048]], "Ev Idx": 7398 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 1336756, "tid": 1336756, + "ts": 1655274082358.360, "dur": 17.689, + "args": { + "External id": 4049488,"kernel_hash": "cta7vcczabyyuqarwmn4dcnazkxudhfwrvnick7ql5cmsd5lz4rz", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/ta/cta7vcczabyyuqarwmn4dcnazkxudhfwrvnick7ql5cmsd5lz4rz.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[8388608, 2048, 1], [2048, 1], []], "Input Dims": [[16, 4096, 2048], [65536, 2048], []], "Ev Idx": 7399 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.17)", "pid": 1336756, "tid": 1336756, + "ts": 1655274082535.510, "dur": 74.258, + "args": { + "External id": 4049489,"Record function id": 0, "Ev Idx": 7400 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 1336756, "tid": 1336756, + "ts": 1655274082681.109, "dur": 45.770, + "args": { + "External id": 4049490,"Record function id": 0, "Ev Idx": 7401 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.18)", "pid": 1336756, "tid": 1336756, + "ts": 1655274082736.526, "dur": 18165.428, + "args": { + "External id": 4049491,"Record function id": 0, "Ev Idx": 7402 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.18)", "pid": 1336756, "tid": 1336756, + "ts": 1655274082743.650, "dur": 865.678, + "args": { + "External id": 4049492,"Record function id": 0, "Ev Idx": 7403 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274082820.617, "dur": 8.059, + "args": { + "External id": 4049493,"Record function id": 0, "Concrete Inputs": ["[6423040]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7404 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336756, "tid": 1336756, + "ts": 1655274082842.257, "dur": 32.852, + "args": { + "External id": 4049494,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 7405 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274082847.188, "dur": 2.160, + "args": { + "External id": 4049495,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7406 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274082853.374, "dur": 0.377, + "args": { + "External id": 4049496,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7407 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274082855.001, "dur": 0.155, + "args": { + "External id": 4049497,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7408 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274082856.948, "dur": 0.446, + "args": { + "External id": 4049498,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7409 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274082860.258, "dur": 0.150, + "args": { + "External id": 4049499,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7410 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274082862.083, "dur": 0.183, + "args": { + "External id": 4049500,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7411 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274082863.428, "dur": 2.774, + "args": { + "External id": 4049501,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7412 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274082867.674, "dur": 0.203, + "args": { + "External id": 4049502,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7413 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274082869.250, "dur": 0.159, + "args": { + "External id": 4049503,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7414 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336756, "tid": 1336756, + "ts": 1655274082885.380, "dur": 37.176, + "args": { + "External id": 4049504,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 7415 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 1336756, "tid": 1336756, + "ts": 1655274082953.533, "dur": 156.136, + "args": { + "External id": 4049505,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "6423040", "8", "3", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [], [], [], [], [], []], "Ev Idx": 7416 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274082964.129, "dur": 4.087, + "args": { + "External id": 4049506,"Record function id": 0, "Concrete Inputs": ["[51384320]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7417 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 1336756, "tid": 1336756, + "ts": 1655274082973.235, "dur": 48.372, + "args": { + "External id": 4049507,"Record function id": 0, "Concrete Inputs": ["", "0", "19269120", "6423040"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 7418 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1336756, + "ts": 1655274082977.288, "dur": 43.859, + "args": { + "External id": 4049508,"Record function id": 0, "Concrete Inputs": ["", "0", "19269120", "25692160", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[51384320], [], [], [], []], "Ev Idx": 7419 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274082980.589, "dur": 38.183, + "args": { + "External id": 4049509,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "[1]", "19269120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 7420 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336756, "tid": 1336756, + "ts": 1655274083031.684, "dur": 29.963, + "args": { + "External id": 4049510,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 7421 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274083033.938, "dur": 2.281, + "args": { + "External id": 4049511,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "19269120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7422 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274083037.882, "dur": 0.314, + "args": { + "External id": 4049512,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "19269376"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7423 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274083039.612, "dur": 0.165, + "args": { + "External id": 4049513,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "19793664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7424 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274083045.886, "dur": 1.049, + "args": { + "External id": 4049514,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "20317952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7425 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274083048.104, "dur": 0.168, + "args": { + "External id": 4049515,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "20842240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7426 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274083049.958, "dur": 0.506, + "args": { + "External id": 4049516,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "21366528"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7427 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274083052.935, "dur": 0.267, + "args": { + "External id": 4049517,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "21366784"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7428 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274083054.340, "dur": 0.219, + "args": { + "External id": 4049518,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "22808576"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7429 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274083055.727, "dur": 2.021, + "args": { + "External id": 4049519,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "24250368"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7430 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336756, "tid": 1336756, + "ts": 1655274083073.866, "dur": 26.946, + "args": { + "External id": 4049520,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 7431 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 1336756, "tid": 1336756, + "ts": 1655274083164.689, "dur": 355.020, + "args": { + "External id": 4049521,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[51384320], [6423040], [], [], []], "Ev Idx": 7432 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336756, "tid": 1336756, + "ts": 1655274083195.490, "dur": 319.150, + "args": { + "External id": 4049522,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 3, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "3", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 51384320, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[6423040], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 7433, "In msg nelems": 6423040 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 1336756, "tid": 1336756, + "ts": 1655274083205.776, "dur": 303.052, + "args": { + "External id": 4049523,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[6423040]], "Ev Idx": 7434 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336756, "tid": 1336756, + "ts": 1655274083542.636, "dur": 2.787, + "args": { + "External id": 4049524,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "3", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 7435, "In msg nelems": 0, "Rank": 3, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.18)", "pid": 1336756, "tid": 1336756, + "ts": 1655274083629.028, "dur": 17091.803, + "args": { + "External id": 4049525,"Record function id": 0, "Ev Idx": 7436 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274083721.155, "dur": 5.829, + "args": { + "External id": 4049526,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[51384320], []], "Ev Idx": 7437 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274083730.069, "dur": 1.161, + "args": { + "External id": 4049527,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 7438 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274083732.840, "dur": 2.054, + "args": { + "External id": 4049528,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 7439 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274083736.465, "dur": 0.627, + "args": { + "External id": 4049529,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 7440 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274083738.470, "dur": 1.028, + "args": { + "External id": 4049530,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 7441 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274083740.662, "dur": 0.630, + "args": { + "External id": 4049531,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 7442 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274083744.372, "dur": 0.563, + "args": { + "External id": 4049532,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 7443 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274083746.455, "dur": 1.679, + "args": { + "External id": 4049533,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 7444 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274083749.634, "dur": 0.585, + "args": { + "External id": 4049534,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 7445 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274083751.908, "dur": 0.651, + "args": { + "External id": 4049535,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 7446 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 1336756, "tid": 1336756, + "ts": 1655274083772.420, "dur": 16910.334, + "args": { + "External id": 4049536,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 7447 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 1336756, "tid": 1336756, + "ts": 1655274083788.284, "dur": 16887.826, + "args": { + "External id": 4049537,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 7448 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274083809.899, "dur": 12.873, + "args": { + "External id": 4049538,"Record function id": 0, "Concrete Inputs": ["[2133]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7449 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655274083825.730, "dur": 16818.197, + "args": { + "External id": 4049539,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], [], []], "Ev Idx": 7450 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336756, "tid": 1336756, + "ts": 1655274083828.166, "dur": 16815.233, + "args": { + "External id": 4049540,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], []], "Ev Idx": 7451 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274083833.677, "dur": 5.834, + "args": { + "External id": 4049541,"Record function id": 0, "Concrete Inputs": ["[2133]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7452 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1336756, + "ts": 1655274083840.954, "dur": 16799.676, + "args": { + "External id": 4049542,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[2133], [2133], []], "Ev Idx": 7453 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 1336756, "tid": 1336756, + "ts": 1655274100843.535, "dur": 34.419, + "args": { + "External id": 4049543,"Sequence number": 40618389, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 7454 + } + }, + { + "ph": "s", "id": 191, "pid": 1336756, "tid": 1336756, "ts": 1655274100843.535, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 1336756, "tid": 1336756, + "ts": 1655274100866.320, "dur": 6.954, + "args": { + "External id": 4049544,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[8388608, 2048, 1], [8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048], [16, 4096, 2048]], "Ev Idx": 7455 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274100869.365, "dur": 3.639, + "args": { + "External id": 4049545,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 7456 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 1336756, "tid": 1336756, + "ts": 1655274100939.088, "dur": 99.046, + "args": { + "External id": 4049546,"Record function id": 0, "Ev Idx": 7457 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 1336756, "tid": 1336756, + "ts": 1655274101040.999, "dur": 1032.968, + "args": { + "External id": 4049547,"Record function id": 0, "Ev Idx": 7458 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 1336756, "tid": 1336756, + "ts": 1655274101082.096, "dur": 978.009, + "args": { + "External id": 4049548,"Sequence number": 40618390, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[8388608, 2048, 1], [1], [2048, 1], [2048, 1], [2048, 1], [32, 1], [32, 1], [2048, 1], [1], [2048, 1], [2048, 1], [5632, 1]], "Input Dims": [[16, 4096, 2048], [2048], [2048, 2048], [2048, 2048], [2048, 2048], [8192, 32], [8192, 32], [2048, 2048], [2048], [5632, 2048], [5632, 2048], [2048, 5632]], "Ev Idx": 7459 + } + }, + { + "ph": "s", "id": 190, "pid": 1336756, "tid": 1336756, "ts": 1655274101082.096, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 1336756, "tid": 1336756, + "ts": 1655274101151.342, "dur": 41.375, + "args": { + "External id": 4049549,"kernel_hash": "cd26ogptnjelaibpl2zumx5nxdttspqepvjkh7lpmsxbzrrexbxm", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "2048", "1", "9.9999999999999995e-07", "True", "2048", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/d2/cd26ogptnjelaibpl2zumx5nxdttspqepvjkh7lpmsxbzrrexbxm.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [65536, 2048], [2048], [65536], [], [], [], [], [], [], [], [], []], "Ev Idx": 7460 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274101206.170, "dur": 101.857, + "args": { + "External id": 4049550,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 7461 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274101317.226, "dur": 39.426, + "args": { + "External id": 4049551,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 7462 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274101362.294, "dur": 31.046, + "args": { + "External id": 4049552,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 7463 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336756, "tid": 1336756, + "ts": 1655274101433.100, "dur": 25.365, + "args": { + "External id": 4049553,"kernel_hash": "cahe5odluo4swiyj4n2lohwh57qg5lym5qsijyjsjca7pvto5oka", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/ah/cahe5odluo4swiyj4n2lohwh57qg5lym5qsijyjsjca7pvto5oka.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 7464 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336756, "tid": 1336756, + "ts": 1655274101475.394, "dur": 16.972, + "args": { + "External id": 4049554,"kernel_hash": "cahe5odluo4swiyj4n2lohwh57qg5lym5qsijyjsjca7pvto5oka", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/ah/cahe5odluo4swiyj4n2lohwh57qg5lym5qsijyjsjca7pvto5oka.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 7465 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 1336756, "tid": 1336756, + "ts": 1655274101508.128, "dur": 128.834, + "args": { + "External id": 4049555,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.125", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [], [], [], [], [], [], [], []], "Ev Idx": 7466 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336756, "tid": 1336756, + "ts": 1655274101557.288, "dur": 12.008, + "args": { + "External id": 4049556,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[8388608, 2048, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [], [], [], [], []], "Ev Idx": 7467 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274101562.417, "dur": 6.138, + "args": { + "External id": 4049557,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "[8388608, 2048, 64, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7468 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274101571.922, "dur": 5.258, + "args": { + "External id": 4049558,"Record function id": 0, "Concrete Inputs": ["[16, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7469 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274101578.561, "dur": 2.816, + "args": { + "External id": 4049559,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7470 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274101583.705, "dur": 3.594, + "args": { + "External id": 4049560,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7471 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274101648.194, "dur": 47.975, + "args": { + "External id": 4049561,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 7472 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_2", "pid": 1336756, "tid": 1336756, + "ts": 1655274101724.970, "dur": 24.511, + "args": { + "External id": 4049562,"kernel_hash": "ckbsutlugbs4qoncxuwq6kkwome3xojo3ke4p7z74lcl5h4q62to", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "2048", "1", "9.9999999999999995e-07", "True", "2048", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/kb/ckbsutlugbs4qoncxuwq6kkwome3xojo3ke4p7z74lcl5h4q62to.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [1], [2048, 1], [2048, 1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [65536, 2048], [2048], [65536, 2048], [65536, 2048], [65536], [], [], [], [], [], [], [], [], []], "Ev Idx": 7473 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274101757.204, "dur": 41.661, + "args": { + "External id": 4049563,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [5632, 1]], "Input Dims": [[65536, 2048], [2048, 5632], [65536, 5632]], "Ev Idx": 7474 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274101805.419, "dur": 34.805, + "args": { + "External id": 4049564,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [5632, 1]], "Input Dims": [[65536, 2048], [2048, 5632], [65536, 5632]], "Ev Idx": 7475 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 1336756, "tid": 1336756, + "ts": 1655274101864.098, "dur": 22.997, + "args": { + "External id": 4049565,"kernel_hash": "cgh2wg2b6li2ipjwrhdr326ycb37fu4v576nwebfoyhwx5kppapn", "grid": "grid(369098752,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "369098752"], "kernel_file": "/tmp/torchinductor_cvm/gh/cgh2wg2b6li2ipjwrhdr326ycb37fu4v576nwebfoyhwx5kppapn.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[5632, 1], [5632, 1], [23068672, 5632, 1], []], "Input Dims": [[65536, 5632], [65536, 5632], [16, 4096, 5632], []], "Ev Idx": 7476 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274101892.475, "dur": 35.713, + "args": { + "External id": 4049566,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [1, 5632], [2048, 1]], "Input Dims": [[65536, 5632], [5632, 2048], [65536, 2048]], "Ev Idx": 7477 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 1336756, "tid": 1336756, + "ts": 1655274101944.517, "dur": 19.642, + "args": { + "External id": 4049567,"kernel_hash": "cta7vcczabyyuqarwmn4dcnazkxudhfwrvnick7ql5cmsd5lz4rz", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/ta/cta7vcczabyyuqarwmn4dcnazkxudhfwrvnick7ql5cmsd5lz4rz.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[8388608, 2048, 1], [2048, 1], []], "Input Dims": [[16, 4096, 2048], [65536, 2048], []], "Ev Idx": 7478 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.18)", "pid": 1336756, "tid": 1336756, + "ts": 1655274102137.889, "dur": 69.314, + "args": { + "External id": 4049568,"Record function id": 0, "Ev Idx": 7479 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 1336756, "tid": 1336756, + "ts": 1655274102278.155, "dur": 46.083, + "args": { + "External id": 4049569,"Record function id": 0, "Ev Idx": 7480 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.19)", "pid": 1336756, "tid": 1336756, + "ts": 1655274102333.050, "dur": 18108.984, + "args": { + "External id": 4049570,"Record function id": 0, "Ev Idx": 7481 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.19)", "pid": 1336756, "tid": 1336756, + "ts": 1655274102340.916, "dur": 906.132, + "args": { + "External id": 4049571,"Record function id": 0, "Ev Idx": 7482 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274102432.181, "dur": 9.021, + "args": { + "External id": 4049572,"Record function id": 0, "Concrete Inputs": ["[6423040]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7483 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336756, "tid": 1336756, + "ts": 1655274102455.606, "dur": 34.054, + "args": { + "External id": 4049573,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 7484 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274102461.341, "dur": 2.351, + "args": { + "External id": 4049574,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7485 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274102467.773, "dur": 0.265, + "args": { + "External id": 4049575,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7486 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274102469.303, "dur": 0.367, + "args": { + "External id": 4049576,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7487 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274102471.059, "dur": 0.267, + "args": { + "External id": 4049577,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7488 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274102474.246, "dur": 0.168, + "args": { + "External id": 4049578,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7489 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274102476.010, "dur": 0.297, + "args": { + "External id": 4049579,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7490 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274102477.336, "dur": 2.938, + "args": { + "External id": 4049580,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7491 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274102481.762, "dur": 0.228, + "args": { + "External id": 4049581,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7492 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274102483.406, "dur": 0.287, + "args": { + "External id": 4049582,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7493 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336756, "tid": 1336756, + "ts": 1655274102499.717, "dur": 41.273, + "args": { + "External id": 4049583,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 7494 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 1336756, "tid": 1336756, + "ts": 1655274102573.241, "dur": 107.301, + "args": { + "External id": 4049584,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "6423040", "8", "3", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [], [], [], [], [], []], "Ev Idx": 7495 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274102584.748, "dur": 3.583, + "args": { + "External id": 4049585,"Record function id": 0, "Concrete Inputs": ["[51384320]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7496 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 1336756, "tid": 1336756, + "ts": 1655274102593.263, "dur": 9.874, + "args": { + "External id": 4049586,"Record function id": 0, "Concrete Inputs": ["", "0", "19269120", "6423040"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 7497 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1336756, + "ts": 1655274102597.273, "dur": 5.482, + "args": { + "External id": 4049587,"Record function id": 0, "Concrete Inputs": ["", "0", "19269120", "25692160", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[51384320], [], [], [], []], "Ev Idx": 7498 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274102600.876, "dur": 0.622, + "args": { + "External id": 4049588,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "[1]", "19269120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 7499 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336756, "tid": 1336756, + "ts": 1655274102609.869, "dur": 28.169, + "args": { + "External id": 4049589,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 7500 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274102612.059, "dur": 2.162, + "args": { + "External id": 4049590,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "19269120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7501 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274102616.153, "dur": 0.319, + "args": { + "External id": 4049591,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "19269376"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7502 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274102618.264, "dur": 0.319, + "args": { + "External id": 4049592,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "19793664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7503 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274102621.595, "dur": 1.123, + "args": { + "External id": 4049593,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "20317952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7504 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274102624.382, "dur": 0.259, + "args": { + "External id": 4049594,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "20842240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7505 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274102626.213, "dur": 0.257, + "args": { + "External id": 4049595,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "21366528"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7506 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274102629.108, "dur": 0.320, + "args": { + "External id": 4049596,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "21366784"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7507 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274102630.864, "dur": 0.281, + "args": { + "External id": 4049597,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "22808576"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7508 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274102632.505, "dur": 1.684, + "args": { + "External id": 4049598,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "24250368"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7509 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336756, "tid": 1336756, + "ts": 1655274102649.547, "dur": 23.129, + "args": { + "External id": 4049599,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 7510 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 1336756, "tid": 1336756, + "ts": 1655274102733.204, "dur": 417.385, + "args": { + "External id": 4049600,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[51384320], [6423040], [], [], []], "Ev Idx": 7511 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336756, "tid": 1336756, + "ts": 1655274102762.930, "dur": 381.989, + "args": { + "External id": 4049601,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 3, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "3", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 51384320, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[6423040], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 7512, "In msg nelems": 6423040 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 1336756, "tid": 1336756, + "ts": 1655274102773.010, "dur": 365.781, + "args": { + "External id": 4049602,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[6423040]], "Ev Idx": 7513 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336756, "tid": 1336756, + "ts": 1655274103174.833, "dur": 2.736, + "args": { + "External id": 4049603,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "3", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 7514, "In msg nelems": 0, "Rank": 3, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.19)", "pid": 1336756, "tid": 1336756, + "ts": 1655274103267.719, "dur": 16980.356, + "args": { + "External id": 4049604,"Record function id": 0, "Ev Idx": 7515 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274103360.617, "dur": 6.174, + "args": { + "External id": 4049605,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[51384320], []], "Ev Idx": 7516 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274103370.035, "dur": 1.113, + "args": { + "External id": 4049606,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 7517 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274103372.830, "dur": 1.652, + "args": { + "External id": 4049607,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 7518 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274103376.064, "dur": 0.810, + "args": { + "External id": 4049608,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 7519 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274103378.311, "dur": 0.765, + "args": { + "External id": 4049609,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 7520 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274103380.229, "dur": 0.698, + "args": { + "External id": 4049610,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 7521 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274103383.873, "dur": 0.584, + "args": { + "External id": 4049611,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 7522 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274103385.959, "dur": 1.691, + "args": { + "External id": 4049612,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 7523 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274103389.296, "dur": 0.443, + "args": { + "External id": 4049613,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 7524 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274103391.120, "dur": 0.588, + "args": { + "External id": 4049614,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 7525 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 1336756, "tid": 1336756, + "ts": 1655274103411.280, "dur": 16800.100, + "args": { + "External id": 4049615,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 7526 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 1336756, "tid": 1336756, + "ts": 1655274103443.850, "dur": 16760.903, + "args": { + "External id": 4049616,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 7527 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274103470.242, "dur": 12.322, + "args": { + "External id": 4049617,"Record function id": 0, "Concrete Inputs": ["[2133]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7528 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655274103485.468, "dur": 16688.184, + "args": { + "External id": 4049618,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], [], []], "Ev Idx": 7529 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336756, "tid": 1336756, + "ts": 1655274103491.138, "dur": 16682.038, + "args": { + "External id": 4049619,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], []], "Ev Idx": 7530 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274103496.343, "dur": 5.559, + "args": { + "External id": 4049620,"Record function id": 0, "Concrete Inputs": ["[2133]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7531 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1336756, + "ts": 1655274103503.534, "dur": 16666.859, + "args": { + "External id": 4049621,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[2133], [2133], []], "Ev Idx": 7532 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 1336756, "tid": 1336756, + "ts": 1655274120369.380, "dur": 36.440, + "args": { + "External id": 4049622,"Sequence number": 40618391, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 7533 + } + }, + { + "ph": "s", "id": 189, "pid": 1336756, "tid": 1336756, "ts": 1655274120369.380, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 1336756, "tid": 1336756, + "ts": 1655274120393.634, "dur": 7.200, + "args": { + "External id": 4049623,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[8388608, 2048, 1], [8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048], [16, 4096, 2048]], "Ev Idx": 7534 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274120396.752, "dur": 3.843, + "args": { + "External id": 4049624,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 7535 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 1336756, "tid": 1336756, + "ts": 1655274120480.543, "dur": 70.295, + "args": { + "External id": 4049625,"Record function id": 0, "Ev Idx": 7536 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 1336756, "tid": 1336756, + "ts": 1655274120552.098, "dur": 1051.514, + "args": { + "External id": 4049626,"Record function id": 0, "Ev Idx": 7537 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 1336756, "tid": 1336756, + "ts": 1655274120591.787, "dur": 998.772, + "args": { + "External id": 4049627,"Sequence number": 40618392, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[8388608, 2048, 1], [1], [2048, 1], [2048, 1], [2048, 1], [32, 1], [32, 1], [2048, 1], [1], [2048, 1], [2048, 1], [5632, 1]], "Input Dims": [[16, 4096, 2048], [2048], [2048, 2048], [2048, 2048], [2048, 2048], [8192, 32], [8192, 32], [2048, 2048], [2048], [5632, 2048], [5632, 2048], [2048, 5632]], "Ev Idx": 7538 + } + }, + { + "ph": "s", "id": 188, "pid": 1336756, "tid": 1336756, "ts": 1655274120591.787, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 1336756, "tid": 1336756, + "ts": 1655274120658.537, "dur": 40.832, + "args": { + "External id": 4049628,"kernel_hash": "cd26ogptnjelaibpl2zumx5nxdttspqepvjkh7lpmsxbzrrexbxm", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "2048", "1", "9.9999999999999995e-07", "True", "2048", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/d2/cd26ogptnjelaibpl2zumx5nxdttspqepvjkh7lpmsxbzrrexbxm.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [65536, 2048], [2048], [65536], [], [], [], [], [], [], [], [], []], "Ev Idx": 7539 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274120711.214, "dur": 105.839, + "args": { + "External id": 4049629,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 7540 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274120826.280, "dur": 39.097, + "args": { + "External id": 4049630,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 7541 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274120874.168, "dur": 30.763, + "args": { + "External id": 4049631,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 7542 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336756, "tid": 1336756, + "ts": 1655274120928.906, "dur": 25.069, + "args": { + "External id": 4049632,"kernel_hash": "cahe5odluo4swiyj4n2lohwh57qg5lym5qsijyjsjca7pvto5oka", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/ah/cahe5odluo4swiyj4n2lohwh57qg5lym5qsijyjsjca7pvto5oka.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 7543 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336756, "tid": 1336756, + "ts": 1655274120970.324, "dur": 50.186, + "args": { + "External id": 4049633,"kernel_hash": "cahe5odluo4swiyj4n2lohwh57qg5lym5qsijyjsjca7pvto5oka", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/ah/cahe5odluo4swiyj4n2lohwh57qg5lym5qsijyjsjca7pvto5oka.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 7544 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 1336756, "tid": 1336756, + "ts": 1655274121040.714, "dur": 125.806, + "args": { + "External id": 4049634,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.125", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [], [], [], [], [], [], [], []], "Ev Idx": 7545 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336756, "tid": 1336756, + "ts": 1655274121088.619, "dur": 11.772, + "args": { + "External id": 4049635,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[8388608, 2048, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [], [], [], [], []], "Ev Idx": 7546 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274121093.926, "dur": 5.773, + "args": { + "External id": 4049636,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "[8388608, 2048, 64, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7547 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274121103.397, "dur": 5.713, + "args": { + "External id": 4049637,"Record function id": 0, "Concrete Inputs": ["[16, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7548 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274121110.430, "dur": 1.104, + "args": { + "External id": 4049638,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7549 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274121113.890, "dur": 3.813, + "args": { + "External id": 4049639,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7550 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274121177.381, "dur": 50.061, + "args": { + "External id": 4049640,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 7551 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_2", "pid": 1336756, "tid": 1336756, + "ts": 1655274121257.119, "dur": 27.094, + "args": { + "External id": 4049641,"kernel_hash": "ckbsutlugbs4qoncxuwq6kkwome3xojo3ke4p7z74lcl5h4q62to", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "2048", "1", "9.9999999999999995e-07", "True", "2048", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/kb/ckbsutlugbs4qoncxuwq6kkwome3xojo3ke4p7z74lcl5h4q62to.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [1], [2048, 1], [2048, 1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [65536, 2048], [2048], [65536, 2048], [65536, 2048], [65536], [], [], [], [], [], [], [], [], []], "Ev Idx": 7552 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274121293.000, "dur": 41.621, + "args": { + "External id": 4049642,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [5632, 1]], "Input Dims": [[65536, 2048], [2048, 5632], [65536, 5632]], "Ev Idx": 7553 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274121342.640, "dur": 34.727, + "args": { + "External id": 4049643,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [5632, 1]], "Input Dims": [[65536, 2048], [2048, 5632], [65536, 5632]], "Ev Idx": 7554 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 1336756, "tid": 1336756, + "ts": 1655274121398.670, "dur": 39.131, + "args": { + "External id": 4049644,"kernel_hash": "cgh2wg2b6li2ipjwrhdr326ycb37fu4v576nwebfoyhwx5kppapn", "grid": "grid(369098752,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "369098752"], "kernel_file": "/tmp/torchinductor_cvm/gh/cgh2wg2b6li2ipjwrhdr326ycb37fu4v576nwebfoyhwx5kppapn.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[5632, 1], [5632, 1], [23068672, 5632, 1], []], "Input Dims": [[65536, 5632], [65536, 5632], [16, 4096, 5632], []], "Ev Idx": 7555 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274121445.359, "dur": 38.787, + "args": { + "External id": 4049645,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [1, 5632], [2048, 1]], "Input Dims": [[65536, 5632], [5632, 2048], [65536, 2048]], "Ev Idx": 7556 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 1336756, "tid": 1336756, + "ts": 1655274121505.431, "dur": 17.184, + "args": { + "External id": 4049646,"kernel_hash": "cta7vcczabyyuqarwmn4dcnazkxudhfwrvnick7ql5cmsd5lz4rz", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/ta/cta7vcczabyyuqarwmn4dcnazkxudhfwrvnick7ql5cmsd5lz4rz.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[8388608, 2048, 1], [2048, 1], []], "Input Dims": [[16, 4096, 2048], [65536, 2048], []], "Ev Idx": 7557 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.19)", "pid": 1336756, "tid": 1336756, + "ts": 1655274121666.137, "dur": 70.260, + "args": { + "External id": 4049647,"Record function id": 0, "Ev Idx": 7558 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 1336756, "tid": 1336756, + "ts": 1655274121808.737, "dur": 48.772, + "args": { + "External id": 4049648,"Record function id": 0, "Ev Idx": 7559 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.20)", "pid": 1336756, "tid": 1336756, + "ts": 1655274121867.315, "dur": 18046.805, + "args": { + "External id": 4049649,"Record function id": 0, "Ev Idx": 7560 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.20)", "pid": 1336756, "tid": 1336756, + "ts": 1655274121875.358, "dur": 865.973, + "args": { + "External id": 4049650,"Record function id": 0, "Ev Idx": 7561 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274121947.665, "dur": 7.079, + "args": { + "External id": 4049651,"Record function id": 0, "Concrete Inputs": ["[6423040]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7562 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336756, "tid": 1336756, + "ts": 1655274121967.752, "dur": 72.828, + "args": { + "External id": 4049652,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 7563 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274121972.559, "dur": 2.258, + "args": { + "External id": 4049653,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7564 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274121978.863, "dur": 0.433, + "args": { + "External id": 4049654,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7565 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274121980.681, "dur": 38.620, + "args": { + "External id": 4049655,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7566 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274122022.055, "dur": 0.187, + "args": { + "External id": 4049656,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7567 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274122025.412, "dur": 0.175, + "args": { + "External id": 4049657,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7568 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274122026.701, "dur": 0.504, + "args": { + "External id": 4049658,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7569 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274122028.568, "dur": 2.806, + "args": { + "External id": 4049659,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7570 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274122032.781, "dur": 0.251, + "args": { + "External id": 4049660,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7571 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274122034.489, "dur": 0.176, + "args": { + "External id": 4049661,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7572 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336756, "tid": 1336756, + "ts": 1655274122052.441, "dur": 39.515, + "args": { + "External id": 4049662,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 7573 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 1336756, "tid": 1336756, + "ts": 1655274122126.056, "dur": 111.828, + "args": { + "External id": 4049663,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "6423040", "8", "3", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [], [], [], [], [], []], "Ev Idx": 7574 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274122137.409, "dur": 5.545, + "args": { + "External id": 4049664,"Record function id": 0, "Concrete Inputs": ["[51384320]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7575 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 1336756, "tid": 1336756, + "ts": 1655274122148.202, "dur": 9.711, + "args": { + "External id": 4049665,"Record function id": 0, "Concrete Inputs": ["", "0", "19269120", "6423040"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 7576 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1336756, + "ts": 1655274122152.258, "dur": 5.231, + "args": { + "External id": 4049666,"Record function id": 0, "Concrete Inputs": ["", "0", "19269120", "25692160", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[51384320], [], [], [], []], "Ev Idx": 7577 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274122155.877, "dur": 0.398, + "args": { + "External id": 4049667,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "[1]", "19269120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 7578 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336756, "tid": 1336756, + "ts": 1655274122165.615, "dur": 26.743, + "args": { + "External id": 4049668,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 7579 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274122167.893, "dur": 1.898, + "args": { + "External id": 4049669,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "19269120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7580 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274122171.247, "dur": 0.515, + "args": { + "External id": 4049670,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "19269376"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7581 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274122173.354, "dur": 0.213, + "args": { + "External id": 4049671,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "19793664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7582 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274122176.614, "dur": 1.353, + "args": { + "External id": 4049672,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "20317952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7583 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274122179.769, "dur": 0.184, + "args": { + "External id": 4049673,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "20842240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7584 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274122181.043, "dur": 0.406, + "args": { + "External id": 4049674,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "21366528"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7585 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274122183.445, "dur": 0.428, + "args": { + "External id": 4049675,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "21366784"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7586 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274122184.857, "dur": 0.291, + "args": { + "External id": 4049676,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "22808576"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7587 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274122186.608, "dur": 1.783, + "args": { + "External id": 4049677,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "24250368"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7588 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336756, "tid": 1336756, + "ts": 1655274122206.420, "dur": 24.131, + "args": { + "External id": 4049678,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 7589 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 1336756, "tid": 1336756, + "ts": 1655274122292.867, "dur": 357.745, + "args": { + "External id": 4049679,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[51384320], [6423040], [], [], []], "Ev Idx": 7590 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336756, "tid": 1336756, + "ts": 1655274122322.414, "dur": 322.905, + "args": { + "External id": 4049680,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 3, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "3", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 51384320, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[6423040], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 7591, "In msg nelems": 6423040 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 1336756, "tid": 1336756, + "ts": 1655274122333.821, "dur": 305.717, + "args": { + "External id": 4049681,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[6423040]], "Ev Idx": 7592 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336756, "tid": 1336756, + "ts": 1655274122673.555, "dur": 2.324, + "args": { + "External id": 4049682,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "3", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 7593, "In msg nelems": 0, "Rank": 3, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.20)", "pid": 1336756, "tid": 1336756, + "ts": 1655274122761.001, "dur": 16965.440, + "args": { + "External id": 4049683,"Record function id": 0, "Ev Idx": 7594 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274122848.721, "dur": 6.256, + "args": { + "External id": 4049684,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[51384320], []], "Ev Idx": 7595 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274122858.045, "dur": 0.766, + "args": { + "External id": 4049685,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 7596 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274122860.350, "dur": 1.737, + "args": { + "External id": 4049686,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 7597 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274122863.604, "dur": 0.812, + "args": { + "External id": 4049687,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 7598 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274122865.779, "dur": 0.684, + "args": { + "External id": 4049688,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 7599 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274122867.789, "dur": 0.653, + "args": { + "External id": 4049689,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 7600 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274122871.644, "dur": 0.546, + "args": { + "External id": 4049690,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 7601 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274122873.892, "dur": 1.621, + "args": { + "External id": 4049691,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 7602 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274122876.846, "dur": 0.583, + "args": { + "External id": 4049692,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 7603 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274122878.681, "dur": 0.554, + "args": { + "External id": 4049693,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 7604 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 1336756, "tid": 1336756, + "ts": 1655274122898.168, "dur": 16790.856, + "args": { + "External id": 4049694,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 7605 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 1336756, "tid": 1336756, + "ts": 1655274122913.049, "dur": 16769.220, + "args": { + "External id": 4049695,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 7606 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274122933.796, "dur": 14.199, + "args": { + "External id": 4049696,"Record function id": 0, "Concrete Inputs": ["[2133]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7607 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655274122950.766, "dur": 16700.245, + "args": { + "External id": 4049697,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], [], []], "Ev Idx": 7608 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336756, "tid": 1336756, + "ts": 1655274122953.097, "dur": 16697.354, + "args": { + "External id": 4049698,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], []], "Ev Idx": 7609 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274122958.376, "dur": 4.872, + "args": { + "External id": 4049699,"Record function id": 0, "Concrete Inputs": ["[2133]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7610 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1336756, + "ts": 1655274122964.983, "dur": 16682.088, + "args": { + "External id": 4049700,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[2133], [2133], []], "Ev Idx": 7611 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 1336756, "tid": 1336756, + "ts": 1655274139847.092, "dur": 41.523, + "args": { + "External id": 4049701,"Sequence number": 40618393, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 7612 + } + }, + { + "ph": "s", "id": 187, "pid": 1336756, "tid": 1336756, "ts": 1655274139847.092, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 1336756, "tid": 1336756, + "ts": 1655274139871.730, "dur": 11.678, + "args": { + "External id": 4049702,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[8388608, 2048, 1], [8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048], [16, 4096, 2048]], "Ev Idx": 7613 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274139879.137, "dur": 4.004, + "args": { + "External id": 4049703,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 7614 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 1336756, "tid": 1336756, + "ts": 1655274139951.098, "dur": 98.824, + "args": { + "External id": 4049704,"Record function id": 0, "Ev Idx": 7615 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 1336756, "tid": 1336756, + "ts": 1655274140053.377, "dur": 1033.141, + "args": { + "External id": 4049705,"Record function id": 0, "Ev Idx": 7616 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 1336756, "tid": 1336756, + "ts": 1655274140095.292, "dur": 978.358, + "args": { + "External id": 4049706,"Sequence number": 40618394, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[8388608, 2048, 1], [1], [2048, 1], [2048, 1], [2048, 1], [32, 1], [32, 1], [2048, 1], [1], [2048, 1], [2048, 1], [5632, 1]], "Input Dims": [[16, 4096, 2048], [2048], [2048, 2048], [2048, 2048], [2048, 2048], [8192, 32], [8192, 32], [2048, 2048], [2048], [5632, 2048], [5632, 2048], [2048, 5632]], "Ev Idx": 7617 + } + }, + { + "ph": "s", "id": 186, "pid": 1336756, "tid": 1336756, "ts": 1655274140095.292, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 1336756, "tid": 1336756, + "ts": 1655274140161.783, "dur": 41.777, + "args": { + "External id": 4049707,"kernel_hash": "cd26ogptnjelaibpl2zumx5nxdttspqepvjkh7lpmsxbzrrexbxm", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "2048", "1", "9.9999999999999995e-07", "True", "2048", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/d2/cd26ogptnjelaibpl2zumx5nxdttspqepvjkh7lpmsxbzrrexbxm.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [65536, 2048], [2048], [65536], [], [], [], [], [], [], [], [], []], "Ev Idx": 7618 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274140215.267, "dur": 102.211, + "args": { + "External id": 4049708,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 7619 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274140329.051, "dur": 38.487, + "args": { + "External id": 4049709,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 7620 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274140373.632, "dur": 32.591, + "args": { + "External id": 4049710,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 7621 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336756, "tid": 1336756, + "ts": 1655274140447.774, "dur": 26.870, + "args": { + "External id": 4049711,"kernel_hash": "cahe5odluo4swiyj4n2lohwh57qg5lym5qsijyjsjca7pvto5oka", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/ah/cahe5odluo4swiyj4n2lohwh57qg5lym5qsijyjsjca7pvto5oka.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 7622 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336756, "tid": 1336756, + "ts": 1655274140491.346, "dur": 13.850, + "args": { + "External id": 4049712,"kernel_hash": "cahe5odluo4swiyj4n2lohwh57qg5lym5qsijyjsjca7pvto5oka", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/ah/cahe5odluo4swiyj4n2lohwh57qg5lym5qsijyjsjca7pvto5oka.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 7623 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 1336756, "tid": 1336756, + "ts": 1655274140521.529, "dur": 125.459, + "args": { + "External id": 4049713,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.125", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [], [], [], [], [], [], [], []], "Ev Idx": 7624 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336756, "tid": 1336756, + "ts": 1655274140569.036, "dur": 11.299, + "args": { + "External id": 4049714,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[8388608, 2048, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [], [], [], [], []], "Ev Idx": 7625 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274140574.065, "dur": 5.440, + "args": { + "External id": 4049715,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "[8388608, 2048, 64, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7626 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274140582.852, "dur": 5.154, + "args": { + "External id": 4049716,"Record function id": 0, "Concrete Inputs": ["[16, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7627 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274140589.349, "dur": 1.490, + "args": { + "External id": 4049717,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7628 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274140594.751, "dur": 4.050, + "args": { + "External id": 4049718,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7629 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274140657.488, "dur": 48.377, + "args": { + "External id": 4049719,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 7630 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_2", "pid": 1336756, "tid": 1336756, + "ts": 1655274140733.345, "dur": 27.098, + "args": { + "External id": 4049720,"kernel_hash": "ckbsutlugbs4qoncxuwq6kkwome3xojo3ke4p7z74lcl5h4q62to", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "2048", "1", "9.9999999999999995e-07", "True", "2048", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/kb/ckbsutlugbs4qoncxuwq6kkwome3xojo3ke4p7z74lcl5h4q62to.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [1], [2048, 1], [2048, 1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [65536, 2048], [2048], [65536, 2048], [65536, 2048], [65536], [], [], [], [], [], [], [], [], []], "Ev Idx": 7631 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274140768.943, "dur": 40.853, + "args": { + "External id": 4049721,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [5632, 1]], "Input Dims": [[65536, 2048], [2048, 5632], [65536, 5632]], "Ev Idx": 7632 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274140815.734, "dur": 35.049, + "args": { + "External id": 4049722,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [5632, 1]], "Input Dims": [[65536, 2048], [2048, 5632], [65536, 5632]], "Ev Idx": 7633 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 1336756, "tid": 1336756, + "ts": 1655274140871.995, "dur": 25.832, + "args": { + "External id": 4049723,"kernel_hash": "cgh2wg2b6li2ipjwrhdr326ycb37fu4v576nwebfoyhwx5kppapn", "grid": "grid(369098752,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "369098752"], "kernel_file": "/tmp/torchinductor_cvm/gh/cgh2wg2b6li2ipjwrhdr326ycb37fu4v576nwebfoyhwx5kppapn.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[5632, 1], [5632, 1], [23068672, 5632, 1], []], "Input Dims": [[65536, 5632], [65536, 5632], [16, 4096, 5632], []], "Ev Idx": 7634 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274140902.387, "dur": 35.339, + "args": { + "External id": 4049724,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [1, 5632], [2048, 1]], "Input Dims": [[65536, 5632], [5632, 2048], [65536, 2048]], "Ev Idx": 7635 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 1336756, "tid": 1336756, + "ts": 1655274140954.865, "dur": 16.804, + "args": { + "External id": 4049725,"kernel_hash": "cta7vcczabyyuqarwmn4dcnazkxudhfwrvnick7ql5cmsd5lz4rz", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/ta/cta7vcczabyyuqarwmn4dcnazkxudhfwrvnick7ql5cmsd5lz4rz.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[8388608, 2048, 1], [2048, 1], []], "Input Dims": [[16, 4096, 2048], [65536, 2048], []], "Ev Idx": 7636 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.20)", "pid": 1336756, "tid": 1336756, + "ts": 1655274141149.902, "dur": 69.236, + "args": { + "External id": 4049726,"Record function id": 0, "Ev Idx": 7637 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 1336756, "tid": 1336756, + "ts": 1655274141288.055, "dur": 44.323, + "args": { + "External id": 4049727,"Record function id": 0, "Ev Idx": 7638 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.21)", "pid": 1336756, "tid": 1336756, + "ts": 1655274141341.166, "dur": 18090.558, + "args": { + "External id": 4049728,"Record function id": 0, "Ev Idx": 7639 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.21)", "pid": 1336756, "tid": 1336756, + "ts": 1655274141349.398, "dur": 863.842, + "args": { + "External id": 4049729,"Record function id": 0, "Ev Idx": 7640 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274141439.252, "dur": 9.068, + "args": { + "External id": 4049730,"Record function id": 0, "Concrete Inputs": ["[6423040]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7641 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336756, "tid": 1336756, + "ts": 1655274141462.473, "dur": 33.116, + "args": { + "External id": 4049731,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 7642 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274141467.422, "dur": 2.227, + "args": { + "External id": 4049732,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7643 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274141473.847, "dur": 0.221, + "args": { + "External id": 4049733,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7644 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274141475.463, "dur": 0.298, + "args": { + "External id": 4049734,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7645 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274141477.790, "dur": 0.260, + "args": { + "External id": 4049735,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7646 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274141480.838, "dur": 0.285, + "args": { + "External id": 4049736,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7647 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274141482.325, "dur": 0.174, + "args": { + "External id": 4049737,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7648 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274141483.658, "dur": 2.907, + "args": { + "External id": 4049738,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7649 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274141488.178, "dur": 0.332, + "args": { + "External id": 4049739,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7650 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274141489.684, "dur": 0.259, + "args": { + "External id": 4049740,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7651 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336756, "tid": 1336756, + "ts": 1655274141505.855, "dur": 39.866, + "args": { + "External id": 4049741,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 7652 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 1336756, "tid": 1336756, + "ts": 1655274141578.382, "dur": 106.058, + "args": { + "External id": 4049742,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "6423040", "8", "3", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [], [], [], [], [], []], "Ev Idx": 7653 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274141589.291, "dur": 3.891, + "args": { + "External id": 4049743,"Record function id": 0, "Concrete Inputs": ["[51384320]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7654 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 1336756, "tid": 1336756, + "ts": 1655274141598.131, "dur": 9.667, + "args": { + "External id": 4049744,"Record function id": 0, "Concrete Inputs": ["", "0", "19269120", "6423040"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 7655 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1336756, + "ts": 1655274141602.475, "dur": 4.917, + "args": { + "External id": 4049745,"Record function id": 0, "Concrete Inputs": ["", "0", "19269120", "25692160", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[51384320], [], [], [], []], "Ev Idx": 7656 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274141605.828, "dur": 0.432, + "args": { + "External id": 4049746,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "[1]", "19269120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 7657 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336756, "tid": 1336756, + "ts": 1655274141614.833, "dur": 26.877, + "args": { + "External id": 4049747,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 7658 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274141617.327, "dur": 1.934, + "args": { + "External id": 4049748,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "19269120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7659 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274141620.857, "dur": 0.301, + "args": { + "External id": 4049749,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "19269376"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7660 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274141622.225, "dur": 0.381, + "args": { + "External id": 4049750,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "19793664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7661 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274141625.635, "dur": 1.404, + "args": { + "External id": 4049751,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "20317952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7662 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274141628.282, "dur": 0.484, + "args": { + "External id": 4049752,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "20842240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7663 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274141630.056, "dur": 0.287, + "args": { + "External id": 4049753,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "21366528"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7664 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274141633.104, "dur": 0.160, + "args": { + "External id": 4049754,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "21366784"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7665 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274141634.564, "dur": 0.323, + "args": { + "External id": 4049755,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "22808576"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7666 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274141636.288, "dur": 1.682, + "args": { + "External id": 4049756,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "24250368"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7667 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336756, "tid": 1336756, + "ts": 1655274141653.223, "dur": 23.602, + "args": { + "External id": 4049757,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 7668 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 1336756, "tid": 1336756, + "ts": 1655274141736.014, "dur": 381.304, + "args": { + "External id": 4049758,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[51384320], [6423040], [], [], []], "Ev Idx": 7669 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336756, "tid": 1336756, + "ts": 1655274141766.390, "dur": 345.225, + "args": { + "External id": 4049759,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 3, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "3", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 51384320, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[6423040], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 7670, "In msg nelems": 6423040 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 1336756, "tid": 1336756, + "ts": 1655274141786.134, "dur": 319.645, + "args": { + "External id": 4049760,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[6423040]], "Ev Idx": 7671 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336756, "tid": 1336756, + "ts": 1655274142142.014, "dur": 2.436, + "args": { + "External id": 4049761,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "3", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 7672, "In msg nelems": 0, "Rank": 3, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.21)", "pid": 1336756, "tid": 1336756, + "ts": 1655274142235.106, "dur": 17000.582, + "args": { + "External id": 4049762,"Record function id": 0, "Ev Idx": 7673 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274142329.250, "dur": 6.063, + "args": { + "External id": 4049763,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[51384320], []], "Ev Idx": 7674 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274142338.427, "dur": 0.936, + "args": { + "External id": 4049764,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 7675 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274142340.995, "dur": 2.037, + "args": { + "External id": 4049765,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 7676 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274142344.771, "dur": 0.713, + "args": { + "External id": 4049766,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 7677 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274142346.999, "dur": 0.698, + "args": { + "External id": 4049767,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 7678 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274142348.885, "dur": 0.683, + "args": { + "External id": 4049768,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 7679 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274142353.019, "dur": 0.652, + "args": { + "External id": 4049769,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 7680 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274142354.992, "dur": 1.720, + "args": { + "External id": 4049770,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 7681 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274142358.172, "dur": 0.540, + "args": { + "External id": 4049771,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 7682 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274142360.064, "dur": 0.580, + "args": { + "External id": 4049772,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 7683 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 1336756, "tid": 1336756, + "ts": 1655274142380.681, "dur": 16818.885, + "args": { + "External id": 4049773,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 7684 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 1336756, "tid": 1336756, + "ts": 1655274142396.349, "dur": 16796.429, + "args": { + "External id": 4049774,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 7685 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274142432.568, "dur": 13.566, + "args": { + "External id": 4049775,"Record function id": 0, "Concrete Inputs": ["[2133]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7686 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655274142449.485, "dur": 16712.422, + "args": { + "External id": 4049776,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], [], []], "Ev Idx": 7687 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336756, "tid": 1336756, + "ts": 1655274142452.019, "dur": 16709.348, + "args": { + "External id": 4049777,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], []], "Ev Idx": 7688 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274142457.358, "dur": 5.589, + "args": { + "External id": 4049778,"Record function id": 0, "Concrete Inputs": ["[2133]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7689 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1336756, + "ts": 1655274142464.748, "dur": 16693.839, + "args": { + "External id": 4049779,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[2133], [2133], []], "Ev Idx": 7690 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 1336756, "tid": 1336756, + "ts": 1655274159359.178, "dur": 35.827, + "args": { + "External id": 4049780,"Sequence number": 40618395, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 7691 + } + }, + { + "ph": "s", "id": 185, "pid": 1336756, "tid": 1336756, "ts": 1655274159359.178, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 1336756, "tid": 1336756, + "ts": 1655274159382.830, "dur": 7.241, + "args": { + "External id": 4049781,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[8388608, 2048, 1], [8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048], [16, 4096, 2048]], "Ev Idx": 7692 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274159385.871, "dur": 3.951, + "args": { + "External id": 4049782,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 7693 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 1336756, "tid": 1336756, + "ts": 1655274159470.750, "dur": 71.882, + "args": { + "External id": 4049783,"Record function id": 0, "Ev Idx": 7694 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 1336756, "tid": 1336756, + "ts": 1655274159544.164, "dur": 1041.252, + "args": { + "External id": 4049784,"Record function id": 0, "Ev Idx": 7695 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 1336756, "tid": 1336756, + "ts": 1655274159584.946, "dur": 987.269, + "args": { + "External id": 4049785,"Sequence number": 40618396, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[8388608, 2048, 1], [1], [2048, 1], [2048, 1], [2048, 1], [32, 1], [32, 1], [2048, 1], [1], [2048, 1], [2048, 1], [5632, 1]], "Input Dims": [[16, 4096, 2048], [2048], [2048, 2048], [2048, 2048], [2048, 2048], [8192, 32], [8192, 32], [2048, 2048], [2048], [5632, 2048], [5632, 2048], [2048, 5632]], "Ev Idx": 7696 + } + }, + { + "ph": "s", "id": 184, "pid": 1336756, "tid": 1336756, "ts": 1655274159584.946, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 1336756, "tid": 1336756, + "ts": 1655274159648.017, "dur": 39.966, + "args": { + "External id": 4049786,"kernel_hash": "cd26ogptnjelaibpl2zumx5nxdttspqepvjkh7lpmsxbzrrexbxm", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "2048", "1", "9.9999999999999995e-07", "True", "2048", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/d2/cd26ogptnjelaibpl2zumx5nxdttspqepvjkh7lpmsxbzrrexbxm.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [65536, 2048], [2048], [65536], [], [], [], [], [], [], [], [], []], "Ev Idx": 7697 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274159699.779, "dur": 105.835, + "args": { + "External id": 4049787,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 7698 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274159814.834, "dur": 38.956, + "args": { + "External id": 4049788,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 7699 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274159861.531, "dur": 30.471, + "args": { + "External id": 4049789,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 7700 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336756, "tid": 1336756, + "ts": 1655274159915.385, "dur": 24.546, + "args": { + "External id": 4049790,"kernel_hash": "cahe5odluo4swiyj4n2lohwh57qg5lym5qsijyjsjca7pvto5oka", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/ah/cahe5odluo4swiyj4n2lohwh57qg5lym5qsijyjsjca7pvto5oka.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 7701 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336756, "tid": 1336756, + "ts": 1655274159956.387, "dur": 14.011, + "args": { + "External id": 4049791,"kernel_hash": "cahe5odluo4swiyj4n2lohwh57qg5lym5qsijyjsjca7pvto5oka", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/ah/cahe5odluo4swiyj4n2lohwh57qg5lym5qsijyjsjca7pvto5oka.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 7702 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 1336756, "tid": 1336756, + "ts": 1655274160020.038, "dur": 131.750, + "args": { + "External id": 4049792,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.125", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [], [], [], [], [], [], [], []], "Ev Idx": 7703 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336756, "tid": 1336756, + "ts": 1655274160072.201, "dur": 12.054, + "args": { + "External id": 4049793,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[8388608, 2048, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [], [], [], [], []], "Ev Idx": 7704 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274160077.230, "dur": 5.970, + "args": { + "External id": 4049794,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "[8388608, 2048, 64, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7705 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274160087.093, "dur": 5.515, + "args": { + "External id": 4049795,"Record function id": 0, "Concrete Inputs": ["[16, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7706 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274160093.912, "dur": 1.225, + "args": { + "External id": 4049796,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7707 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274160097.897, "dur": 3.794, + "args": { + "External id": 4049797,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7708 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274160163.017, "dur": 49.458, + "args": { + "External id": 4049798,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 7709 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_2", "pid": 1336756, "tid": 1336756, + "ts": 1655274160241.142, "dur": 26.572, + "args": { + "External id": 4049799,"kernel_hash": "ckbsutlugbs4qoncxuwq6kkwome3xojo3ke4p7z74lcl5h4q62to", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "2048", "1", "9.9999999999999995e-07", "True", "2048", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/kb/ckbsutlugbs4qoncxuwq6kkwome3xojo3ke4p7z74lcl5h4q62to.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [1], [2048, 1], [2048, 1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [65536, 2048], [2048], [65536, 2048], [65536, 2048], [65536], [], [], [], [], [], [], [], [], []], "Ev Idx": 7710 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274160275.684, "dur": 41.364, + "args": { + "External id": 4049800,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [5632, 1]], "Input Dims": [[65536, 2048], [2048, 5632], [65536, 5632]], "Ev Idx": 7711 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274160325.592, "dur": 34.419, + "args": { + "External id": 4049801,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [5632, 1]], "Input Dims": [[65536, 2048], [2048, 5632], [65536, 5632]], "Ev Idx": 7712 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 1336756, "tid": 1336756, + "ts": 1655274160382.578, "dur": 23.572, + "args": { + "External id": 4049802,"kernel_hash": "cgh2wg2b6li2ipjwrhdr326ycb37fu4v576nwebfoyhwx5kppapn", "grid": "grid(369098752,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "369098752"], "kernel_file": "/tmp/torchinductor_cvm/gh/cgh2wg2b6li2ipjwrhdr326ycb37fu4v576nwebfoyhwx5kppapn.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[5632, 1], [5632, 1], [23068672, 5632, 1], []], "Input Dims": [[65536, 5632], [65536, 5632], [16, 4096, 5632], []], "Ev Idx": 7713 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274160411.053, "dur": 52.685, + "args": { + "External id": 4049803,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [1, 5632], [2048, 1]], "Input Dims": [[65536, 5632], [5632, 2048], [65536, 2048]], "Ev Idx": 7714 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 1336756, "tid": 1336756, + "ts": 1655274160485.940, "dur": 18.151, + "args": { + "External id": 4049804,"kernel_hash": "cta7vcczabyyuqarwmn4dcnazkxudhfwrvnick7ql5cmsd5lz4rz", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/ta/cta7vcczabyyuqarwmn4dcnazkxudhfwrvnick7ql5cmsd5lz4rz.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[8388608, 2048, 1], [2048, 1], []], "Input Dims": [[16, 4096, 2048], [65536, 2048], []], "Ev Idx": 7715 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.21)", "pid": 1336756, "tid": 1336756, + "ts": 1655274160644.790, "dur": 67.950, + "args": { + "External id": 4049805,"Record function id": 0, "Ev Idx": 7716 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 1336756, "tid": 1336756, + "ts": 1655274160784.119, "dur": 45.667, + "args": { + "External id": 4049806,"Record function id": 0, "Ev Idx": 7717 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.22)", "pid": 1336756, "tid": 1336756, + "ts": 1655274160838.774, "dur": 18075.596, + "args": { + "External id": 4049807,"Record function id": 0, "Ev Idx": 7718 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.22)", "pid": 1336756, "tid": 1336756, + "ts": 1655274160846.391, "dur": 886.778, + "args": { + "External id": 4049808,"Record function id": 0, "Ev Idx": 7719 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274160920.101, "dur": 7.495, + "args": { + "External id": 4049809,"Record function id": 0, "Concrete Inputs": ["[6423040]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7720 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336756, "tid": 1336756, + "ts": 1655274160940.434, "dur": 33.149, + "args": { + "External id": 4049810,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 7721 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274160945.482, "dur": 2.244, + "args": { + "External id": 4049811,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7722 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274160951.752, "dur": 0.208, + "args": { + "External id": 4049812,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7723 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274160953.193, "dur": 0.149, + "args": { + "External id": 4049813,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7724 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274160954.853, "dur": 0.334, + "args": { + "External id": 4049814,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7725 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274160958.499, "dur": 0.415, + "args": { + "External id": 4049815,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7726 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274160960.154, "dur": 0.298, + "args": { + "External id": 4049816,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7727 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274160961.679, "dur": 2.967, + "args": { + "External id": 4049817,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7728 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274160965.803, "dur": 0.283, + "args": { + "External id": 4049818,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7729 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274160967.890, "dur": 0.222, + "args": { + "External id": 4049819,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7730 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336756, "tid": 1336756, + "ts": 1655274161021.772, "dur": 44.275, + "args": { + "External id": 4049820,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 7731 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 1336756, "tid": 1336756, + "ts": 1655274161101.127, "dur": 111.239, + "args": { + "External id": 4049821,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "6423040", "8", "3", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [], [], [], [], [], []], "Ev Idx": 7732 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274161112.320, "dur": 5.384, + "args": { + "External id": 4049822,"Record function id": 0, "Concrete Inputs": ["[51384320]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7733 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 1336756, "tid": 1336756, + "ts": 1655274161123.179, "dur": 10.736, + "args": { + "External id": 4049823,"Record function id": 0, "Concrete Inputs": ["", "0", "19269120", "6423040"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 7734 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1336756, + "ts": 1655274161127.508, "dur": 6.005, + "args": { + "External id": 4049824,"Record function id": 0, "Concrete Inputs": ["", "0", "19269120", "25692160", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[51384320], [], [], [], []], "Ev Idx": 7735 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274161131.335, "dur": 0.602, + "args": { + "External id": 4049825,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "[1]", "19269120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 7736 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336756, "tid": 1336756, + "ts": 1655274161141.611, "dur": 27.305, + "args": { + "External id": 4049826,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 7737 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274161144.111, "dur": 2.080, + "args": { + "External id": 4049827,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "19269120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7738 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274161147.981, "dur": 0.313, + "args": { + "External id": 4049828,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "19269376"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7739 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274161149.548, "dur": 0.156, + "args": { + "External id": 4049829,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "19793664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7740 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274161153.029, "dur": 1.241, + "args": { + "External id": 4049830,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "20317952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7741 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274161155.653, "dur": 0.302, + "args": { + "External id": 4049831,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "20842240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7742 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274161157.278, "dur": 0.352, + "args": { + "External id": 4049832,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "21366528"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7743 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274161160.337, "dur": 0.145, + "args": { + "External id": 4049833,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "21366784"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7744 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274161161.951, "dur": 0.155, + "args": { + "External id": 4049834,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "22808576"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7745 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274161163.450, "dur": 1.953, + "args": { + "External id": 4049835,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "24250368"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7746 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336756, "tid": 1336756, + "ts": 1655274161180.285, "dur": 24.919, + "args": { + "External id": 4049836,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 7747 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 1336756, "tid": 1336756, + "ts": 1655274161266.654, "dur": 375.004, + "args": { + "External id": 4049837,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[51384320], [6423040], [], [], []], "Ev Idx": 7748 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336756, "tid": 1336756, + "ts": 1655274161304.071, "dur": 332.631, + "args": { + "External id": 4049838,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 3, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "3", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 51384320, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[6423040], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 7749, "In msg nelems": 6423040 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 1336756, "tid": 1336756, + "ts": 1655274161314.374, "dur": 316.140, + "args": { + "External id": 4049839,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[6423040]], "Ev Idx": 7750 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336756, "tid": 1336756, + "ts": 1655274161664.044, "dur": 2.247, + "args": { + "External id": 4049840,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "3", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 7751, "In msg nelems": 0, "Rank": 3, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.22)", "pid": 1336756, "tid": 1336756, + "ts": 1655274161752.301, "dur": 16982.768, + "args": { + "External id": 4049841,"Record function id": 0, "Ev Idx": 7752 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274161843.712, "dur": 5.829, + "args": { + "External id": 4049842,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[51384320], []], "Ev Idx": 7753 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274161852.866, "dur": 0.837, + "args": { + "External id": 4049843,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 7754 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274161855.243, "dur": 2.064, + "args": { + "External id": 4049844,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 7755 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274161859.239, "dur": 0.794, + "args": { + "External id": 4049845,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 7756 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274161861.276, "dur": 0.800, + "args": { + "External id": 4049846,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 7757 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274161864.852, "dur": 0.594, + "args": { + "External id": 4049847,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 7758 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274161866.970, "dur": 0.686, + "args": { + "External id": 4049848,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 7759 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274161869.225, "dur": 1.375, + "args": { + "External id": 4049849,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 7760 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274161871.939, "dur": 0.607, + "args": { + "External id": 4049850,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 7761 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274161875.831, "dur": 0.526, + "args": { + "External id": 4049851,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 7762 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 1336756, "tid": 1336756, + "ts": 1655274161894.074, "dur": 16805.059, + "args": { + "External id": 4049852,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 7763 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 1336756, "tid": 1336756, + "ts": 1655274161913.598, "dur": 16779.118, + "args": { + "External id": 4049853,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 7764 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274161932.069, "dur": 13.260, + "args": { + "External id": 4049854,"Record function id": 0, "Concrete Inputs": ["[2133]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7765 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655274161948.186, "dur": 16713.897, + "args": { + "External id": 4049855,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], [], []], "Ev Idx": 7766 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336756, "tid": 1336756, + "ts": 1655274161950.677, "dur": 16710.851, + "args": { + "External id": 4049856,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], []], "Ev Idx": 7767 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274161956.335, "dur": 5.660, + "args": { + "External id": 4049857,"Record function id": 0, "Concrete Inputs": ["[2133]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7768 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1336756, + "ts": 1655274161963.891, "dur": 16694.614, + "args": { + "External id": 4049858,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[2133], [2133], []], "Ev Idx": 7769 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 1336756, "tid": 1336756, + "ts": 1655274178854.014, "dur": 35.337, + "args": { + "External id": 4049859,"Sequence number": 40618397, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 7770 + } + }, + { + "ph": "s", "id": 183, "pid": 1336756, "tid": 1336756, "ts": 1655274178854.014, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 1336756, "tid": 1336756, + "ts": 1655274178877.586, "dur": 7.074, + "args": { + "External id": 4049860,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[8388608, 2048, 1], [8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048], [16, 4096, 2048]], "Ev Idx": 7771 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274178880.431, "dur": 3.995, + "args": { + "External id": 4049861,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 7772 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 1336756, "tid": 1336756, + "ts": 1655274178951.132, "dur": 100.402, + "args": { + "External id": 4049862,"Record function id": 0, "Ev Idx": 7773 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 1336756, "tid": 1336756, + "ts": 1655274179054.426, "dur": 1043.979, + "args": { + "External id": 4049863,"Record function id": 0, "Ev Idx": 7774 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 1336756, "tid": 1336756, + "ts": 1655274179093.146, "dur": 992.219, + "args": { + "External id": 4049864,"Sequence number": 40618398, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[8388608, 2048, 1], [1], [2048, 1], [2048, 1], [2048, 1], [32, 1], [32, 1], [2048, 1], [1], [2048, 1], [2048, 1], [5632, 1]], "Input Dims": [[16, 4096, 2048], [2048], [2048, 2048], [2048, 2048], [2048, 2048], [8192, 32], [8192, 32], [2048, 2048], [2048], [5632, 2048], [5632, 2048], [2048, 5632]], "Ev Idx": 7775 + } + }, + { + "ph": "s", "id": 182, "pid": 1336756, "tid": 1336756, "ts": 1655274179093.146, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 1336756, "tid": 1336756, + "ts": 1655274179157.041, "dur": 42.643, + "args": { + "External id": 4049865,"kernel_hash": "cd26ogptnjelaibpl2zumx5nxdttspqepvjkh7lpmsxbzrrexbxm", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "2048", "1", "9.9999999999999995e-07", "True", "2048", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/d2/cd26ogptnjelaibpl2zumx5nxdttspqepvjkh7lpmsxbzrrexbxm.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [65536, 2048], [2048], [65536], [], [], [], [], [], [], [], [], []], "Ev Idx": 7776 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274179211.534, "dur": 103.796, + "args": { + "External id": 4049866,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 7777 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274179324.659, "dur": 39.985, + "args": { + "External id": 4049867,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 7778 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274179372.274, "dur": 32.150, + "args": { + "External id": 4049868,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 7779 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336756, "tid": 1336756, + "ts": 1655274179449.217, "dur": 28.563, + "args": { + "External id": 4049869,"kernel_hash": "cahe5odluo4swiyj4n2lohwh57qg5lym5qsijyjsjca7pvto5oka", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/ah/cahe5odluo4swiyj4n2lohwh57qg5lym5qsijyjsjca7pvto5oka.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 7780 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336756, "tid": 1336756, + "ts": 1655274179496.483, "dur": 13.901, + "args": { + "External id": 4049870,"kernel_hash": "cahe5odluo4swiyj4n2lohwh57qg5lym5qsijyjsjca7pvto5oka", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/ah/cahe5odluo4swiyj4n2lohwh57qg5lym5qsijyjsjca7pvto5oka.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 7781 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 1336756, "tid": 1336756, + "ts": 1655274179527.550, "dur": 125.599, + "args": { + "External id": 4049871,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.125", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [], [], [], [], [], [], [], []], "Ev Idx": 7782 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336756, "tid": 1336756, + "ts": 1655274179576.128, "dur": 12.012, + "args": { + "External id": 4049872,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[8388608, 2048, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [], [], [], [], []], "Ev Idx": 7783 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274179581.411, "dur": 6.040, + "args": { + "External id": 4049873,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "[8388608, 2048, 64, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7784 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274179590.827, "dur": 5.095, + "args": { + "External id": 4049874,"Record function id": 0, "Concrete Inputs": ["[16, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7785 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274179597.204, "dur": 1.066, + "args": { + "External id": 4049875,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7786 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274179600.348, "dur": 3.529, + "args": { + "External id": 4049876,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7787 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274179663.424, "dur": 50.008, + "args": { + "External id": 4049877,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 7788 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_2", "pid": 1336756, "tid": 1336756, + "ts": 1655274179741.868, "dur": 25.503, + "args": { + "External id": 4049878,"kernel_hash": "ckbsutlugbs4qoncxuwq6kkwome3xojo3ke4p7z74lcl5h4q62to", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "2048", "1", "9.9999999999999995e-07", "True", "2048", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/kb/ckbsutlugbs4qoncxuwq6kkwome3xojo3ke4p7z74lcl5h4q62to.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [1], [2048, 1], [2048, 1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [65536, 2048], [2048], [65536, 2048], [65536, 2048], [65536], [], [], [], [], [], [], [], [], []], "Ev Idx": 7789 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274179775.420, "dur": 41.709, + "args": { + "External id": 4049879,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [5632, 1]], "Input Dims": [[65536, 2048], [2048, 5632], [65536, 5632]], "Ev Idx": 7790 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274179825.529, "dur": 35.344, + "args": { + "External id": 4049880,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [5632, 1]], "Input Dims": [[65536, 2048], [2048, 5632], [65536, 5632]], "Ev Idx": 7791 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 1336756, "tid": 1336756, + "ts": 1655274179883.295, "dur": 22.783, + "args": { + "External id": 4049881,"kernel_hash": "cgh2wg2b6li2ipjwrhdr326ycb37fu4v576nwebfoyhwx5kppapn", "grid": "grid(369098752,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "369098752"], "kernel_file": "/tmp/torchinductor_cvm/gh/cgh2wg2b6li2ipjwrhdr326ycb37fu4v576nwebfoyhwx5kppapn.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[5632, 1], [5632, 1], [23068672, 5632, 1], []], "Input Dims": [[65536, 5632], [65536, 5632], [16, 4096, 5632], []], "Ev Idx": 7792 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274179911.423, "dur": 34.608, + "args": { + "External id": 4049882,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [1, 5632], [2048, 1]], "Input Dims": [[65536, 5632], [5632, 2048], [65536, 2048]], "Ev Idx": 7793 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 1336756, "tid": 1336756, + "ts": 1655274179964.324, "dur": 16.270, + "args": { + "External id": 4049883,"kernel_hash": "cta7vcczabyyuqarwmn4dcnazkxudhfwrvnick7ql5cmsd5lz4rz", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/ta/cta7vcczabyyuqarwmn4dcnazkxudhfwrvnick7ql5cmsd5lz4rz.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[8388608, 2048, 1], [2048, 1], []], "Input Dims": [[16, 4096, 2048], [65536, 2048], []], "Ev Idx": 7794 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.22)", "pid": 1336756, "tid": 1336756, + "ts": 1655274180159.853, "dur": 71.234, + "args": { + "External id": 4049884,"Record function id": 0, "Ev Idx": 7795 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 1336756, "tid": 1336756, + "ts": 1655274180300.997, "dur": 46.656, + "args": { + "External id": 4049885,"Record function id": 0, "Ev Idx": 7796 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.23)", "pid": 1336756, "tid": 1336756, + "ts": 1655274180357.189, "dur": 18205.654, + "args": { + "External id": 4049886,"Record function id": 0, "Ev Idx": 7797 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.23)", "pid": 1336756, "tid": 1336756, + "ts": 1655274180365.374, "dur": 838.591, + "args": { + "External id": 4049887,"Record function id": 0, "Ev Idx": 7798 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274180455.904, "dur": 8.960, + "args": { + "External id": 4049888,"Record function id": 0, "Concrete Inputs": ["[6423040]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7799 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336756, "tid": 1336756, + "ts": 1655274180478.014, "dur": 31.018, + "args": { + "External id": 4049889,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 7800 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274180482.870, "dur": 2.253, + "args": { + "External id": 4049890,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7801 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274180488.772, "dur": 0.262, + "args": { + "External id": 4049891,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7802 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274180489.989, "dur": 0.284, + "args": { + "External id": 4049892,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7803 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274180491.560, "dur": 0.187, + "args": { + "External id": 4049893,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7804 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274180494.615, "dur": 0.323, + "args": { + "External id": 4049894,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7805 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274180496.251, "dur": 0.259, + "args": { + "External id": 4049895,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7806 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274180497.603, "dur": 2.981, + "args": { + "External id": 4049896,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7807 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274180502.049, "dur": 0.170, + "args": { + "External id": 4049897,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7808 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274180503.238, "dur": 0.365, + "args": { + "External id": 4049898,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7809 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336756, "tid": 1336756, + "ts": 1655274180519.318, "dur": 39.680, + "args": { + "External id": 4049899,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 7810 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 1336756, "tid": 1336756, + "ts": 1655274180591.061, "dur": 97.326, + "args": { + "External id": 4049900,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "6423040", "8", "3", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [], [], [], [], [], []], "Ev Idx": 7811 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274180601.650, "dur": 3.543, + "args": { + "External id": 4049901,"Record function id": 0, "Concrete Inputs": ["[51384320]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7812 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 1336756, "tid": 1336756, + "ts": 1655274180609.951, "dur": 9.226, + "args": { + "External id": 4049902,"Record function id": 0, "Concrete Inputs": ["", "0", "19269120", "6423040"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 7813 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1336756, + "ts": 1655274180614.132, "dur": 4.637, + "args": { + "External id": 4049903,"Record function id": 0, "Concrete Inputs": ["", "0", "19269120", "25692160", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[51384320], [], [], [], []], "Ev Idx": 7814 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274180617.143, "dur": 0.468, + "args": { + "External id": 4049904,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "[1]", "19269120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 7815 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336756, "tid": 1336756, + "ts": 1655274180625.359, "dur": 23.508, + "args": { + "External id": 4049905,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 7816 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274180626.803, "dur": 1.683, + "args": { + "External id": 4049906,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "19269120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7817 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274180629.773, "dur": 0.273, + "args": { + "External id": 4049907,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "19269376"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7818 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274180631.133, "dur": 0.214, + "args": { + "External id": 4049908,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "19793664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7819 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274180634.385, "dur": 1.250, + "args": { + "External id": 4049909,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "20317952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7820 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274180636.662, "dur": 0.370, + "args": { + "External id": 4049910,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "20842240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7821 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274180637.880, "dur": 0.292, + "args": { + "External id": 4049911,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "21366528"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7822 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274180641.159, "dur": 0.213, + "args": { + "External id": 4049912,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "21366784"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7823 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274180642.334, "dur": 0.166, + "args": { + "External id": 4049913,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "22808576"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7824 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274180643.351, "dur": 1.829, + "args": { + "External id": 4049914,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "24250368"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7825 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336756, "tid": 1336756, + "ts": 1655274180659.565, "dur": 21.644, + "args": { + "External id": 4049915,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 7826 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 1336756, "tid": 1336756, + "ts": 1655274180742.318, "dur": 370.931, + "args": { + "External id": 4049916,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[51384320], [6423040], [], [], []], "Ev Idx": 7827 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336756, "tid": 1336756, + "ts": 1655274180771.140, "dur": 337.102, + "args": { + "External id": 4049917,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 3, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "3", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 51384320, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[6423040], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 7828, "In msg nelems": 6423040 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 1336756, "tid": 1336756, + "ts": 1655274180780.645, "dur": 321.912, + "args": { + "External id": 4049918,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[6423040]], "Ev Idx": 7829 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336756, "tid": 1336756, + "ts": 1655274181135.424, "dur": 2.479, + "args": { + "External id": 4049919,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "3", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 7830, "In msg nelems": 0, "Rank": 3, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.23)", "pid": 1336756, "tid": 1336756, + "ts": 1655274181223.850, "dur": 17134.901, + "args": { + "External id": 4049920,"Record function id": 0, "Ev Idx": 7831 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274181342.483, "dur": 6.114, + "args": { + "External id": 4049921,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[51384320], []], "Ev Idx": 7832 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274181351.888, "dur": 0.820, + "args": { + "External id": 4049922,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 7833 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274181354.412, "dur": 1.563, + "args": { + "External id": 4049923,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 7834 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274181358.983, "dur": 0.638, + "args": { + "External id": 4049924,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 7835 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274181361.212, "dur": 0.709, + "args": { + "External id": 4049925,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 7836 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274181363.178, "dur": 0.550, + "args": { + "External id": 4049926,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 7837 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274181365.254, "dur": 0.602, + "args": { + "External id": 4049927,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 7838 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274181368.908, "dur": 1.674, + "args": { + "External id": 4049928,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 7839 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274181372.050, "dur": 0.664, + "args": { + "External id": 4049929,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 7840 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274181374.021, "dur": 0.569, + "args": { + "External id": 4049930,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 7841 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 1336756, "tid": 1336756, + "ts": 1655274181393.966, "dur": 16925.512, + "args": { + "External id": 4049931,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 7842 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 1336756, "tid": 1336756, + "ts": 1655274181409.488, "dur": 16903.231, + "args": { + "External id": 4049932,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 7843 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274181440.958, "dur": 13.111, + "args": { + "External id": 4049933,"Record function id": 0, "Concrete Inputs": ["[2133]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7844 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655274181458.825, "dur": 16822.360, + "args": { + "External id": 4049934,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], [], []], "Ev Idx": 7845 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336756, "tid": 1336756, + "ts": 1655274181461.344, "dur": 16819.218, + "args": { + "External id": 4049935,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], []], "Ev Idx": 7846 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274181466.257, "dur": 5.585, + "args": { + "External id": 4049936,"Record function id": 0, "Concrete Inputs": ["[2133]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7847 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1336756, + "ts": 1655274181473.427, "dur": 16804.131, + "args": { + "External id": 4049937,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[2133], [2133], []], "Ev Idx": 7848 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 1336756, "tid": 1336756, + "ts": 1655274198499.061, "dur": 37.630, + "args": { + "External id": 4049938,"Sequence number": 40618399, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 7849 + } + }, + { + "ph": "s", "id": 181, "pid": 1336756, "tid": 1336756, "ts": 1655274198499.061, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 1336756, "tid": 1336756, + "ts": 1655274198524.396, "dur": 7.599, + "args": { + "External id": 4049939,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[8388608, 2048, 1], [8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048], [16, 4096, 2048]], "Ev Idx": 7850 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274198527.398, "dur": 4.212, + "args": { + "External id": 4049940,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 7851 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 1336756, "tid": 1336756, + "ts": 1655274198600.437, "dur": 71.160, + "args": { + "External id": 4049941,"Record function id": 0, "Ev Idx": 7852 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 1336756, "tid": 1336756, + "ts": 1655274198673.030, "dur": 1036.895, + "args": { + "External id": 4049942,"Record function id": 0, "Ev Idx": 7853 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 1336756, "tid": 1336756, + "ts": 1655274198712.675, "dur": 985.036, + "args": { + "External id": 4049943,"Sequence number": 40618400, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[8388608, 2048, 1], [1], [2048, 1], [2048, 1], [2048, 1], [32, 1], [32, 1], [2048, 1], [1], [2048, 1], [2048, 1], [5632, 1]], "Input Dims": [[16, 4096, 2048], [2048], [2048, 2048], [2048, 2048], [2048, 2048], [8192, 32], [8192, 32], [2048, 2048], [2048], [5632, 2048], [5632, 2048], [2048, 5632]], "Ev Idx": 7854 + } + }, + { + "ph": "s", "id": 180, "pid": 1336756, "tid": 1336756, "ts": 1655274198712.675, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 1336756, "tid": 1336756, + "ts": 1655274198777.785, "dur": 40.304, + "args": { + "External id": 4049944,"kernel_hash": "cd26ogptnjelaibpl2zumx5nxdttspqepvjkh7lpmsxbzrrexbxm", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "2048", "1", "9.9999999999999995e-07", "True", "2048", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/d2/cd26ogptnjelaibpl2zumx5nxdttspqepvjkh7lpmsxbzrrexbxm.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [65536, 2048], [2048], [65536], [], [], [], [], [], [], [], [], []], "Ev Idx": 7855 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274198829.772, "dur": 106.038, + "args": { + "External id": 4049945,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 7856 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274198944.283, "dur": 74.545, + "args": { + "External id": 4049946,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 7857 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274199031.524, "dur": 36.139, + "args": { + "External id": 4049947,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 7858 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336756, "tid": 1336756, + "ts": 1655274199092.229, "dur": 25.003, + "args": { + "External id": 4049948,"kernel_hash": "cahe5odluo4swiyj4n2lohwh57qg5lym5qsijyjsjca7pvto5oka", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/ah/cahe5odluo4swiyj4n2lohwh57qg5lym5qsijyjsjca7pvto5oka.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 7859 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336756, "tid": 1336756, + "ts": 1655274199133.906, "dur": 13.517, + "args": { + "External id": 4049949,"kernel_hash": "cahe5odluo4swiyj4n2lohwh57qg5lym5qsijyjsjca7pvto5oka", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/ah/cahe5odluo4swiyj4n2lohwh57qg5lym5qsijyjsjca7pvto5oka.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 7860 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 1336756, "tid": 1336756, + "ts": 1655274199164.011, "dur": 120.956, + "args": { + "External id": 4049950,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.125", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [], [], [], [], [], [], [], []], "Ev Idx": 7861 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336756, "tid": 1336756, + "ts": 1655274199211.420, "dur": 10.529, + "args": { + "External id": 4049951,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[8388608, 2048, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [], [], [], [], []], "Ev Idx": 7862 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274199216.347, "dur": 4.837, + "args": { + "External id": 4049952,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "[8388608, 2048, 64, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7863 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274199224.289, "dur": 5.349, + "args": { + "External id": 4049953,"Record function id": 0, "Concrete Inputs": ["[16, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7864 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274199230.898, "dur": 1.224, + "args": { + "External id": 4049954,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7865 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274199234.227, "dur": 3.215, + "args": { + "External id": 4049955,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7866 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274199295.283, "dur": 45.103, + "args": { + "External id": 4049956,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 7867 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_2", "pid": 1336756, "tid": 1336756, + "ts": 1655274199368.644, "dur": 25.299, + "args": { + "External id": 4049957,"kernel_hash": "ckbsutlugbs4qoncxuwq6kkwome3xojo3ke4p7z74lcl5h4q62to", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "2048", "1", "9.9999999999999995e-07", "True", "2048", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/kb/ckbsutlugbs4qoncxuwq6kkwome3xojo3ke4p7z74lcl5h4q62to.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [1], [2048, 1], [2048, 1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [65536, 2048], [2048], [65536, 2048], [65536, 2048], [65536], [], [], [], [], [], [], [], [], []], "Ev Idx": 7868 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274199402.062, "dur": 58.052, + "args": { + "External id": 4049958,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [5632, 1]], "Input Dims": [[65536, 2048], [2048, 5632], [65536, 5632]], "Ev Idx": 7869 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274199470.889, "dur": 37.367, + "args": { + "External id": 4049959,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [5632, 1]], "Input Dims": [[65536, 2048], [2048, 5632], [65536, 5632]], "Ev Idx": 7870 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 1336756, "tid": 1336756, + "ts": 1655274199528.920, "dur": 23.694, + "args": { + "External id": 4049960,"kernel_hash": "cgh2wg2b6li2ipjwrhdr326ycb37fu4v576nwebfoyhwx5kppapn", "grid": "grid(369098752,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "369098752"], "kernel_file": "/tmp/torchinductor_cvm/gh/cgh2wg2b6li2ipjwrhdr326ycb37fu4v576nwebfoyhwx5kppapn.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[5632, 1], [5632, 1], [23068672, 5632, 1], []], "Input Dims": [[65536, 5632], [65536, 5632], [16, 4096, 5632], []], "Ev Idx": 7871 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274199558.294, "dur": 33.875, + "args": { + "External id": 4049961,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [1, 5632], [2048, 1]], "Input Dims": [[65536, 5632], [5632, 2048], [65536, 2048]], "Ev Idx": 7872 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 1336756, "tid": 1336756, + "ts": 1655274199612.637, "dur": 17.333, + "args": { + "External id": 4049962,"kernel_hash": "cta7vcczabyyuqarwmn4dcnazkxudhfwrvnick7ql5cmsd5lz4rz", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/ta/cta7vcczabyyuqarwmn4dcnazkxudhfwrvnick7ql5cmsd5lz4rz.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[8388608, 2048, 1], [2048, 1], []], "Input Dims": [[16, 4096, 2048], [65536, 2048], []], "Ev Idx": 7873 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.23)", "pid": 1336756, "tid": 1336756, + "ts": 1655274199772.182, "dur": 70.011, + "args": { + "External id": 4049963,"Record function id": 0, "Ev Idx": 7874 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 1336756, "tid": 1336756, + "ts": 1655274199912.838, "dur": 45.437, + "args": { + "External id": 4049964,"Record function id": 0, "Ev Idx": 7875 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.24)", "pid": 1336756, "tid": 1336756, + "ts": 1655274199967.964, "dur": 18157.469, + "args": { + "External id": 4049965,"Record function id": 0, "Ev Idx": 7876 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.24)", "pid": 1336756, "tid": 1336756, + "ts": 1655274199976.286, "dur": 910.475, + "args": { + "External id": 4049966,"Record function id": 0, "Ev Idx": 7877 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274200088.412, "dur": 8.878, + "args": { + "External id": 4049967,"Record function id": 0, "Concrete Inputs": ["[6423040]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7878 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336756, "tid": 1336756, + "ts": 1655274200111.312, "dur": 33.027, + "args": { + "External id": 4049968,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 7879 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274200116.549, "dur": 2.490, + "args": { + "External id": 4049969,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7880 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274200122.912, "dur": 0.608, + "args": { + "External id": 4049970,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7881 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274200124.956, "dur": 0.285, + "args": { + "External id": 4049971,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7882 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274200126.709, "dur": 0.340, + "args": { + "External id": 4049972,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7883 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274200129.772, "dur": 0.207, + "args": { + "External id": 4049973,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7884 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274200130.889, "dur": 0.467, + "args": { + "External id": 4049974,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7885 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274200132.865, "dur": 2.760, + "args": { + "External id": 4049975,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7886 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274200136.635, "dur": 0.365, + "args": { + "External id": 4049976,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7887 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274200138.136, "dur": 0.431, + "args": { + "External id": 4049977,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7888 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336756, "tid": 1336756, + "ts": 1655274200154.968, "dur": 37.109, + "args": { + "External id": 4049978,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 7889 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 1336756, "tid": 1336756, + "ts": 1655274200223.335, "dur": 101.709, + "args": { + "External id": 4049979,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "6423040", "8", "3", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [], [], [], [], [], []], "Ev Idx": 7890 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274200234.065, "dur": 4.088, + "args": { + "External id": 4049980,"Record function id": 0, "Concrete Inputs": ["[51384320]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7891 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 1336756, "tid": 1336756, + "ts": 1655274200243.065, "dur": 9.886, + "args": { + "External id": 4049981,"Record function id": 0, "Concrete Inputs": ["", "0", "19269120", "6423040"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 7892 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1336756, + "ts": 1655274200247.305, "dur": 5.232, + "args": { + "External id": 4049982,"Record function id": 0, "Concrete Inputs": ["", "0", "19269120", "25692160", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[51384320], [], [], [], []], "Ev Idx": 7893 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274200250.776, "dur": 0.585, + "args": { + "External id": 4049983,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "[1]", "19269120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 7894 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336756, "tid": 1336756, + "ts": 1655274200259.920, "dur": 24.848, + "args": { + "External id": 4049984,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 7895 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274200262.208, "dur": 2.239, + "args": { + "External id": 4049985,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "19269120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7896 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274200265.873, "dur": 0.543, + "args": { + "External id": 4049986,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "19269376"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7897 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274200267.284, "dur": 0.265, + "args": { + "External id": 4049987,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "19793664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7898 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274200270.195, "dur": 1.022, + "args": { + "External id": 4049988,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "20317952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7899 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274200272.082, "dur": 0.171, + "args": { + "External id": 4049989,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "20842240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7900 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274200273.098, "dur": 0.281, + "args": { + "External id": 4049990,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "21366528"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7901 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274200276.421, "dur": 0.138, + "args": { + "External id": 4049991,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "21366784"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7902 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274200277.471, "dur": 0.184, + "args": { + "External id": 4049992,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "22808576"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7903 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274200278.935, "dur": 2.085, + "args": { + "External id": 4049993,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "24250368"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7904 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336756, "tid": 1336756, + "ts": 1655274200294.848, "dur": 23.080, + "args": { + "External id": 4049994,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 7905 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 1336756, "tid": 1336756, + "ts": 1655274200378.183, "dur": 412.874, + "args": { + "External id": 4049995,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[51384320], [6423040], [], [], []], "Ev Idx": 7906 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336756, "tid": 1336756, + "ts": 1655274200407.959, "dur": 377.654, + "args": { + "External id": 4049996,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 3, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "3", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 51384320, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[6423040], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 7907, "In msg nelems": 6423040 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 1336756, "tid": 1336756, + "ts": 1655274200433.311, "dur": 345.320, + "args": { + "External id": 4049997,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[6423040]], "Ev Idx": 7908 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336756, "tid": 1336756, + "ts": 1655274200815.711, "dur": 2.705, + "args": { + "External id": 4049998,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "3", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 7909, "In msg nelems": 0, "Rank": 3, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.24)", "pid": 1336756, "tid": 1336756, + "ts": 1655274200907.782, "dur": 17006.106, + "args": { + "External id": 4049999,"Record function id": 0, "Ev Idx": 7910 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274201041.997, "dur": 7.126, + "args": { + "External id": 4050000,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[51384320], []], "Ev Idx": 7911 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274201052.933, "dur": 1.120, + "args": { + "External id": 4050001,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 7912 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274201055.837, "dur": 2.153, + "args": { + "External id": 4050002,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 7913 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274201059.707, "dur": 0.776, + "args": { + "External id": 4050003,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 7914 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274201071.379, "dur": 1.042, + "args": { + "External id": 4050004,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 7915 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274201076.063, "dur": 0.815, + "args": { + "External id": 4050005,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 7916 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274201080.438, "dur": 0.777, + "args": { + "External id": 4050006,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 7917 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274201082.485, "dur": 1.956, + "args": { + "External id": 4050007,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 7918 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274201085.800, "dur": 0.670, + "args": { + "External id": 4050008,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 7919 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274201087.810, "dur": 0.631, + "args": { + "External id": 4050009,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 7920 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 1336756, "tid": 1336756, + "ts": 1655274201110.996, "dur": 16764.185, + "args": { + "External id": 4050010,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 7921 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 1336756, "tid": 1336756, + "ts": 1655274201126.437, "dur": 16742.699, + "args": { + "External id": 4050011,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 7922 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274201144.795, "dur": 13.589, + "args": { + "External id": 4050012,"Record function id": 0, "Concrete Inputs": ["[2133]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7923 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655274201161.310, "dur": 16676.877, + "args": { + "External id": 4050013,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], [], []], "Ev Idx": 7924 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336756, "tid": 1336756, + "ts": 1655274201164.050, "dur": 16673.650, + "args": { + "External id": 4050014,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], []], "Ev Idx": 7925 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274201169.917, "dur": 5.032, + "args": { + "External id": 4050015,"Record function id": 0, "Concrete Inputs": ["[2133]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7926 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1336756, + "ts": 1655274201176.552, "dur": 16658.380, + "args": { + "External id": 4050016,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[2133], [2133], []], "Ev Idx": 7927 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 1336756, "tid": 1336756, + "ts": 1655274218064.726, "dur": 35.174, + "args": { + "External id": 4050017,"Sequence number": 40618401, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 7928 + } + }, + { + "ph": "s", "id": 179, "pid": 1336756, "tid": 1336756, "ts": 1655274218064.726, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 1336756, "tid": 1336756, + "ts": 1655274218087.968, "dur": 7.248, + "args": { + "External id": 4050018,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[8388608, 2048, 1], [8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048], [16, 4096, 2048]], "Ev Idx": 7929 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274218091.046, "dur": 3.803, + "args": { + "External id": 4050019,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 7930 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 1336756, "tid": 1336756, + "ts": 1655274218162.866, "dur": 71.509, + "args": { + "External id": 4050020,"Record function id": 0, "Ev Idx": 7931 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 1336756, "tid": 1336756, + "ts": 1655274218236.135, "dur": 1027.781, + "args": { + "External id": 4050021,"Record function id": 0, "Ev Idx": 7932 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 1336756, "tid": 1336756, + "ts": 1655274218274.208, "dur": 977.071, + "args": { + "External id": 4050022,"Sequence number": 40618402, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[8388608, 2048, 1], [1], [2048, 1], [2048, 1], [2048, 1], [32, 1], [32, 1], [2048, 1], [1], [2048, 1], [2048, 1], [5632, 1]], "Input Dims": [[16, 4096, 2048], [2048], [2048, 2048], [2048, 2048], [2048, 2048], [8192, 32], [8192, 32], [2048, 2048], [2048], [5632, 2048], [5632, 2048], [2048, 5632]], "Ev Idx": 7933 + } + }, + { + "ph": "s", "id": 178, "pid": 1336756, "tid": 1336756, "ts": 1655274218274.208, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 1336756, "tid": 1336756, + "ts": 1655274218335.500, "dur": 39.657, + "args": { + "External id": 4050023,"kernel_hash": "cd26ogptnjelaibpl2zumx5nxdttspqepvjkh7lpmsxbzrrexbxm", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "2048", "1", "9.9999999999999995e-07", "True", "2048", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/d2/cd26ogptnjelaibpl2zumx5nxdttspqepvjkh7lpmsxbzrrexbxm.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [65536, 2048], [2048], [65536], [], [], [], [], [], [], [], [], []], "Ev Idx": 7934 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274218386.954, "dur": 119.843, + "args": { + "External id": 4050024,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 7935 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274218519.408, "dur": 40.197, + "args": { + "External id": 4050025,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 7936 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274218568.414, "dur": 32.162, + "args": { + "External id": 4050026,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 7937 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336756, "tid": 1336756, + "ts": 1655274218625.146, "dur": 24.502, + "args": { + "External id": 4050027,"kernel_hash": "cahe5odluo4swiyj4n2lohwh57qg5lym5qsijyjsjca7pvto5oka", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/ah/cahe5odluo4swiyj4n2lohwh57qg5lym5qsijyjsjca7pvto5oka.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 7938 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336756, "tid": 1336756, + "ts": 1655274218665.889, "dur": 14.645, + "args": { + "External id": 4050028,"kernel_hash": "cahe5odluo4swiyj4n2lohwh57qg5lym5qsijyjsjca7pvto5oka", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/ah/cahe5odluo4swiyj4n2lohwh57qg5lym5qsijyjsjca7pvto5oka.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 7939 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 1336756, "tid": 1336756, + "ts": 1655274218697.691, "dur": 121.372, + "args": { + "External id": 4050029,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.125", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [], [], [], [], [], [], [], []], "Ev Idx": 7940 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336756, "tid": 1336756, + "ts": 1655274218745.285, "dur": 10.128, + "args": { + "External id": 4050030,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[8388608, 2048, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [], [], [], [], []], "Ev Idx": 7941 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274218749.956, "dur": 4.710, + "args": { + "External id": 4050031,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "[8388608, 2048, 64, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7942 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274218757.921, "dur": 5.343, + "args": { + "External id": 4050032,"Record function id": 0, "Concrete Inputs": ["[16, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7943 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274218764.693, "dur": 1.312, + "args": { + "External id": 4050033,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7944 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274218768.292, "dur": 2.840, + "args": { + "External id": 4050034,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7945 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274218828.750, "dur": 45.009, + "args": { + "External id": 4050035,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 7946 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_2", "pid": 1336756, "tid": 1336756, + "ts": 1655274218901.680, "dur": 24.283, + "args": { + "External id": 4050036,"kernel_hash": "ckbsutlugbs4qoncxuwq6kkwome3xojo3ke4p7z74lcl5h4q62to", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "2048", "1", "9.9999999999999995e-07", "True", "2048", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/kb/ckbsutlugbs4qoncxuwq6kkwome3xojo3ke4p7z74lcl5h4q62to.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [1], [2048, 1], [2048, 1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [65536, 2048], [2048], [65536, 2048], [65536, 2048], [65536], [], [], [], [], [], [], [], [], []], "Ev Idx": 7947 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274218933.612, "dur": 41.156, + "args": { + "External id": 4050037,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [5632, 1]], "Input Dims": [[65536, 2048], [2048, 5632], [65536, 5632]], "Ev Idx": 7948 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274219019.380, "dur": 41.584, + "args": { + "External id": 4050038,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [5632, 1]], "Input Dims": [[65536, 2048], [2048, 5632], [65536, 5632]], "Ev Idx": 7949 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 1336756, "tid": 1336756, + "ts": 1655274219085.878, "dur": 24.099, + "args": { + "External id": 4050039,"kernel_hash": "cgh2wg2b6li2ipjwrhdr326ycb37fu4v576nwebfoyhwx5kppapn", "grid": "grid(369098752,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "369098752"], "kernel_file": "/tmp/torchinductor_cvm/gh/cgh2wg2b6li2ipjwrhdr326ycb37fu4v576nwebfoyhwx5kppapn.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[5632, 1], [5632, 1], [23068672, 5632, 1], []], "Input Dims": [[65536, 5632], [65536, 5632], [16, 4096, 5632], []], "Ev Idx": 7950 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274219116.260, "dur": 35.490, + "args": { + "External id": 4050040,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [1, 5632], [2048, 1]], "Input Dims": [[65536, 5632], [5632, 2048], [65536, 2048]], "Ev Idx": 7951 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 1336756, "tid": 1336756, + "ts": 1655274219169.736, "dur": 17.413, + "args": { + "External id": 4050041,"kernel_hash": "cta7vcczabyyuqarwmn4dcnazkxudhfwrvnick7ql5cmsd5lz4rz", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/ta/cta7vcczabyyuqarwmn4dcnazkxudhfwrvnick7ql5cmsd5lz4rz.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[8388608, 2048, 1], [2048, 1], []], "Input Dims": [[16, 4096, 2048], [65536, 2048], []], "Ev Idx": 7952 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.24)", "pid": 1336756, "tid": 1336756, + "ts": 1655274219325.389, "dur": 70.251, + "args": { + "External id": 4050042,"Record function id": 0, "Ev Idx": 7953 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 1336756, "tid": 1336756, + "ts": 1655274219486.275, "dur": 47.235, + "args": { + "External id": 4050043,"Record function id": 0, "Ev Idx": 7954 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.25)", "pid": 1336756, "tid": 1336756, + "ts": 1655274219542.584, "dur": 18181.937, + "args": { + "External id": 4050044,"Record function id": 0, "Ev Idx": 7955 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.25)", "pid": 1336756, "tid": 1336756, + "ts": 1655274219551.444, "dur": 835.218, + "args": { + "External id": 4050045,"Record function id": 0, "Ev Idx": 7956 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274219626.874, "dur": 9.556, + "args": { + "External id": 4050046,"Record function id": 0, "Concrete Inputs": ["[6423040]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7957 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336756, "tid": 1336756, + "ts": 1655274219649.754, "dur": 35.257, + "args": { + "External id": 4050047,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 7958 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274219654.960, "dur": 2.342, + "args": { + "External id": 4050048,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7959 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274219661.048, "dur": 0.427, + "args": { + "External id": 4050049,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7960 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274219662.651, "dur": 0.669, + "args": { + "External id": 4050050,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7961 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274219668.142, "dur": 0.380, + "args": { + "External id": 4050051,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7962 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274219671.142, "dur": 0.406, + "args": { + "External id": 4050052,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7963 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274219672.801, "dur": 0.324, + "args": { + "External id": 4050053,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7964 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274219674.061, "dur": 2.093, + "args": { + "External id": 4050054,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7965 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274219677.090, "dur": 0.576, + "args": { + "External id": 4050055,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7966 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274219678.801, "dur": 0.448, + "args": { + "External id": 4050056,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7967 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336756, "tid": 1336756, + "ts": 1655274219695.211, "dur": 40.709, + "args": { + "External id": 4050057,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 7968 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 1336756, "tid": 1336756, + "ts": 1655274219765.717, "dur": 101.679, + "args": { + "External id": 4050058,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "6423040", "8", "3", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [], [], [], [], [], []], "Ev Idx": 7969 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274219776.101, "dur": 4.040, + "args": { + "External id": 4050059,"Record function id": 0, "Concrete Inputs": ["[51384320]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 7970 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 1336756, "tid": 1336756, + "ts": 1655274219785.003, "dur": 9.691, + "args": { + "External id": 4050060,"Record function id": 0, "Concrete Inputs": ["", "0", "19269120", "6423040"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 7971 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1336756, + "ts": 1655274219789.071, "dur": 5.205, + "args": { + "External id": 4050061,"Record function id": 0, "Concrete Inputs": ["", "0", "19269120", "25692160", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[51384320], [], [], [], []], "Ev Idx": 7972 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274219792.388, "dur": 0.746, + "args": { + "External id": 4050062,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "[1]", "19269120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 7973 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336756, "tid": 1336756, + "ts": 1655274219801.453, "dur": 26.057, + "args": { + "External id": 4050063,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 7974 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274219803.757, "dur": 1.918, + "args": { + "External id": 4050064,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "19269120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7975 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274219806.595, "dur": 0.649, + "args": { + "External id": 4050065,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "19269376"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7976 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274219808.390, "dur": 0.927, + "args": { + "External id": 4050066,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "19793664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7977 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274219812.053, "dur": 0.332, + "args": { + "External id": 4050067,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "20317952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7978 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274219813.473, "dur": 0.499, + "args": { + "External id": 4050068,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "20842240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7979 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274219814.919, "dur": 0.604, + "args": { + "External id": 4050069,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "21366528"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7980 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274219818.077, "dur": 0.645, + "args": { + "External id": 4050070,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "21366784"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7981 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274219819.710, "dur": 0.735, + "args": { + "External id": 4050071,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "22808576"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7982 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274219821.872, "dur": 1.805, + "args": { + "External id": 4050072,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "24250368"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 7983 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336756, "tid": 1336756, + "ts": 1655274219838.457, "dur": 21.360, + "args": { + "External id": 4050073,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 7984 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 1336756, "tid": 1336756, + "ts": 1655274219918.665, "dur": 376.077, + "args": { + "External id": 4050074,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[51384320], [6423040], [], [], []], "Ev Idx": 7985 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336756, "tid": 1336756, + "ts": 1655274219948.796, "dur": 341.176, + "args": { + "External id": 4050075,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 3, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "3", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 51384320, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[6423040], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 7986, "In msg nelems": 6423040 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 1336756, "tid": 1336756, + "ts": 1655274219958.558, "dur": 325.703, + "args": { + "External id": 4050076,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[6423040]], "Ev Idx": 7987 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336756, "tid": 1336756, + "ts": 1655274220318.605, "dur": 2.419, + "args": { + "External id": 4050077,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "3", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 7988, "In msg nelems": 0, "Rank": 3, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.25)", "pid": 1336756, "tid": 1336756, + "ts": 1655274220405.892, "dur": 17140.391, + "args": { + "External id": 4050078,"Record function id": 0, "Ev Idx": 7989 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274220517.370, "dur": 6.844, + "args": { + "External id": 4050079,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[51384320], []], "Ev Idx": 7990 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274220528.183, "dur": 1.195, + "args": { + "External id": 4050080,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 7991 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274220531.025, "dur": 1.167, + "args": { + "External id": 4050081,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 7992 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274220533.986, "dur": 1.166, + "args": { + "External id": 4050082,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 7993 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274220536.489, "dur": 1.038, + "args": { + "External id": 4050083,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 7994 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274220538.879, "dur": 0.842, + "args": { + "External id": 4050084,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 7995 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274220543.472, "dur": 1.082, + "args": { + "External id": 4050085,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 7996 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274220545.851, "dur": 2.044, + "args": { + "External id": 4050086,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 7997 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274220549.307, "dur": 0.991, + "args": { + "External id": 4050087,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 7998 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274220551.773, "dur": 0.746, + "args": { + "External id": 4050088,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 7999 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 1336756, "tid": 1336756, + "ts": 1655274220572.161, "dur": 16938.035, + "args": { + "External id": 4050089,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 8000 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 1336756, "tid": 1336756, + "ts": 1655274220587.187, "dur": 16916.689, + "args": { + "External id": 4050090,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 8001 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274220610.030, "dur": 11.987, + "args": { + "External id": 4050091,"Record function id": 0, "Concrete Inputs": ["[2133]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8002 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655274220624.825, "dur": 16847.404, + "args": { + "External id": 4050092,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], [], []], "Ev Idx": 8003 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336756, "tid": 1336756, + "ts": 1655274220627.371, "dur": 16844.355, + "args": { + "External id": 4050093,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], []], "Ev Idx": 8004 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274220632.927, "dur": 5.428, + "args": { + "External id": 4050094,"Record function id": 0, "Concrete Inputs": ["[2133]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8005 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1336756, + "ts": 1655274220640.113, "dur": 16828.913, + "args": { + "External id": 4050095,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[2133], [2133], []], "Ev Idx": 8006 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 1336756, "tid": 1336756, + "ts": 1655274237664.400, "dur": 36.620, + "args": { + "External id": 4050096,"Sequence number": 40618403, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 8007 + } + }, + { + "ph": "s", "id": 177, "pid": 1336756, "tid": 1336756, "ts": 1655274237664.400, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 1336756, "tid": 1336756, + "ts": 1655274237689.011, "dur": 7.439, + "args": { + "External id": 4050097,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[8388608, 2048, 1], [8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048], [16, 4096, 2048]], "Ev Idx": 8008 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274237692.246, "dur": 3.955, + "args": { + "External id": 4050098,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8009 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 1336756, "tid": 1336756, + "ts": 1655274237760.462, "dur": 69.087, + "args": { + "External id": 4050099,"Record function id": 0, "Ev Idx": 8010 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 1336756, "tid": 1336756, + "ts": 1655274237830.946, "dur": 1037.255, + "args": { + "External id": 4050100,"Record function id": 0, "Ev Idx": 8011 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 1336756, "tid": 1336756, + "ts": 1655274237867.550, "dur": 987.683, + "args": { + "External id": 4050101,"Sequence number": 40618404, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[8388608, 2048, 1], [1], [2048, 1], [2048, 1], [2048, 1], [32, 1], [32, 1], [2048, 1], [1], [2048, 1], [2048, 1], [5632, 1]], "Input Dims": [[16, 4096, 2048], [2048], [2048, 2048], [2048, 2048], [2048, 2048], [8192, 32], [8192, 32], [2048, 2048], [2048], [5632, 2048], [5632, 2048], [2048, 5632]], "Ev Idx": 8012 + } + }, + { + "ph": "s", "id": 176, "pid": 1336756, "tid": 1336756, "ts": 1655274237867.550, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 1336756, "tid": 1336756, + "ts": 1655274237929.697, "dur": 45.064, + "args": { + "External id": 4050102,"kernel_hash": "cd26ogptnjelaibpl2zumx5nxdttspqepvjkh7lpmsxbzrrexbxm", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "2048", "1", "9.9999999999999995e-07", "True", "2048", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/d2/cd26ogptnjelaibpl2zumx5nxdttspqepvjkh7lpmsxbzrrexbxm.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [65536, 2048], [2048], [65536], [], [], [], [], [], [], [], [], []], "Ev Idx": 8013 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274238018.906, "dur": 97.341, + "args": { + "External id": 4050103,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 8014 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274238126.771, "dur": 37.654, + "args": { + "External id": 4050104,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 8015 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274238172.838, "dur": 32.017, + "args": { + "External id": 4050105,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 8016 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336756, "tid": 1336756, + "ts": 1655274238230.477, "dur": 25.139, + "args": { + "External id": 4050106,"kernel_hash": "cahe5odluo4swiyj4n2lohwh57qg5lym5qsijyjsjca7pvto5oka", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/ah/cahe5odluo4swiyj4n2lohwh57qg5lym5qsijyjsjca7pvto5oka.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 8017 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336756, "tid": 1336756, + "ts": 1655274238273.132, "dur": 14.355, + "args": { + "External id": 4050107,"kernel_hash": "cahe5odluo4swiyj4n2lohwh57qg5lym5qsijyjsjca7pvto5oka", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/ah/cahe5odluo4swiyj4n2lohwh57qg5lym5qsijyjsjca7pvto5oka.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 8018 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 1336756, "tid": 1336756, + "ts": 1655274238304.468, "dur": 138.177, + "args": { + "External id": 4050108,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.125", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [], [], [], [], [], [], [], []], "Ev Idx": 8019 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336756, "tid": 1336756, + "ts": 1655274238351.270, "dur": 10.921, + "args": { + "External id": 4050109,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[8388608, 2048, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [], [], [], [], []], "Ev Idx": 8020 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274238356.184, "dur": 5.248, + "args": { + "External id": 4050110,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "[8388608, 2048, 64, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8021 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274238364.663, "dur": 5.255, + "args": { + "External id": 4050111,"Record function id": 0, "Concrete Inputs": ["[16, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8022 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274238371.362, "dur": 1.561, + "args": { + "External id": 4050112,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8023 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274238375.289, "dur": 2.942, + "args": { + "External id": 4050113,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8024 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274238455.293, "dur": 50.271, + "args": { + "External id": 4050114,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 8025 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_2", "pid": 1336756, "tid": 1336756, + "ts": 1655274238536.844, "dur": 26.410, + "args": { + "External id": 4050115,"kernel_hash": "ckbsutlugbs4qoncxuwq6kkwome3xojo3ke4p7z74lcl5h4q62to", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "2048", "1", "9.9999999999999995e-07", "True", "2048", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/kb/ckbsutlugbs4qoncxuwq6kkwome3xojo3ke4p7z74lcl5h4q62to.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [1], [2048, 1], [2048, 1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [65536, 2048], [2048], [65536, 2048], [65536, 2048], [65536], [], [], [], [], [], [], [], [], []], "Ev Idx": 8026 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274238571.702, "dur": 42.527, + "args": { + "External id": 4050116,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [5632, 1]], "Input Dims": [[65536, 2048], [2048, 5632], [65536, 5632]], "Ev Idx": 8027 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274238622.150, "dur": 35.531, + "args": { + "External id": 4050117,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [5632, 1]], "Input Dims": [[65536, 2048], [2048, 5632], [65536, 5632]], "Ev Idx": 8028 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 1336756, "tid": 1336756, + "ts": 1655274238680.759, "dur": 32.483, + "args": { + "External id": 4050118,"kernel_hash": "cgh2wg2b6li2ipjwrhdr326ycb37fu4v576nwebfoyhwx5kppapn", "grid": "grid(369098752,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "369098752"], "kernel_file": "/tmp/torchinductor_cvm/gh/cgh2wg2b6li2ipjwrhdr326ycb37fu4v576nwebfoyhwx5kppapn.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[5632, 1], [5632, 1], [23068672, 5632, 1], []], "Input Dims": [[65536, 5632], [65536, 5632], [16, 4096, 5632], []], "Ev Idx": 8029 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274238719.555, "dur": 34.885, + "args": { + "External id": 4050119,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [1, 5632], [2048, 1]], "Input Dims": [[65536, 5632], [5632, 2048], [65536, 2048]], "Ev Idx": 8030 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 1336756, "tid": 1336756, + "ts": 1655274238773.076, "dur": 15.826, + "args": { + "External id": 4050120,"kernel_hash": "cta7vcczabyyuqarwmn4dcnazkxudhfwrvnick7ql5cmsd5lz4rz", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/ta/cta7vcczabyyuqarwmn4dcnazkxudhfwrvnick7ql5cmsd5lz4rz.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[8388608, 2048, 1], [2048, 1], []], "Input Dims": [[16, 4096, 2048], [65536, 2048], []], "Ev Idx": 8031 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.25)", "pid": 1336756, "tid": 1336756, + "ts": 1655274238930.664, "dur": 121.932, + "args": { + "External id": 4050121,"Record function id": 0, "Ev Idx": 8032 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 1336756, "tid": 1336756, + "ts": 1655274239131.528, "dur": 48.040, + "args": { + "External id": 4050122,"Record function id": 0, "Ev Idx": 8033 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.26)", "pid": 1336756, "tid": 1336756, + "ts": 1655274239188.344, "dur": 18190.532, + "args": { + "External id": 4050123,"Record function id": 0, "Ev Idx": 8034 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.26)", "pid": 1336756, "tid": 1336756, + "ts": 1655274239196.114, "dur": 874.765, + "args": { + "External id": 4050124,"Record function id": 0, "Ev Idx": 8035 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274239270.925, "dur": 9.269, + "args": { + "External id": 4050125,"Record function id": 0, "Concrete Inputs": ["[6423040]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8036 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336756, "tid": 1336756, + "ts": 1655274239292.827, "dur": 32.169, + "args": { + "External id": 4050126,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 8037 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274239297.965, "dur": 2.298, + "args": { + "External id": 4050127,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 8038 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274239304.349, "dur": 0.743, + "args": { + "External id": 4050128,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 8039 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274239306.272, "dur": 0.576, + "args": { + "External id": 4050129,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 8040 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274239307.844, "dur": 0.766, + "args": { + "External id": 4050130,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 8041 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274239311.048, "dur": 0.503, + "args": { + "External id": 4050131,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 8042 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274239312.759, "dur": 0.592, + "args": { + "External id": 4050132,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 8043 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274239314.296, "dur": 1.672, + "args": { + "External id": 4050133,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 8044 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274239316.807, "dur": 0.869, + "args": { + "External id": 4050134,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 8045 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274239318.679, "dur": 0.461, + "args": { + "External id": 4050135,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 8046 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336756, "tid": 1336756, + "ts": 1655274239334.910, "dur": 39.914, + "args": { + "External id": 4050136,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 8047 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 1336756, "tid": 1336756, + "ts": 1655274239405.099, "dur": 129.291, + "args": { + "External id": 4050137,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "6423040", "8", "3", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [], [], [], [], [], []], "Ev Idx": 8048 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274239432.534, "dur": 5.486, + "args": { + "External id": 4050138,"Record function id": 0, "Concrete Inputs": ["[51384320]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8049 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 1336756, "tid": 1336756, + "ts": 1655274239444.006, "dur": 10.029, + "args": { + "External id": 4050139,"Record function id": 0, "Concrete Inputs": ["", "0", "19269120", "6423040"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 8050 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1336756, + "ts": 1655274239448.113, "dur": 5.513, + "args": { + "External id": 4050140,"Record function id": 0, "Concrete Inputs": ["", "0", "19269120", "25692160", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[51384320], [], [], [], []], "Ev Idx": 8051 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274239451.446, "dur": 0.759, + "args": { + "External id": 4050141,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "[1]", "19269120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 8052 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336756, "tid": 1336756, + "ts": 1655274239461.706, "dur": 29.572, + "args": { + "External id": 4050142,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 8053 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274239463.593, "dur": 2.236, + "args": { + "External id": 4050143,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "19269120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 8054 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274239467.040, "dur": 0.980, + "args": { + "External id": 4050144,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "19269376"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 8055 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274239469.141, "dur": 0.637, + "args": { + "External id": 4050145,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "19793664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 8056 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274239472.259, "dur": 0.342, + "args": { + "External id": 4050146,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "20317952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 8057 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274239473.706, "dur": 0.403, + "args": { + "External id": 4050147,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "20842240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 8058 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274239478.298, "dur": 1.611, + "args": { + "External id": 4050148,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "21366528"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 8059 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274239482.429, "dur": 0.437, + "args": { + "External id": 4050149,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "21366784"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 8060 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274239483.610, "dur": 0.701, + "args": { + "External id": 4050150,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "22808576"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 8061 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274239485.245, "dur": 2.077, + "args": { + "External id": 4050151,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "24250368"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 8062 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336756, "tid": 1336756, + "ts": 1655274239501.535, "dur": 24.600, + "args": { + "External id": 4050152,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 8063 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 1336756, "tid": 1336756, + "ts": 1655274239587.235, "dur": 357.246, + "args": { + "External id": 4050153,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[51384320], [6423040], [], [], []], "Ev Idx": 8064 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336756, "tid": 1336756, + "ts": 1655274239616.336, "dur": 322.980, + "args": { + "External id": 4050154,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 3, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "3", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 51384320, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[6423040], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 8065, "In msg nelems": 6423040 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 1336756, "tid": 1336756, + "ts": 1655274239625.956, "dur": 307.197, + "args": { + "External id": 4050155,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[6423040]], "Ev Idx": 8066 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336756, "tid": 1336756, + "ts": 1655274239965.571, "dur": 2.490, + "args": { + "External id": 4050156,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "3", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 8067, "In msg nelems": 0, "Rank": 3, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.26)", "pid": 1336756, "tid": 1336756, + "ts": 1655274240091.685, "dur": 17108.995, + "args": { + "External id": 4050157,"Record function id": 0, "Ev Idx": 8068 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274240182.097, "dur": 6.797, + "args": { + "External id": 4050158,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[51384320], []], "Ev Idx": 8069 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274240192.363, "dur": 1.220, + "args": { + "External id": 4050159,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 8070 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274240195.441, "dur": 1.128, + "args": { + "External id": 4050160,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 8071 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274240198.207, "dur": 1.152, + "args": { + "External id": 4050161,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 8072 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274240200.709, "dur": 1.466, + "args": { + "External id": 4050162,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 8073 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274240203.573, "dur": 0.699, + "args": { + "External id": 4050163,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 8074 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274240207.493, "dur": 0.847, + "args": { + "External id": 4050164,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 8075 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274240209.939, "dur": 2.182, + "args": { + "External id": 4050165,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 8076 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274240213.359, "dur": 0.814, + "args": { + "External id": 4050166,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 8077 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274240215.470, "dur": 0.887, + "args": { + "External id": 4050167,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 8078 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 1336756, "tid": 1336756, + "ts": 1655274240235.394, "dur": 16930.402, + "args": { + "External id": 4050168,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 8079 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 1336756, "tid": 1336756, + "ts": 1655274240256.613, "dur": 16902.619, + "args": { + "External id": 4050169,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 8080 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274240273.960, "dur": 12.760, + "args": { + "External id": 4050170,"Record function id": 0, "Concrete Inputs": ["[2133]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8081 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655274240289.612, "dur": 16838.484, + "args": { + "External id": 4050171,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], [], []], "Ev Idx": 8082 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336756, "tid": 1336756, + "ts": 1655274240292.050, "dur": 16835.452, + "args": { + "External id": 4050172,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], []], "Ev Idx": 8083 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274240297.463, "dur": 5.289, + "args": { + "External id": 4050173,"Record function id": 0, "Concrete Inputs": ["[2133]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8084 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1336756, + "ts": 1655274240304.396, "dur": 16820.441, + "args": { + "External id": 4050174,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[2133], [2133], []], "Ev Idx": 8085 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 1336756, "tid": 1336756, + "ts": 1655274257320.072, "dur": 35.466, + "args": { + "External id": 4050175,"Sequence number": 40618405, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 8086 + } + }, + { + "ph": "s", "id": 175, "pid": 1336756, "tid": 1336756, "ts": 1655274257320.072, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 1336756, "tid": 1336756, + "ts": 1655274257343.060, "dur": 7.566, + "args": { + "External id": 4050176,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[8388608, 2048, 1], [8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048], [16, 4096, 2048]], "Ev Idx": 8087 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274257346.211, "dur": 4.164, + "args": { + "External id": 4050177,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8088 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 1336756, "tid": 1336756, + "ts": 1655274257427.637, "dur": 71.795, + "args": { + "External id": 4050178,"Record function id": 0, "Ev Idx": 8089 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 1336756, "tid": 1336756, + "ts": 1655274257501.485, "dur": 1033.120, + "args": { + "External id": 4050179,"Record function id": 0, "Ev Idx": 8090 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 1336756, "tid": 1336756, + "ts": 1655274257541.649, "dur": 980.239, + "args": { + "External id": 4050180,"Sequence number": 40618406, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[8388608, 2048, 1], [1], [2048, 1], [2048, 1], [2048, 1], [32, 1], [32, 1], [2048, 1], [1], [2048, 1], [2048, 1], [5632, 1]], "Input Dims": [[16, 4096, 2048], [2048], [2048, 2048], [2048, 2048], [2048, 2048], [8192, 32], [8192, 32], [2048, 2048], [2048], [5632, 2048], [5632, 2048], [2048, 5632]], "Ev Idx": 8091 + } + }, + { + "ph": "s", "id": 174, "pid": 1336756, "tid": 1336756, "ts": 1655274257541.649, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 1336756, "tid": 1336756, + "ts": 1655274257605.188, "dur": 40.881, + "args": { + "External id": 4050181,"kernel_hash": "cd26ogptnjelaibpl2zumx5nxdttspqepvjkh7lpmsxbzrrexbxm", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "2048", "1", "9.9999999999999995e-07", "True", "2048", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/d2/cd26ogptnjelaibpl2zumx5nxdttspqepvjkh7lpmsxbzrrexbxm.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [65536, 2048], [2048], [65536], [], [], [], [], [], [], [], [], []], "Ev Idx": 8092 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274257658.208, "dur": 101.935, + "args": { + "External id": 4050182,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 8093 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274257768.029, "dur": 39.438, + "args": { + "External id": 4050183,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 8094 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274257815.638, "dur": 32.311, + "args": { + "External id": 4050184,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 8095 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336756, "tid": 1336756, + "ts": 1655274257870.403, "dur": 24.565, + "args": { + "External id": 4050185,"kernel_hash": "cahe5odluo4swiyj4n2lohwh57qg5lym5qsijyjsjca7pvto5oka", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/ah/cahe5odluo4swiyj4n2lohwh57qg5lym5qsijyjsjca7pvto5oka.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 8096 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336756, "tid": 1336756, + "ts": 1655274257911.416, "dur": 13.669, + "args": { + "External id": 4050186,"kernel_hash": "cahe5odluo4swiyj4n2lohwh57qg5lym5qsijyjsjca7pvto5oka", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/ah/cahe5odluo4swiyj4n2lohwh57qg5lym5qsijyjsjca7pvto5oka.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 8097 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 1336756, "tid": 1336756, + "ts": 1655274257941.220, "dur": 166.758, + "args": { + "External id": 4050187,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.125", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [], [], [], [], [], [], [], []], "Ev Idx": 8098 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336756, "tid": 1336756, + "ts": 1655274258025.620, "dur": 12.322, + "args": { + "External id": 4050188,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[8388608, 2048, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [], [], [], [], []], "Ev Idx": 8099 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274258030.559, "dur": 6.453, + "args": { + "External id": 4050189,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "[8388608, 2048, 64, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8100 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274258040.436, "dur": 5.439, + "args": { + "External id": 4050190,"Record function id": 0, "Concrete Inputs": ["[16, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8101 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274258047.150, "dur": 1.641, + "args": { + "External id": 4050191,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8102 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274258050.973, "dur": 3.009, + "args": { + "External id": 4050192,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8103 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274258120.157, "dur": 48.450, + "args": { + "External id": 4050193,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 8104 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_2", "pid": 1336756, "tid": 1336756, + "ts": 1655274258198.243, "dur": 26.762, + "args": { + "External id": 4050194,"kernel_hash": "ckbsutlugbs4qoncxuwq6kkwome3xojo3ke4p7z74lcl5h4q62to", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "2048", "1", "9.9999999999999995e-07", "True", "2048", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/kb/ckbsutlugbs4qoncxuwq6kkwome3xojo3ke4p7z74lcl5h4q62to.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [1], [2048, 1], [2048, 1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [65536, 2048], [2048], [65536, 2048], [65536, 2048], [65536], [], [], [], [], [], [], [], [], []], "Ev Idx": 8105 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274258232.557, "dur": 39.853, + "args": { + "External id": 4050195,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [5632, 1]], "Input Dims": [[65536, 2048], [2048, 5632], [65536, 5632]], "Ev Idx": 8106 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274258281.142, "dur": 35.436, + "args": { + "External id": 4050196,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [5632, 1]], "Input Dims": [[65536, 2048], [2048, 5632], [65536, 5632]], "Ev Idx": 8107 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 1336756, "tid": 1336756, + "ts": 1655274258337.760, "dur": 22.905, + "args": { + "External id": 4050197,"kernel_hash": "cgh2wg2b6li2ipjwrhdr326ycb37fu4v576nwebfoyhwx5kppapn", "grid": "grid(369098752,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "369098752"], "kernel_file": "/tmp/torchinductor_cvm/gh/cgh2wg2b6li2ipjwrhdr326ycb37fu4v576nwebfoyhwx5kppapn.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[5632, 1], [5632, 1], [23068672, 5632, 1], []], "Input Dims": [[65536, 5632], [65536, 5632], [16, 4096, 5632], []], "Ev Idx": 8108 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274258365.909, "dur": 33.779, + "args": { + "External id": 4050198,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [1, 5632], [2048, 1]], "Input Dims": [[65536, 5632], [5632, 2048], [65536, 2048]], "Ev Idx": 8109 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 1336756, "tid": 1336756, + "ts": 1655274258433.720, "dur": 20.410, + "args": { + "External id": 4050199,"kernel_hash": "cta7vcczabyyuqarwmn4dcnazkxudhfwrvnick7ql5cmsd5lz4rz", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/ta/cta7vcczabyyuqarwmn4dcnazkxudhfwrvnick7ql5cmsd5lz4rz.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[8388608, 2048, 1], [2048, 1], []], "Input Dims": [[16, 4096, 2048], [65536, 2048], []], "Ev Idx": 8110 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.26)", "pid": 1336756, "tid": 1336756, + "ts": 1655274258596.583, "dur": 72.125, + "args": { + "External id": 4050200,"Record function id": 0, "Ev Idx": 8111 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 1336756, "tid": 1336756, + "ts": 1655274258740.792, "dur": 45.466, + "args": { + "External id": 4050201,"Record function id": 0, "Ev Idx": 8112 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.27)", "pid": 1336756, "tid": 1336756, + "ts": 1655274258795.493, "dur": 18176.148, + "args": { + "External id": 4050202,"Record function id": 0, "Ev Idx": 8113 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.27)", "pid": 1336756, "tid": 1336756, + "ts": 1655274258803.228, "dur": 864.598, + "args": { + "External id": 4050203,"Record function id": 0, "Ev Idx": 8114 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274258880.020, "dur": 8.376, + "args": { + "External id": 4050204,"Record function id": 0, "Concrete Inputs": ["[6423040]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8115 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336756, "tid": 1336756, + "ts": 1655274258901.077, "dur": 32.795, + "args": { + "External id": 4050205,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 8116 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274258906.055, "dur": 2.534, + "args": { + "External id": 4050206,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 8117 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274258912.666, "dur": 0.746, + "args": { + "External id": 4050207,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "256"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 8118 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274258914.694, "dur": 0.706, + "args": { + "External id": 4050208,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "524544"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 8119 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274258916.570, "dur": 0.625, + "args": { + "External id": 4050209,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1048832"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 8120 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274258920.190, "dur": 0.557, + "args": { + "External id": 4050210,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "1573120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 8121 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274258921.849, "dur": 0.640, + "args": { + "External id": 4050211,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "2097408"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 8122 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274258923.706, "dur": 1.834, + "args": { + "External id": 4050212,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "2097664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 8123 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274258926.469, "dur": 0.604, + "args": { + "External id": 4050213,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "3539456"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 8124 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274258928.116, "dur": 0.442, + "args": { + "External id": 4050214,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "4981248"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 8125 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336756, "tid": 1336756, + "ts": 1655274258944.678, "dur": 72.912, + "args": { + "External id": 4050215,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 8126 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::all_gather_copy_in", "pid": 1336756, "tid": 1336756, + "ts": 1655274259053.455, "dur": 113.907, + "args": { + "External id": 4050216,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "6423040", "8", "3", "15", ""], "Input type": ["TensorList", "ScalarList", "Scalar", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [], [], [], [], [], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [], [], [], [], [], []], "Ev Idx": 8127 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274259064.984, "dur": 6.280, + "args": { + "External id": 4050217,"Record function id": 0, "Concrete Inputs": ["[51384320]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8128 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::narrow", "pid": 1336756, "tid": 1336756, + "ts": 1655274259076.192, "dur": 10.635, + "args": { + "External id": 4050218,"Record function id": 0, "Concrete Inputs": ["", "0", "19269120", "6423040"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 8129 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1336756, + "ts": 1655274259080.434, "dur": 5.993, + "args": { + "External id": 4050219,"Record function id": 0, "Concrete Inputs": ["", "0", "19269120", "25692160", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[51384320], [], [], [], []], "Ev Idx": 8130 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274259083.942, "dur": 0.983, + "args": { + "External id": 4050220,"Record function id": 0, "Concrete Inputs": ["", "[6423040]", "[1]", "19269120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[51384320], [], [], []], "Ev Idx": 8131 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes", "pid": 1336756, "tid": 1336756, + "ts": 1655274259094.685, "dur": 27.287, + "args": { + "External id": 4050221,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[6423040], [], []], "Ev Idx": 8132 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274259096.788, "dur": 2.193, + "args": { + "External id": 4050222,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "19269120"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 8133 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274259100.523, "dur": 0.548, + "args": { + "External id": 4050223,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "19269376"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 8134 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274259102.110, "dur": 0.551, + "args": { + "External id": 4050224,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "19793664"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 8135 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274259105.347, "dur": 0.578, + "args": { + "External id": 4050225,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "20317952"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 8136 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274259107.091, "dur": 0.987, + "args": { + "External id": 4050226,"Record function id": 0, "Concrete Inputs": ["", "[524288]", "[1]", "20842240"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 8137 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274259109.084, "dur": 0.500, + "args": { + "External id": 4050227,"Record function id": 0, "Concrete Inputs": ["", "[256]", "[1]", "21366528"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 8138 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274259112.379, "dur": 0.600, + "args": { + "External id": 4050228,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "21366784"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 8139 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274259113.986, "dur": 0.763, + "args": { + "External id": 4050229,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "22808576"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 8140 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274259115.983, "dur": 1.962, + "args": { + "External id": 4050230,"Record function id": 0, "Concrete Inputs": ["", "[1441792]", "[1]", "24250368"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[6423040], [], [], []], "Ev Idx": 8141 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_copy_", "pid": 1336756, "tid": 1336756, + "ts": 1655274259133.451, "dur": 26.266, + "args": { + "External id": 4050231,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["TensorList", "TensorList", "Scalar"], "Input Strides": [[[1], [1], [1], [1], [1], [1], [1], [1], [1]], [[1], [1], [1], [1], [1], [1], [1], [1], [1]], []], "Input Dims": [[[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], [[256], [524288], [524288], [524288], [524288], [256], [1441792], [1441792], [1441792]], []], "Ev Idx": 8142 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::_allgather_base_", "pid": 1336756, "tid": 1336756, + "ts": 1655274259222.481, "dur": 355.186, + "args": { + "External id": 4050232,"Record function id": 0, "Concrete Inputs": ["", "", "", "False", "-1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "Scalar", "Scalar"], "Input Strides": [[1], [1], [], [], []], "Input Dims": [[51384320], [6423040], [], [], []], "Ev Idx": 8143 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336756, "tid": 1336756, + "ts": 1655274259252.125, "dur": 320.496, + "args": { + "External id": 4050233,"Record function id": 0, "Collective name": "_allgather_base", "Process Group Description": "default_pg", "dtype": "BFloat16", "Rank": 3, "Input Strides": [[1], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "3", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 51384320, "Process Group Name": "0", "Input type": ["c10::BFloat16", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[6423040], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 8144, "In msg nelems": 6423040 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:_all_gather_base", "pid": 1336756, "tid": 1336756, + "ts": 1655274259261.998, "dur": 305.055, + "args": { + "External id": 4050234,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[1]], "Input Dims": [[6423040]], "Ev Idx": 8145 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336756, "tid": 1336756, + "ts": 1655274259599.464, "dur": 2.729, + "args": { + "External id": 4050235,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "3", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 8146, "In msg nelems": 0, "Rank": 3, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather_copy_out (model.layers.27)", "pid": 1336756, "tid": 1336756, + "ts": 1655274259687.203, "dur": 17093.707, + "args": { + "External id": 4050236,"Record function id": 0, "Ev Idx": 8147 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274259780.662, "dur": 6.076, + "args": { + "External id": 4050237,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[51384320], []], "Ev Idx": 8148 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274259790.058, "dur": 1.190, + "args": { + "External id": 4050238,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 8149 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274259793.061, "dur": 0.996, + "args": { + "External id": 4050239,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 8150 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274259805.067, "dur": 1.045, + "args": { + "External id": 4050240,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 8151 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274259807.714, "dur": 0.944, + "args": { + "External id": 4050241,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 8152 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274259809.898, "dur": 1.021, + "args": { + "External id": 4050242,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[4194304], []], "Ev Idx": 8153 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274259814.215, "dur": 0.675, + "args": { + "External id": 4050243,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[2048], []], "Ev Idx": 8154 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274259816.349, "dur": 1.911, + "args": { + "External id": 4050244,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 8155 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274259819.562, "dur": 0.606, + "args": { + "External id": 4050245,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 8156 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274259821.551, "dur": 0.586, + "args": { + "External id": 4050246,"Record function id": 0, "Concrete Inputs": ["", "[8, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[11534336], []], "Ev Idx": 8157 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "fsdp::split_with_sizes_copy", "pid": 1336756, "tid": 1336756, + "ts": 1655274259841.685, "dur": 16898.748, + "args": { + "External id": 4050247,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 8158 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::split_with_sizes_copy", "pid": 1336756, "tid": 1336756, + "ts": 1655274259856.032, "dur": 16877.503, + "args": { + "External id": 4050248,"Record function id": 0, "Concrete Inputs": ["", "[256, 524288, 524288, 524288, 524288, 256, 1441792, 1441792, 1441792]", "1", ""], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "TensorList"], "Input Strides": [[6423040, 1], [], [], [[256, 1], [524288, 1], [524288, 1], [524288, 1], [524288, 1], [256, 1], [1441792, 1], [1441792, 1], [1441792, 1]]], "Input Dims": [[8, 6423040], [], [], [[8, 256], [8, 524288], [8, 524288], [8, 524288], [8, 524288], [8, 256], [8, 1441792], [8, 1441792], [8, 1441792]]], "Ev Idx": 8159 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274259873.039, "dur": 11.952, + "args": { + "External id": 4050249,"Record function id": 0, "Concrete Inputs": ["[2133]", "4", "", "", "True", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8160 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655274259887.662, "dur": 16815.377, + "args": { + "External id": 4050250,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", "False", ""], "Input type": ["long int", "", "", "", "", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], [], []], "Ev Idx": 8161 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336756, "tid": 1336756, + "ts": 1655274259890.075, "dur": 16812.448, + "args": { + "External id": 4050251,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "True", ""], "Input type": ["long int", "", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[2133], [], [], [], [], [], []], "Ev Idx": 8162 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274259895.596, "dur": 5.806, + "args": { + "External id": 4050252,"Record function id": 0, "Concrete Inputs": ["[2133]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8163 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1336756, + "ts": 1655274259903.004, "dur": 16796.537, + "args": { + "External id": 4050253,"Record function id": 0, "Concrete Inputs": ["", "", "True"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[2133], [2133], []], "Ev Idx": 8164 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunction", "pid": 1336756, "tid": 1336756, + "ts": 1655274276909.296, "dur": 37.355, + "args": { + "External id": 4050254,"Sequence number": 40618407, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048]], "Ev Idx": 8165 + } + }, + { + "ph": "s", "id": 173, "pid": 1336756, "tid": 1336756, "ts": 1655274276909.296, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 1336756, "tid": 1336756, + "ts": 1655274276934.148, "dur": 7.632, + "args": { + "External id": 4050255,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[8388608, 2048, 1], [8388608, 2048, 1]], "Input Dims": [[16, 4096, 2048], [16, 4096, 2048]], "Ev Idx": 8166 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274276937.448, "dur": 4.090, + "args": { + "External id": 4050256,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8167 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 1336756, "tid": 1336756, + "ts": 1655274277036.667, "dur": 69.389, + "args": { + "External id": 4050257,"Record function id": 0, "Ev Idx": 8168 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 1336756, "tid": 1336756, + "ts": 1655274277108.132, "dur": 1033.266, + "args": { + "External id": 4050258,"Record function id": 0, "Ev Idx": 8169 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 1336756, "tid": 1336756, + "ts": 1655274277149.363, "dur": 979.562, + "args": { + "External id": 4050259,"Sequence number": 40618408, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "", "", "", "", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[8388608, 2048, 1], [1], [2048, 1], [2048, 1], [2048, 1], [32, 1], [32, 1], [2048, 1], [1], [2048, 1], [2048, 1], [5632, 1]], "Input Dims": [[16, 4096, 2048], [2048], [2048, 2048], [2048, 2048], [2048, 2048], [8192, 32], [8192, 32], [2048, 2048], [2048], [5632, 2048], [5632, 2048], [2048, 5632]], "Ev Idx": 8170 + } + }, + { + "ph": "s", "id": 172, "pid": 1336756, "tid": 1336756, "ts": 1655274277149.363, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 1336756, "tid": 1336756, + "ts": 1655274277214.450, "dur": 39.410, + "args": { + "External id": 4050260,"kernel_hash": "cd26ogptnjelaibpl2zumx5nxdttspqepvjkh7lpmsxbzrrexbxm", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "2048", "1", "9.9999999999999995e-07", "True", "2048", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/d2/cd26ogptnjelaibpl2zumx5nxdttspqepvjkh7lpmsxbzrrexbxm.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [65536, 2048], [2048], [65536], [], [], [], [], [], [], [], [], []], "Ev Idx": 8171 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274277265.734, "dur": 105.086, + "args": { + "External id": 4050261,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 8172 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274277379.976, "dur": 52.734, + "args": { + "External id": 4050262,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 8173 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274277444.713, "dur": 34.613, + "args": { + "External id": 4050263,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 8174 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336756, "tid": 1336756, + "ts": 1655274277505.093, "dur": 24.894, + "args": { + "External id": 4050264,"kernel_hash": "cahe5odluo4swiyj4n2lohwh57qg5lym5qsijyjsjca7pvto5oka", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/ah/cahe5odluo4swiyj4n2lohwh57qg5lym5qsijyjsjca7pvto5oka.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 8175 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "rotary_embedding_kernel_1", "pid": 1336756, "tid": 1336756, + "ts": 1655274277547.099, "dur": 14.985, + "args": { + "External id": 4050265,"kernel_hash": "cahe5odluo4swiyj4n2lohwh57qg5lym5qsijyjsjca7pvto5oka", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "0", "16", "4096", "32", "64", "32", "8192", "32", "64", "False", "False", "False", "False"], "kernel_file": "/tmp/torchinductor_cvm/ah/cahe5odluo4swiyj4n2lohwh57qg5lym5qsijyjsjca7pvto5oka.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 8176 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 1336756, "tid": 1336756, + "ts": 1655274277580.039, "dur": 124.434, + "args": { + "External id": 4050266,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.125", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [], [], [], [], [], [], [], []], "Ev Idx": 8177 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336756, "tid": 1336756, + "ts": 1655274277629.375, "dur": 11.186, + "args": { + "External id": 4050267,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[8388608, 2048, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [], [], [], [], []], "Ev Idx": 8178 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274277634.071, "dur": 5.675, + "args": { + "External id": 4050268,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "[8388608, 2048, 64, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8179 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274277643.078, "dur": 4.586, + "args": { + "External id": 4050269,"Record function id": 0, "Concrete Inputs": ["[16, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8180 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274277649.092, "dur": 1.592, + "args": { + "External id": 4050270,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8181 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274277653.161, "dur": 3.185, + "args": { + "External id": 4050271,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8182 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274277715.874, "dur": 44.351, + "args": { + "External id": 4050272,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [2048, 1]], "Input Dims": [[65536, 2048], [2048, 2048], [65536, 2048]], "Ev Idx": 8183 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_2", "pid": 1336756, "tid": 1336756, + "ts": 1655274277789.368, "dur": 25.153, + "args": { + "External id": 4050273,"kernel_hash": "ckbsutlugbs4qoncxuwq6kkwome3xojo3ke4p7z74lcl5h4q62to", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "", "", "2048", "1", "9.9999999999999995e-07", "True", "2048", "True", "True", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/kb/ckbsutlugbs4qoncxuwq6kkwome3xojo3ke4p7z74lcl5h4q62to.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [1], [2048, 1], [2048, 1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[65536, 2048], [65536, 2048], [2048], [65536, 2048], [65536, 2048], [65536], [], [], [], [], [], [], [], [], []], "Ev Idx": 8184 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274277822.186, "dur": 41.094, + "args": { + "External id": 4050274,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [5632, 1]], "Input Dims": [[65536, 2048], [2048, 5632], [65536, 5632]], "Ev Idx": 8185 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274277870.872, "dur": 34.790, + "args": { + "External id": 4050275,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048], [5632, 1]], "Input Dims": [[65536, 2048], [2048, 5632], [65536, 5632]], "Ev Idx": 8186 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused__to_copy_mul_silu_0", "pid": 1336756, "tid": 1336756, + "ts": 1655274277926.707, "dur": 24.400, + "args": { + "External id": 4050276,"kernel_hash": "cgh2wg2b6li2ipjwrhdr326ycb37fu4v576nwebfoyhwx5kppapn", "grid": "grid(369098752,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "369098752"], "kernel_file": "/tmp/torchinductor_cvm/gh/cgh2wg2b6li2ipjwrhdr326ycb37fu4v576nwebfoyhwx5kppapn.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[5632, 1], [5632, 1], [23068672, 5632, 1], []], "Input Dims": [[65536, 5632], [65536, 5632], [16, 4096, 5632], []], "Ev Idx": 8187 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274277957.168, "dur": 64.783, + "args": { + "External id": 4050277,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [1, 5632], [2048, 1]], "Input Dims": [[65536, 5632], [5632, 2048], [65536, 2048]], "Ev Idx": 8188 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_add_1", "pid": 1336756, "tid": 1336756, + "ts": 1655274278045.675, "dur": 18.355, + "args": { + "External id": 4050278,"kernel_hash": "cta7vcczabyyuqarwmn4dcnazkxudhfwrvnick7ql5cmsd5lz4rz", "grid": "grid(134217728,)", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "134217728"], "kernel_file": "/tmp/torchinductor_cvm/ta/cta7vcczabyyuqarwmn4dcnazkxudhfwrvnick7ql5cmsd5lz4rz.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[8388608, 2048, 1], [2048, 1], []], "Input Dims": [[16, 4096, 2048], [65536, 2048], []], "Ev Idx": 8189 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward (model.layers.27)", "pid": 1336756, "tid": 1336756, + "ts": 1655274278202.427, "dur": 32.451, + "args": { + "External id": 4050279,"Record function id": 0, "Ev Idx": 8190 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunction", "pid": 1336756, "tid": 1336756, + "ts": 1655274278360.904, "dur": 261.357, + "args": { + "External id": 4050280,"Sequence number": 40618409, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "9.9999999999999995e-07", "False", "False", "True"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 1], [1], [], [], [], [], [], []], "Input Dims": [[16, 4096, 2048], [2048], [], [], [], [], [], []], "Ev Idx": 8191 + } + }, + { + "ph": "s", "id": 171, "pid": 1336756, "tid": 1336756, "ts": 1655274278360.904, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1336756, + "ts": 1655274278388.425, "dur": 7.859, + "args": { + "External id": 4050281,"Record function id": 0, "Concrete Inputs": ["", "[-1, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8192 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274278390.545, "dur": 5.453, + "args": { + "External id": 4050282,"Record function id": 0, "Concrete Inputs": ["", "[-1, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8193 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336756, "tid": 1336756, + "ts": 1655274278405.132, "dur": 26.852, + "args": { + "External id": 4050283,"Record function id": 0, "Concrete Inputs": ["", "15", "", "", "False", ""], "Input type": ["c10::BFloat16", "Scalar", "", "", "Scalar", ""], "Input Strides": [[2048, 1], [], [], [], [], []], "Input Dims": [[65536, 2048], [], [], [], [], []], "Ev Idx": 8194 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274278408.108, "dur": 22.945, + "args": { + "External id": 4050284,"Record function id": 0, "Concrete Inputs": ["[65536, 2048]", "[2048, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8195 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274278443.335, "dur": 5.573, + "args": { + "External id": 4050285,"Record function id": 0, "Concrete Inputs": ["[65536]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8196 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1336756, + "ts": 1655274278601.836, "dur": 7.036, + "args": { + "External id": 4050286,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 8197 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274278605.198, "dur": 3.441, + "args": { + "External id": 4050287,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 8198 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336756, "tid": 1336756, + "ts": 1655274278649.189, "dur": 123.963, + "args": { + "External id": 4050288,"Sequence number": 40618410, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[8388608, 2048, 1], [2048, 1], []], "Input Dims": [[16, 4096, 2048], [2048, 2048], []], "Ev Idx": 8199 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1336756, + "ts": 1655274278652.406, "dur": 15.798, + "args": { + "External id": 4050289,"Sequence number": 40618410, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 8200 + } + }, + { + "ph": "s", "id": 170, "pid": 1336756, "tid": 1336756, "ts": 1655274278652.406, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1336756, + "ts": 1655274278657.604, "dur": 8.888, + "args": { + "External id": 4050290,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[2048, 2048], [], []], "Ev Idx": 8201 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274278663.798, "dur": 2.347, + "args": { + "External id": 4050291,"Record function id": 0, "Concrete Inputs": ["", "[2048, 2048]", "[1, 2048]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[2048, 2048], [], [], []], "Ev Idx": 8202 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336756, "tid": 1336756, + "ts": 1655274278670.816, "dur": 102.054, + "args": { + "External id": 4050292,"Sequence number": 40618411, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[8388608, 2048, 1], [1, 2048]], "Input Dims": [[16, 4096, 2048], [2048, 2048]], "Ev Idx": 8203 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1336756, + "ts": 1655274278673.655, "dur": 6.182, + "args": { + "External id": 4050293,"Sequence number": 40618411, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[65536, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8204 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274278674.902, "dur": 4.791, + "args": { + "External id": 4050294,"Sequence number": 40618411, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[65536, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8205 + } + }, + { + "ph": "s", "id": 169, "pid": 1336756, "tid": 1336756, "ts": 1655274278674.902, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274278683.205, "dur": 80.655, + "args": { + "External id": 4050295,"Sequence number": 40618412, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048]], "Input Dims": [[65536, 2048], [2048, 2048]], "Ev Idx": 8206 + } + }, + { + "ph": "s", "id": 168, "pid": 1336756, "tid": 1336756, "ts": 1655274278683.205, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 1336756, "tid": 1336756, + "ts": 1655274278767.828, "dur": 4.031, + "args": { + "External id": 4050296,"Sequence number": 40618413, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 8207 + } + }, + { + "ph": "s", "id": 167, "pid": 1336756, "tid": 1336756, "ts": 1655274278767.828, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336756, "tid": 1336756, + "ts": 1655274278782.224, "dur": 68.038, + "args": { + "External id": 4050297,"Sequence number": 40618414, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[8388608, 2048, 1], [2048, 1], []], "Input Dims": [[16, 4096, 2048], [2048, 2048], []], "Ev Idx": 8208 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1336756, + "ts": 1655274278783.323, "dur": 8.545, + "args": { + "External id": 4050298,"Sequence number": 40618414, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 8209 + } + }, + { + "ph": "s", "id": 166, "pid": 1336756, "tid": 1336756, "ts": 1655274278783.323, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1336756, + "ts": 1655274278785.207, "dur": 5.507, + "args": { + "External id": 4050299,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[2048, 2048], [], []], "Ev Idx": 8210 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274278789.730, "dur": 0.751, + "args": { + "External id": 4050300,"Record function id": 0, "Concrete Inputs": ["", "[2048, 2048]", "[1, 2048]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[2048, 2048], [], [], []], "Ev Idx": 8211 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336756, "tid": 1336756, + "ts": 1655274278792.553, "dur": 57.433, + "args": { + "External id": 4050301,"Sequence number": 40618415, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[8388608, 2048, 1], [1, 2048]], "Input Dims": [[16, 4096, 2048], [2048, 2048]], "Ev Idx": 8212 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1336756, + "ts": 1655274278793.814, "dur": 3.215, + "args": { + "External id": 4050302,"Sequence number": 40618415, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[65536, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8213 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274278794.588, "dur": 2.193, + "args": { + "External id": 4050303,"Sequence number": 40618415, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[65536, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8214 + } + }, + { + "ph": "s", "id": 165, "pid": 1336756, "tid": 1336756, "ts": 1655274278794.588, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274278797.908, "dur": 46.233, + "args": { + "External id": 4050304,"Sequence number": 40618416, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048]], "Input Dims": [[65536, 2048], [2048, 2048]], "Ev Idx": 8215 + } + }, + { + "ph": "s", "id": 164, "pid": 1336756, "tid": 1336756, "ts": 1655274278797.908, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 1336756, "tid": 1336756, + "ts": 1655274278845.877, "dur": 3.710, + "args": { + "External id": 4050305,"Sequence number": 40618417, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 8216 + } + }, + { + "ph": "s", "id": 163, "pid": 1336756, "tid": 1336756, "ts": 1655274278845.877, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336756, "tid": 1336756, + "ts": 1655274278857.429, "dur": 61.653, + "args": { + "External id": 4050306,"Sequence number": 40618418, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[8388608, 2048, 1], [2048, 1], []], "Input Dims": [[16, 4096, 2048], [2048, 2048], []], "Ev Idx": 8217 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1336756, + "ts": 1655274278858.171, "dur": 5.045, + "args": { + "External id": 4050307,"Sequence number": 40618418, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 8218 + } + }, + { + "ph": "s", "id": 162, "pid": 1336756, "tid": 1336756, "ts": 1655274278858.171, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1336756, + "ts": 1655274278859.814, "dur": 2.396, + "args": { + "External id": 4050308,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[2048, 2048], [], []], "Ev Idx": 8219 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274278861.371, "dur": 0.651, + "args": { + "External id": 4050309,"Record function id": 0, "Concrete Inputs": ["", "[2048, 2048]", "[1, 2048]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[2048, 2048], [], [], []], "Ev Idx": 8220 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336756, "tid": 1336756, + "ts": 1655274278865.729, "dur": 53.125, + "args": { + "External id": 4050310,"Sequence number": 40618419, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[8388608, 2048, 1], [1, 2048]], "Input Dims": [[16, 4096, 2048], [2048, 2048]], "Ev Idx": 8221 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1336756, + "ts": 1655274278866.713, "dur": 4.299, + "args": { + "External id": 4050311,"Sequence number": 40618419, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[65536, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8222 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274278867.553, "dur": 3.347, + "args": { + "External id": 4050312,"Sequence number": 40618419, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[65536, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8223 + } + }, + { + "ph": "s", "id": 161, "pid": 1336756, "tid": 1336756, "ts": 1655274278867.553, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274278871.465, "dur": 40.654, + "args": { + "External id": 4050313,"Sequence number": 40618420, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048]], "Input Dims": [[65536, 2048], [2048, 2048]], "Ev Idx": 8224 + } + }, + { + "ph": "s", "id": 160, "pid": 1336756, "tid": 1336756, "ts": 1655274278871.465, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 1336756, "tid": 1336756, + "ts": 1655274278913.691, "dur": 4.824, + "args": { + "External id": 4050314,"Sequence number": 40618421, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 8225 + } + }, + { + "ph": "s", "id": 159, "pid": 1336756, "tid": 1336756, "ts": 1655274278913.691, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1336756, + "ts": 1655274278935.580, "dur": 4.180, + "args": { + "External id": 4050315,"Sequence number": 40618422, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 32, 64]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8226 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274278936.681, "dur": 2.929, + "args": { + "External id": 4050316,"Sequence number": 40618422, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 32, 64]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8227 + } + }, + { + "ph": "s", "id": 158, "pid": 1336756, "tid": 1336756, "ts": 1655274278936.681, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1336756, + "ts": 1655274278945.872, "dur": 4.626, + "args": { + "External id": 4050317,"Sequence number": 40618423, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 32, 64]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8228 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274278947.180, "dur": 3.154, + "args": { + "External id": 4050318,"Sequence number": 40618423, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 32, 64]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8229 + } + }, + { + "ph": "s", "id": 157, "pid": 1336756, "tid": 1336756, "ts": 1655274278947.180, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1336756, + "ts": 1655274278956.274, "dur": 3.122, + "args": { + "External id": 4050319,"Sequence number": 40618424, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 32, 64]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8230 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274278957.520, "dur": 1.728, + "args": { + "External id": 4050320,"Sequence number": 40618424, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 32, 64]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8231 + } + }, + { + "ph": "s", "id": 156, "pid": 1336756, "tid": 1336756, "ts": 1655274278957.520, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunction", "pid": 1336756, "tid": 1336756, + "ts": 1655274279027.210, "dur": 174.005, + "args": { + "External id": 4050321,"Sequence number": 40618425, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "False", "False", "0", "", "8192"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [], [], [], [], []], "Ev Idx": 8232 + } + }, + { + "ph": "s", "id": 155, "pid": 1336756, "tid": 1336756, "ts": 1655274279027.210, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336756, "tid": 1336756, + "ts": 1655274279049.231, "dur": 10.921, + "args": { + "External id": 4050322,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[8388608, 2048, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [], [], [], [], []], "Ev Idx": 8233 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274279052.669, "dur": 6.737, + "args": { + "External id": 4050323,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "[8388608, 2048, 64, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8234 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunction", "pid": 1336756, "tid": 1336756, + "ts": 1655274279214.490, "dur": 107.363, + "args": { + "External id": 4050324,"Sequence number": 40618426, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "False", "False", "0", "", "8192"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [], [], [], [], []], "Ev Idx": 8235 + } + }, + { + "ph": "s", "id": 154, "pid": 1336756, "tid": 1336756, "ts": 1655274279214.490, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336756, "tid": 1336756, + "ts": 1655274279228.028, "dur": 7.280, + "args": { + "External id": 4050325,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[8388608, 2048, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [], [], [], [], []], "Ev Idx": 8236 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274279230.439, "dur": 4.450, + "args": { + "External id": 4050326,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "[8388608, 2048, 64, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8237 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "FlashAttnFunc", "pid": 1336756, "tid": 1336756, + "ts": 1655274279351.276, "dur": 201.425, + "args": { + "External id": 4050327,"Sequence number": 40618427, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "", "True", "", "0.", "", "False", "False", "True"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "", "Scalar", "", "Scalar", "", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], []], "Ev Idx": 8238 + } + }, + { + "ph": "s", "id": 153, "pid": 1336756, "tid": 1336756, "ts": 1655274279351.276, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 1336756, "tid": 1336756, + "ts": 1655274279378.041, "dur": 145.490, + "args": { + "External id": 4050328,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.125", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [], [], [], [], [], [], [], []], "Ev Idx": 8239 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336756, "tid": 1336756, + "ts": 1655274279444.402, "dur": 8.807, + "args": { + "External id": 4050329,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[8388608, 2048, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [], [], [], [], []], "Ev Idx": 8240 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274279447.027, "dur": 5.529, + "args": { + "External id": 4050330,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "[8388608, 2048, 64, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8241 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274279456.016, "dur": 4.163, + "args": { + "External id": 4050331,"Record function id": 0, "Concrete Inputs": ["[16, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8242 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274279463.095, "dur": 1.202, + "args": { + "External id": 4050332,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8243 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274279466.586, "dur": 3.134, + "args": { + "External id": 4050333,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8244 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::alias", "pid": 1336756, "tid": 1336756, + "ts": 1655274279537.704, "dur": 4.578, + "args": { + "External id": 4050334,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 64, 1]], "Input Dims": [[16, 4096, 32, 64]], "Ev Idx": 8245 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1336756, + "ts": 1655274279557.627, "dur": 5.830, + "args": { + "External id": 4050335,"Sequence number": 40618428, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[16, 4096, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 64, 1], []], "Input Dims": [[16, 4096, 32, 64], []], "Ev Idx": 8246 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274279559.116, "dur": 4.163, + "args": { + "External id": 4050336,"Sequence number": 40618428, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[16, 4096, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 64, 1], []], "Input Dims": [[16, 4096, 32, 64], []], "Ev Idx": 8247 + } + }, + { + "ph": "s", "id": 152, "pid": 1336756, "tid": 1336756, "ts": 1655274279559.116, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336756, "tid": 1336756, + "ts": 1655274279575.216, "dur": 120.294, + "args": { + "External id": 4050337,"Sequence number": 40618429, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[8388608, 2048, 1], [2048, 1], []], "Input Dims": [[16, 4096, 2048], [2048, 2048], []], "Ev Idx": 8248 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1336756, + "ts": 1655274279578.238, "dur": 7.844, + "args": { + "External id": 4050338,"Sequence number": 40618429, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 8249 + } + }, + { + "ph": "s", "id": 151, "pid": 1336756, "tid": 1336756, "ts": 1655274279578.238, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1336756, + "ts": 1655274279580.716, "dur": 4.393, + "args": { + "External id": 4050339,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[2048, 2048], [], []], "Ev Idx": 8250 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274279583.009, "dur": 1.838, + "args": { + "External id": 4050340,"Record function id": 0, "Concrete Inputs": ["", "[2048, 2048]", "[1, 2048]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[2048, 2048], [], [], []], "Ev Idx": 8251 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336756, "tid": 1336756, + "ts": 1655274279587.371, "dur": 107.803, + "args": { + "External id": 4050341,"Sequence number": 40618430, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[8388608, 2048, 1], [1, 2048]], "Input Dims": [[16, 4096, 2048], [2048, 2048]], "Ev Idx": 8252 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1336756, + "ts": 1655274279589.284, "dur": 6.911, + "args": { + "External id": 4050342,"Sequence number": 40618430, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[65536, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8253 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274279592.135, "dur": 3.923, + "args": { + "External id": 4050343,"Sequence number": 40618430, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[65536, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8254 + } + }, + { + "ph": "s", "id": 150, "pid": 1336756, "tid": 1336756, "ts": 1655274279592.135, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274279597.400, "dur": 91.348, + "args": { + "External id": 4050344,"Sequence number": 40618431, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048]], "Input Dims": [[65536, 2048], [2048, 2048]], "Ev Idx": 8255 + } + }, + { + "ph": "s", "id": 149, "pid": 1336756, "tid": 1336756, "ts": 1655274279597.400, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 1336756, "tid": 1336756, + "ts": 1655274279691.050, "dur": 3.314, + "args": { + "External id": 4050345,"Sequence number": 40618432, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 8256 + } + }, + { + "ph": "s", "id": 148, "pid": 1336756, "tid": 1336756, "ts": 1655274279691.050, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunction", "pid": 1336756, "tid": 1336756, + "ts": 1655274279728.368, "dur": 211.629, + "args": { + "External id": 4050346,"Sequence number": 40618433, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "9.9999999999999995e-07", "True", "False", "True"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 1], [1], [], [8388608, 2048, 1], [], [], [], []], "Input Dims": [[16, 4096, 2048], [2048], [], [16, 4096, 2048], [], [], [], []], "Ev Idx": 8257 + } + }, + { + "ph": "s", "id": 147, "pid": 1336756, "tid": 1336756, "ts": 1655274279728.368, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1336756, + "ts": 1655274279747.735, "dur": 5.873, + "args": { + "External id": 4050347,"Record function id": 0, "Concrete Inputs": ["", "[-1, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8258 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274279751.725, "dur": 1.708, + "args": { + "External id": 4050348,"Record function id": 0, "Concrete Inputs": ["", "[-1, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8259 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape_as", "pid": 1336756, "tid": 1336756, + "ts": 1655274279758.424, "dur": 3.567, + "args": { + "External id": 4050349,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[8388608, 2048, 1], [2048, 1]], "Input Dims": [[16, 4096, 2048], [65536, 2048]], "Ev Idx": 8260 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1336756, + "ts": 1655274279759.543, "dur": 2.343, + "args": { + "External id": 4050350,"Record function id": 0, "Concrete Inputs": ["", "[65536, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8261 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274279760.457, "dur": 1.331, + "args": { + "External id": 4050351,"Record function id": 0, "Concrete Inputs": ["", "[65536, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8262 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336756, "tid": 1336756, + "ts": 1655274279769.365, "dur": 8.340, + "args": { + "External id": 4050352,"Record function id": 0, "Concrete Inputs": ["", "15", "", "", "False", ""], "Input type": ["c10::BFloat16", "Scalar", "", "", "Scalar", ""], "Input Strides": [[2048, 1], [], [], [], [], []], "Input Dims": [[65536, 2048], [], [], [], [], []], "Ev Idx": 8263 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274279773.229, "dur": 4.102, + "args": { + "External id": 4050353,"Record function id": 0, "Concrete Inputs": ["[65536, 2048]", "[2048, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8264 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274279783.898, "dur": 2.952, + "args": { + "External id": 4050354,"Record function id": 0, "Concrete Inputs": ["[65536, 2048]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8265 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274279792.527, "dur": 2.335, + "args": { + "External id": 4050355,"Record function id": 0, "Concrete Inputs": ["[65536]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8266 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1336756, + "ts": 1655274279918.020, "dur": 3.155, + "args": { + "External id": 4050356,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 8267 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274279919.000, "dur": 1.911, + "args": { + "External id": 4050357,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 8268 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1336756, + "ts": 1655274279923.864, "dur": 2.008, + "args": { + "External id": 4050358,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 8269 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274279924.729, "dur": 1.031, + "args": { + "External id": 4050359,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 8270 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336756, "tid": 1336756, + "ts": 1655274279959.411, "dur": 132.510, + "args": { + "External id": 4050360,"Sequence number": 40618434, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[8388608, 2048, 1], [2048, 1], []], "Input Dims": [[16, 4096, 2048], [5632, 2048], []], "Ev Idx": 8271 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1336756, + "ts": 1655274279960.420, "dur": 6.482, + "args": { + "External id": 4050361,"Sequence number": 40618434, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 8272 + } + }, + { + "ph": "s", "id": 146, "pid": 1336756, "tid": 1336756, "ts": 1655274279960.420, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1336756, + "ts": 1655274279962.403, "dur": 3.451, + "args": { + "External id": 4050362,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[5632, 2048], [], []], "Ev Idx": 8273 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274279964.395, "dur": 1.207, + "args": { + "External id": 4050363,"Record function id": 0, "Concrete Inputs": ["", "[2048, 5632]", "[1, 2048]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[5632, 2048], [], [], []], "Ev Idx": 8274 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336756, "tid": 1336756, + "ts": 1655274279967.920, "dur": 123.605, + "args": { + "External id": 4050364,"Sequence number": 40618435, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[8388608, 2048, 1], [1, 2048]], "Input Dims": [[16, 4096, 2048], [2048, 5632]], "Ev Idx": 8275 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1336756, + "ts": 1655274279970.748, "dur": 3.507, + "args": { + "External id": 4050365,"Sequence number": 40618435, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[65536, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8276 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274279971.571, "dur": 2.555, + "args": { + "External id": 4050366,"Sequence number": 40618435, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[65536, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8277 + } + }, + { + "ph": "s", "id": 145, "pid": 1336756, "tid": 1336756, "ts": 1655274279971.571, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274279974.902, "dur": 107.169, + "args": { + "External id": 4050367,"Sequence number": 40618436, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048]], "Input Dims": [[65536, 2048], [2048, 5632]], "Ev Idx": 8278 + } + }, + { + "ph": "s", "id": 144, "pid": 1336756, "tid": 1336756, "ts": 1655274279974.902, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 1336756, "tid": 1336756, + "ts": 1655274280085.647, "dur": 5.080, + "args": { + "External id": 4050368,"Sequence number": 40618437, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 5632]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[5632, 1], []], "Input Dims": [[65536, 5632], []], "Ev Idx": 8279 + } + }, + { + "ph": "s", "id": 143, "pid": 1336756, "tid": 1336756, "ts": 1655274280085.647, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336756, "tid": 1336756, + "ts": 1655274280102.388, "dur": 68.570, + "args": { + "External id": 4050369,"Sequence number": 40618438, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[8388608, 2048, 1], [2048, 1], []], "Input Dims": [[16, 4096, 2048], [5632, 2048], []], "Ev Idx": 8280 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1336756, + "ts": 1655274280104.999, "dur": 5.787, + "args": { + "External id": 4050370,"Sequence number": 40618438, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 8281 + } + }, + { + "ph": "s", "id": 142, "pid": 1336756, "tid": 1336756, "ts": 1655274280104.999, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1336756, + "ts": 1655274280106.905, "dur": 2.818, + "args": { + "External id": 4050371,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[5632, 2048], [], []], "Ev Idx": 8282 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274280108.530, "dur": 1.005, + "args": { + "External id": 4050372,"Record function id": 0, "Concrete Inputs": ["", "[2048, 5632]", "[1, 2048]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[5632, 2048], [], [], []], "Ev Idx": 8283 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336756, "tid": 1336756, + "ts": 1655274280111.543, "dur": 59.094, + "args": { + "External id": 4050373,"Sequence number": 40618439, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[8388608, 2048, 1], [1, 2048]], "Input Dims": [[16, 4096, 2048], [2048, 5632]], "Ev Idx": 8284 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1336756, + "ts": 1655274280112.928, "dur": 5.338, + "args": { + "External id": 4050374,"Sequence number": 40618439, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[65536, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8285 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274280115.003, "dur": 3.118, + "args": { + "External id": 4050375,"Sequence number": 40618439, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[65536, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8286 + } + }, + { + "ph": "s", "id": 141, "pid": 1336756, "tid": 1336756, "ts": 1655274280115.003, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274280118.907, "dur": 47.628, + "args": { + "External id": 4050376,"Sequence number": 40618440, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048]], "Input Dims": [[65536, 2048], [2048, 5632]], "Ev Idx": 8287 + } + }, + { + "ph": "s", "id": 140, "pid": 1336756, "tid": 1336756, "ts": 1655274280118.907, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 1336756, "tid": 1336756, + "ts": 1655274280168.181, "dur": 2.131, + "args": { + "External id": 4050377,"Sequence number": 40618441, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 5632]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[5632, 1], []], "Input Dims": [[65536, 5632], []], "Ev Idx": 8288 + } + }, + { + "ph": "s", "id": 139, "pid": 1336756, "tid": 1336756, "ts": 1655274280168.181, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "SwiGLULinearFunction", "pid": 1336756, "tid": 1336756, + "ts": 1655274280192.167, "dur": 143.850, + "args": { + "External id": 4050378,"Sequence number": 40618442, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[23068672, 5632, 1], [23068672, 5632, 1], [5632, 1], []], "Input Dims": [[16, 4096, 5632], [16, 4096, 5632], [2048, 5632], []], "Ev Idx": 8289 + } + }, + { + "ph": "s", "id": 138, "pid": 1336756, "tid": 1336756, "ts": 1655274280192.167, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274280230.253, "dur": 4.542, + "args": { + "External id": 4050379,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 5632]", "15", "", "", "", "0"], "Input type": ["ScalarList", "Scalar", "", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8290 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336756, "tid": 1336756, + "ts": 1655274280265.331, "dur": 57.700, + "args": { + "External id": 4050380,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[23068672, 5632, 1], [5632, 1], []], "Input Dims": [[16, 4096, 5632], [2048, 5632], []], "Ev Idx": 8291 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1336756, + "ts": 1655274280266.110, "dur": 6.402, + "args": { + "External id": 4050381,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 8292 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1336756, + "ts": 1655274280267.319, "dur": 4.477, + "args": { + "External id": 4050382,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[5632, 1], [], []], "Input Dims": [[2048, 5632], [], []], "Ev Idx": 8293 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274280270.755, "dur": 0.864, + "args": { + "External id": 4050383,"Record function id": 0, "Concrete Inputs": ["", "[5632, 2048]", "[1, 5632]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[5632, 1], [], [], []], "Input Dims": [[2048, 5632], [], [], []], "Ev Idx": 8294 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336756, "tid": 1336756, + "ts": 1655274280273.166, "dur": 49.520, + "args": { + "External id": 4050384,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[23068672, 5632, 1], [1, 5632]], "Input Dims": [[16, 4096, 5632], [5632, 2048]], "Ev Idx": 8295 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1336756, + "ts": 1655274280275.897, "dur": 1.875, + "args": { + "External id": 4050385,"Record function id": 0, "Concrete Inputs": ["", "[65536, 5632]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[23068672, 5632, 1], []], "Input Dims": [[16, 4096, 5632], []], "Ev Idx": 8296 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274280276.559, "dur": 1.090, + "args": { + "External id": 4050386,"Record function id": 0, "Concrete Inputs": ["", "[65536, 5632]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[23068672, 5632, 1], []], "Input Dims": [[16, 4096, 5632], []], "Ev Idx": 8297 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274280278.446, "dur": 40.864, + "args": { + "External id": 4050387,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [1, 5632]], "Input Dims": [[65536, 5632], [5632, 2048]], "Ev Idx": 8298 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 1336756, "tid": 1336756, + "ts": 1655274280321.186, "dur": 0.896, + "args": { + "External id": 4050388,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 8299 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add", "pid": 1336756, "tid": 1336756, + "ts": 1655274280346.135, "dur": 24.131, + "args": { + "External id": 4050389,"Sequence number": 40618443, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[8388608, 2048, 1], [8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], [16, 4096, 2048], []], "Ev Idx": 8300 + } + }, + { + "ph": "s", "id": 137, "pid": 1336756, "tid": 1336756, "ts": 1655274280346.135, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunction", "pid": 1336756, "tid": 1336756, + "ts": 1655274280401.028, "dur": 197.329, + "args": { + "External id": 4050390,"Sequence number": 40618444, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "9.9999999999999995e-07", "False", "False", "True"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 1], [1], [], [], [], [], [], []], "Input Dims": [[16, 4096, 2048], [2048], [], [], [], [], [], []], "Ev Idx": 8301 + } + }, + { + "ph": "s", "id": 136, "pid": 1336756, "tid": 1336756, "ts": 1655274280401.028, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1336756, + "ts": 1655274280436.579, "dur": 5.704, + "args": { + "External id": 4050391,"Record function id": 0, "Concrete Inputs": ["", "[-1, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8302 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274280439.241, "dur": 2.718, + "args": { + "External id": 4050392,"Record function id": 0, "Concrete Inputs": ["", "[-1, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8303 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336756, "tid": 1336756, + "ts": 1655274280450.714, "dur": 7.398, + "args": { + "External id": 4050393,"Record function id": 0, "Concrete Inputs": ["", "15", "", "", "False", ""], "Input type": ["c10::BFloat16", "Scalar", "", "", "Scalar", ""], "Input Strides": [[2048, 1], [], [], [], [], []], "Input Dims": [[65536, 2048], [], [], [], [], []], "Ev Idx": 8304 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274280452.739, "dur": 4.964, + "args": { + "External id": 4050394,"Record function id": 0, "Concrete Inputs": ["[65536, 2048]", "[2048, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8305 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274280464.169, "dur": 3.527, + "args": { + "External id": 4050395,"Record function id": 0, "Concrete Inputs": ["[65536]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8306 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1336756, + "ts": 1655274280582.678, "dur": 3.184, + "args": { + "External id": 4050396,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 8307 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274280583.584, "dur": 2.051, + "args": { + "External id": 4050397,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 8308 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336756, "tid": 1336756, + "ts": 1655274280617.514, "dur": 80.874, + "args": { + "External id": 4050398,"Sequence number": 40618445, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[8388608, 2048, 1], [2048, 1], []], "Input Dims": [[16, 4096, 2048], [2048, 2048], []], "Ev Idx": 8309 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1336756, + "ts": 1655274280618.671, "dur": 8.220, + "args": { + "External id": 4050399,"Sequence number": 40618445, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 8310 + } + }, + { + "ph": "s", "id": 135, "pid": 1336756, "tid": 1336756, "ts": 1655274280618.671, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1336756, + "ts": 1655274280622.379, "dur": 3.229, + "args": { + "External id": 4050400,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[2048, 2048], [], []], "Ev Idx": 8311 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274280624.151, "dur": 1.241, + "args": { + "External id": 4050401,"Record function id": 0, "Concrete Inputs": ["", "[2048, 2048]", "[1, 2048]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[2048, 2048], [], [], []], "Ev Idx": 8312 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336756, "tid": 1336756, + "ts": 1655274280627.787, "dur": 70.258, + "args": { + "External id": 4050402,"Sequence number": 40618446, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[8388608, 2048, 1], [1, 2048]], "Input Dims": [[16, 4096, 2048], [2048, 2048]], "Ev Idx": 8313 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1336756, + "ts": 1655274280629.169, "dur": 4.553, + "args": { + "External id": 4050403,"Sequence number": 40618446, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[65536, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8314 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274280631.358, "dur": 2.199, + "args": { + "External id": 4050404,"Sequence number": 40618446, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[65536, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8315 + } + }, + { + "ph": "s", "id": 134, "pid": 1336756, "tid": 1336756, "ts": 1655274280631.358, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274280634.420, "dur": 57.197, + "args": { + "External id": 4050405,"Sequence number": 40618447, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048]], "Input Dims": [[65536, 2048], [2048, 2048]], "Ev Idx": 8316 + } + }, + { + "ph": "s", "id": 133, "pid": 1336756, "tid": 1336756, "ts": 1655274280634.420, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 1336756, "tid": 1336756, + "ts": 1655274280693.222, "dur": 4.100, + "args": { + "External id": 4050406,"Sequence number": 40618448, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 8317 + } + }, + { + "ph": "s", "id": 132, "pid": 1336756, "tid": 1336756, "ts": 1655274280693.222, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336756, "tid": 1336756, + "ts": 1655274280705.843, "dur": 63.603, + "args": { + "External id": 4050407,"Sequence number": 40618449, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[8388608, 2048, 1], [2048, 1], []], "Input Dims": [[16, 4096, 2048], [2048, 2048], []], "Ev Idx": 8318 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1336756, + "ts": 1655274280706.521, "dur": 9.000, + "args": { + "External id": 4050408,"Sequence number": 40618449, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 8319 + } + }, + { + "ph": "s", "id": 131, "pid": 1336756, "tid": 1336756, "ts": 1655274280706.521, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1336756, + "ts": 1655274280711.965, "dur": 2.612, + "args": { + "External id": 4050409,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[2048, 2048], [], []], "Ev Idx": 8320 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274280713.459, "dur": 0.849, + "args": { + "External id": 4050410,"Record function id": 0, "Concrete Inputs": ["", "[2048, 2048]", "[1, 2048]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[2048, 2048], [], [], []], "Ev Idx": 8321 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336756, "tid": 1336756, + "ts": 1655274280716.126, "dur": 53.106, + "args": { + "External id": 4050411,"Sequence number": 40618450, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[8388608, 2048, 1], [1, 2048]], "Input Dims": [[16, 4096, 2048], [2048, 2048]], "Ev Idx": 8322 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1336756, + "ts": 1655274280716.912, "dur": 4.807, + "args": { + "External id": 4050412,"Sequence number": 40618450, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[65536, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8323 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274280718.059, "dur": 3.509, + "args": { + "External id": 4050413,"Sequence number": 40618450, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[65536, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8324 + } + }, + { + "ph": "s", "id": 130, "pid": 1336756, "tid": 1336756, "ts": 1655274280718.059, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274280722.352, "dur": 42.511, + "args": { + "External id": 4050414,"Sequence number": 40618451, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048]], "Input Dims": [[65536, 2048], [2048, 2048]], "Ev Idx": 8325 + } + }, + { + "ph": "s", "id": 129, "pid": 1336756, "tid": 1336756, "ts": 1655274280722.352, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 1336756, "tid": 1336756, + "ts": 1655274280766.746, "dur": 2.080, + "args": { + "External id": 4050415,"Sequence number": 40618452, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 8326 + } + }, + { + "ph": "s", "id": 128, "pid": 1336756, "tid": 1336756, "ts": 1655274280766.746, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336756, "tid": 1336756, + "ts": 1655274280775.887, "dur": 58.173, + "args": { + "External id": 4050416,"Sequence number": 40618453, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[8388608, 2048, 1], [2048, 1], []], "Input Dims": [[16, 4096, 2048], [2048, 2048], []], "Ev Idx": 8327 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1336756, + "ts": 1655274280776.597, "dur": 6.109, + "args": { + "External id": 4050417,"Sequence number": 40618453, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 8328 + } + }, + { + "ph": "s", "id": 127, "pid": 1336756, "tid": 1336756, "ts": 1655274280776.597, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1336756, + "ts": 1655274280777.665, "dur": 4.191, + "args": { + "External id": 4050418,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[2048, 2048], [], []], "Ev Idx": 8329 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274280780.842, "dur": 0.883, + "args": { + "External id": 4050419,"Record function id": 0, "Concrete Inputs": ["", "[2048, 2048]", "[1, 2048]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[2048, 2048], [], [], []], "Ev Idx": 8330 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336756, "tid": 1336756, + "ts": 1655274280783.213, "dur": 50.659, + "args": { + "External id": 4050420,"Sequence number": 40618454, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[8388608, 2048, 1], [1, 2048]], "Input Dims": [[16, 4096, 2048], [2048, 2048]], "Ev Idx": 8331 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1336756, + "ts": 1655274280784.335, "dur": 4.542, + "args": { + "External id": 4050421,"Sequence number": 40618454, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[65536, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8332 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274280785.099, "dur": 3.639, + "args": { + "External id": 4050422,"Sequence number": 40618454, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[65536, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8333 + } + }, + { + "ph": "s", "id": 126, "pid": 1336756, "tid": 1336756, "ts": 1655274280785.099, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274280791.216, "dur": 38.525, + "args": { + "External id": 4050423,"Sequence number": 40618455, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048]], "Input Dims": [[65536, 2048], [2048, 2048]], "Ev Idx": 8334 + } + }, + { + "ph": "s", "id": 125, "pid": 1336756, "tid": 1336756, "ts": 1655274280791.216, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 1336756, "tid": 1336756, + "ts": 1655274280831.138, "dur": 2.429, + "args": { + "External id": 4050424,"Sequence number": 40618456, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 8335 + } + }, + { + "ph": "s", "id": 124, "pid": 1336756, "tid": 1336756, "ts": 1655274280831.138, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1336756, + "ts": 1655274280847.841, "dur": 3.333, + "args": { + "External id": 4050425,"Sequence number": 40618457, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 32, 64]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8336 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274280848.552, "dur": 2.484, + "args": { + "External id": 4050426,"Sequence number": 40618457, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 32, 64]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8337 + } + }, + { + "ph": "s", "id": 123, "pid": 1336756, "tid": 1336756, "ts": 1655274280848.552, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1336756, + "ts": 1655274280857.508, "dur": 7.539, + "args": { + "External id": 4050427,"Sequence number": 40618458, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 32, 64]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8338 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274280860.000, "dur": 4.867, + "args": { + "External id": 4050428,"Sequence number": 40618458, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 32, 64]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8339 + } + }, + { + "ph": "s", "id": 122, "pid": 1336756, "tid": 1336756, "ts": 1655274280860.000, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1336756, + "ts": 1655274280869.188, "dur": 3.074, + "args": { + "External id": 4050429,"Sequence number": 40618459, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 32, 64]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8340 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274280870.185, "dur": 1.913, + "args": { + "External id": 4050430,"Sequence number": 40618459, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 32, 64]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8341 + } + }, + { + "ph": "s", "id": 121, "pid": 1336756, "tid": 1336756, "ts": 1655274280870.185, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunction", "pid": 1336756, "tid": 1336756, + "ts": 1655274280897.720, "dur": 212.729, + "args": { + "External id": 4050431,"Sequence number": 40618460, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "False", "False", "0", "", "8192"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [], [], [], [], []], "Ev Idx": 8342 + } + }, + { + "ph": "s", "id": 120, "pid": 1336756, "tid": 1336756, "ts": 1655274280897.720, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336756, "tid": 1336756, + "ts": 1655274280915.258, "dur": 33.632, + "args": { + "External id": 4050432,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[8388608, 2048, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [], [], [], [], []], "Ev Idx": 8343 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274280944.127, "dur": 4.342, + "args": { + "External id": 4050433,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "[8388608, 2048, 64, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8344 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunction", "pid": 1336756, "tid": 1336756, + "ts": 1655274281126.938, "dur": 102.719, + "args": { + "External id": 4050434,"Sequence number": 40618461, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "False", "False", "0", "", "8192"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [], [], [], [], []], "Ev Idx": 8345 + } + }, + { + "ph": "s", "id": 119, "pid": 1336756, "tid": 1336756, "ts": 1655274281126.938, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336756, "tid": 1336756, + "ts": 1655274281141.754, "dur": 8.019, + "args": { + "External id": 4050435,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[8388608, 2048, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [], [], [], [], []], "Ev Idx": 8346 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274281144.072, "dur": 5.288, + "args": { + "External id": 4050436,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "[8388608, 2048, 64, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8347 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "FlashAttnFunc", "pid": 1336756, "tid": 1336756, + "ts": 1655274281255.529, "dur": 190.882, + "args": { + "External id": 4050437,"Sequence number": 40618462, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "", "True", "", "0.", "", "False", "False", "True"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "", "Scalar", "", "Scalar", "", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], []], "Ev Idx": 8348 + } + }, + { + "ph": "s", "id": 118, "pid": 1336756, "tid": 1336756, "ts": 1655274281255.529, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 1336756, "tid": 1336756, + "ts": 1655274281283.333, "dur": 116.231, + "args": { + "External id": 4050438,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.125", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [], [], [], [], [], [], [], []], "Ev Idx": 8349 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336756, "tid": 1336756, + "ts": 1655274281329.323, "dur": 6.627, + "args": { + "External id": 4050439,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[8388608, 2048, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [], [], [], [], []], "Ev Idx": 8350 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274281331.388, "dur": 3.985, + "args": { + "External id": 4050440,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "[8388608, 2048, 64, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8351 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274281338.259, "dur": 3.611, + "args": { + "External id": 4050441,"Record function id": 0, "Concrete Inputs": ["[16, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8352 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274281343.119, "dur": 1.349, + "args": { + "External id": 4050442,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8353 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274281346.549, "dur": 3.203, + "args": { + "External id": 4050443,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8354 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::alias", "pid": 1336756, "tid": 1336756, + "ts": 1655274281410.983, "dur": 23.430, + "args": { + "External id": 4050444,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 64, 1]], "Input Dims": [[16, 4096, 32, 64]], "Ev Idx": 8355 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1336756, + "ts": 1655274281453.250, "dur": 8.059, + "args": { + "External id": 4050445,"Sequence number": 40618463, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[16, 4096, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 64, 1], []], "Input Dims": [[16, 4096, 32, 64], []], "Ev Idx": 8356 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274281454.370, "dur": 6.743, + "args": { + "External id": 4050446,"Sequence number": 40618463, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[16, 4096, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 64, 1], []], "Input Dims": [[16, 4096, 32, 64], []], "Ev Idx": 8357 + } + }, + { + "ph": "s", "id": 117, "pid": 1336756, "tid": 1336756, "ts": 1655274281454.370, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336756, "tid": 1336756, + "ts": 1655274281476.874, "dur": 112.150, + "args": { + "External id": 4050447,"Sequence number": 40618464, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[8388608, 2048, 1], [2048, 1], []], "Input Dims": [[16, 4096, 2048], [2048, 2048], []], "Ev Idx": 8358 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1336756, + "ts": 1655274281478.636, "dur": 8.978, + "args": { + "External id": 4050448,"Sequence number": 40618464, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 8359 + } + }, + { + "ph": "s", "id": 116, "pid": 1336756, "tid": 1336756, "ts": 1655274281478.636, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1336756, + "ts": 1655274281482.059, "dur": 4.528, + "args": { + "External id": 4050449,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[2048, 2048], [], []], "Ev Idx": 8360 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274281484.892, "dur": 1.370, + "args": { + "External id": 4050450,"Record function id": 0, "Concrete Inputs": ["", "[2048, 2048]", "[1, 2048]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[2048, 2048], [], [], []], "Ev Idx": 8361 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336756, "tid": 1336756, + "ts": 1655274281488.898, "dur": 99.697, + "args": { + "External id": 4050451,"Sequence number": 40618465, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[8388608, 2048, 1], [1, 2048]], "Input Dims": [[16, 4096, 2048], [2048, 2048]], "Ev Idx": 8362 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1336756, + "ts": 1655274281492.765, "dur": 4.549, + "args": { + "External id": 4050452,"Sequence number": 40618465, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[65536, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8363 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274281493.596, "dur": 3.571, + "args": { + "External id": 4050453,"Sequence number": 40618465, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[65536, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8364 + } + }, + { + "ph": "s", "id": 115, "pid": 1336756, "tid": 1336756, "ts": 1655274281493.596, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274281498.513, "dur": 81.938, + "args": { + "External id": 4050454,"Sequence number": 40618466, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048]], "Input Dims": [[65536, 2048], [2048, 2048]], "Ev Idx": 8365 + } + }, + { + "ph": "s", "id": 114, "pid": 1336756, "tid": 1336756, "ts": 1655274281498.513, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 1336756, "tid": 1336756, + "ts": 1655274281582.876, "dur": 4.944, + "args": { + "External id": 4050455,"Sequence number": 40618467, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 8366 + } + }, + { + "ph": "s", "id": 113, "pid": 1336756, "tid": 1336756, "ts": 1655274281582.876, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunction", "pid": 1336756, "tid": 1336756, + "ts": 1655274281621.774, "dur": 205.709, + "args": { + "External id": 4050456,"Sequence number": 40618468, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "9.9999999999999995e-07", "True", "False", "True"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 1], [1], [], [8388608, 2048, 1], [], [], [], []], "Input Dims": [[16, 4096, 2048], [2048], [], [16, 4096, 2048], [], [], [], []], "Ev Idx": 8367 + } + }, + { + "ph": "s", "id": 112, "pid": 1336756, "tid": 1336756, "ts": 1655274281621.774, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1336756, + "ts": 1655274281642.355, "dur": 2.409, + "args": { + "External id": 4050457,"Record function id": 0, "Concrete Inputs": ["", "[-1, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8368 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274281643.215, "dur": 1.362, + "args": { + "External id": 4050458,"Record function id": 0, "Concrete Inputs": ["", "[-1, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8369 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape_as", "pid": 1336756, "tid": 1336756, + "ts": 1655274281648.588, "dur": 4.342, + "args": { + "External id": 4050459,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[8388608, 2048, 1], [2048, 1]], "Input Dims": [[16, 4096, 2048], [65536, 2048]], "Ev Idx": 8370 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1336756, + "ts": 1655274281649.590, "dur": 3.235, + "args": { + "External id": 4050460,"Record function id": 0, "Concrete Inputs": ["", "[65536, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8371 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274281651.912, "dur": 0.808, + "args": { + "External id": 4050461,"Record function id": 0, "Concrete Inputs": ["", "[65536, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8372 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336756, "tid": 1336756, + "ts": 1655274281660.344, "dur": 6.893, + "args": { + "External id": 4050462,"Record function id": 0, "Concrete Inputs": ["", "15", "", "", "False", ""], "Input type": ["c10::BFloat16", "Scalar", "", "", "Scalar", ""], "Input Strides": [[2048, 1], [], [], [], [], []], "Input Dims": [[65536, 2048], [], [], [], [], []], "Ev Idx": 8373 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274281662.074, "dur": 4.827, + "args": { + "External id": 4050463,"Record function id": 0, "Concrete Inputs": ["[65536, 2048]", "[2048, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8374 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274281673.126, "dur": 3.186, + "args": { + "External id": 4050464,"Record function id": 0, "Concrete Inputs": ["[65536, 2048]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8375 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274281679.659, "dur": 3.175, + "args": { + "External id": 4050465,"Record function id": 0, "Concrete Inputs": ["[65536]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8376 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1336756, + "ts": 1655274281806.175, "dur": 3.061, + "args": { + "External id": 4050466,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 8377 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274281807.073, "dur": 1.879, + "args": { + "External id": 4050467,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 8378 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1336756, + "ts": 1655274281812.847, "dur": 2.058, + "args": { + "External id": 4050468,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 8379 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274281813.768, "dur": 1.025, + "args": { + "External id": 4050469,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 8380 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336756, "tid": 1336756, + "ts": 1655274281846.206, "dur": 87.546, + "args": { + "External id": 4050470,"Sequence number": 40618469, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[8388608, 2048, 1], [2048, 1], []], "Input Dims": [[16, 4096, 2048], [5632, 2048], []], "Ev Idx": 8381 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1336756, + "ts": 1655274281847.043, "dur": 6.967, + "args": { + "External id": 4050471,"Sequence number": 40618469, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 8382 + } + }, + { + "ph": "s", "id": 111, "pid": 1336756, "tid": 1336756, "ts": 1655274281847.043, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1336756, + "ts": 1655274281849.329, "dur": 3.598, + "args": { + "External id": 4050472,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[5632, 2048], [], []], "Ev Idx": 8383 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274281851.234, "dur": 1.395, + "args": { + "External id": 4050473,"Record function id": 0, "Concrete Inputs": ["", "[2048, 5632]", "[1, 2048]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[5632, 2048], [], [], []], "Ev Idx": 8384 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336756, "tid": 1336756, + "ts": 1655274281856.496, "dur": 76.933, + "args": { + "External id": 4050474,"Sequence number": 40618470, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[8388608, 2048, 1], [1, 2048]], "Input Dims": [[16, 4096, 2048], [2048, 5632]], "Ev Idx": 8385 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1336756, + "ts": 1655274281857.729, "dur": 2.805, + "args": { + "External id": 4050475,"Sequence number": 40618470, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[65536, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8386 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274281858.176, "dur": 2.222, + "args": { + "External id": 4050476,"Sequence number": 40618470, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[65536, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8387 + } + }, + { + "ph": "s", "id": 110, "pid": 1336756, "tid": 1336756, "ts": 1655274281858.176, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274281861.244, "dur": 65.632, + "args": { + "External id": 4050477,"Sequence number": 40618471, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048]], "Input Dims": [[65536, 2048], [2048, 5632]], "Ev Idx": 8388 + } + }, + { + "ph": "s", "id": 109, "pid": 1336756, "tid": 1336756, "ts": 1655274281861.244, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 1336756, "tid": 1336756, + "ts": 1655274281928.835, "dur": 3.970, + "args": { + "External id": 4050478,"Sequence number": 40618472, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 5632]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[5632, 1], []], "Input Dims": [[65536, 5632], []], "Ev Idx": 8389 + } + }, + { + "ph": "s", "id": 108, "pid": 1336756, "tid": 1336756, "ts": 1655274281928.835, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336756, "tid": 1336756, + "ts": 1655274281940.981, "dur": 107.933, + "args": { + "External id": 4050479,"Sequence number": 40618473, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[8388608, 2048, 1], [2048, 1], []], "Input Dims": [[16, 4096, 2048], [5632, 2048], []], "Ev Idx": 8390 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1336756, + "ts": 1655274281941.635, "dur": 5.251, + "args": { + "External id": 4050480,"Sequence number": 40618473, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 8391 + } + }, + { + "ph": "s", "id": 107, "pid": 1336756, "tid": 1336756, "ts": 1655274281941.635, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1336756, + "ts": 1655274281943.019, "dur": 2.770, + "args": { + "External id": 4050481,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[5632, 2048], [], []], "Ev Idx": 8392 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274281944.719, "dur": 0.895, + "args": { + "External id": 4050482,"Record function id": 0, "Concrete Inputs": ["", "[2048, 5632]", "[1, 2048]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[5632, 2048], [], [], []], "Ev Idx": 8393 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336756, "tid": 1336756, + "ts": 1655274281947.517, "dur": 101.166, + "args": { + "External id": 4050483,"Sequence number": 40618474, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[8388608, 2048, 1], [1, 2048]], "Input Dims": [[16, 4096, 2048], [2048, 5632]], "Ev Idx": 8394 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1336756, + "ts": 1655274281950.132, "dur": 5.192, + "args": { + "External id": 4050484,"Sequence number": 40618474, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[65536, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8395 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274281950.752, "dur": 4.407, + "args": { + "External id": 4050485,"Sequence number": 40618474, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[65536, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8396 + } + }, + { + "ph": "s", "id": 106, "pid": 1336756, "tid": 1336756, "ts": 1655274281950.752, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274281955.833, "dur": 84.888, + "args": { + "External id": 4050486,"Sequence number": 40618475, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048]], "Input Dims": [[65536, 2048], [2048, 5632]], "Ev Idx": 8397 + } + }, + { + "ph": "s", "id": 105, "pid": 1336756, "tid": 1336756, "ts": 1655274281955.833, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 1336756, "tid": 1336756, + "ts": 1655274282043.497, "dur": 4.706, + "args": { + "External id": 4050487,"Sequence number": 40618476, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 5632]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[5632, 1], []], "Input Dims": [[65536, 5632], []], "Ev Idx": 8398 + } + }, + { + "ph": "s", "id": 104, "pid": 1336756, "tid": 1336756, "ts": 1655274282043.497, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "SwiGLULinearFunction", "pid": 1336756, "tid": 1336756, + "ts": 1655274282073.033, "dur": 144.037, + "args": { + "External id": 4050488,"Sequence number": 40618477, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[23068672, 5632, 1], [23068672, 5632, 1], [5632, 1], []], "Input Dims": [[16, 4096, 5632], [16, 4096, 5632], [2048, 5632], []], "Ev Idx": 8399 + } + }, + { + "ph": "s", "id": 103, "pid": 1336756, "tid": 1336756, "ts": 1655274282073.033, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274282107.461, "dur": 4.655, + "args": { + "External id": 4050489,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 5632]", "15", "", "", "", "0"], "Input type": ["ScalarList", "Scalar", "", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8400 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336756, "tid": 1336756, + "ts": 1655274282141.716, "dur": 61.894, + "args": { + "External id": 4050490,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[23068672, 5632, 1], [5632, 1], []], "Input Dims": [[16, 4096, 5632], [2048, 5632], []], "Ev Idx": 8401 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1336756, + "ts": 1655274282142.635, "dur": 4.855, + "args": { + "External id": 4050491,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 8402 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1336756, + "ts": 1655274282143.809, "dur": 2.834, + "args": { + "External id": 4050492,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[5632, 1], [], []], "Input Dims": [[2048, 5632], [], []], "Ev Idx": 8403 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274282145.389, "dur": 1.069, + "args": { + "External id": 4050493,"Record function id": 0, "Concrete Inputs": ["", "[5632, 2048]", "[1, 5632]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[5632, 1], [], [], []], "Input Dims": [[2048, 5632], [], [], []], "Ev Idx": 8404 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336756, "tid": 1336756, + "ts": 1655274282149.894, "dur": 53.399, + "args": { + "External id": 4050494,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[23068672, 5632, 1], [1, 5632]], "Input Dims": [[16, 4096, 5632], [5632, 2048]], "Ev Idx": 8405 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1336756, + "ts": 1655274282151.123, "dur": 2.322, + "args": { + "External id": 4050495,"Record function id": 0, "Concrete Inputs": ["", "[65536, 5632]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[23068672, 5632, 1], []], "Input Dims": [[16, 4096, 5632], []], "Ev Idx": 8406 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274282151.962, "dur": 1.371, + "args": { + "External id": 4050496,"Record function id": 0, "Concrete Inputs": ["", "[65536, 5632]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[23068672, 5632, 1], []], "Input Dims": [[16, 4096, 5632], []], "Ev Idx": 8407 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274282153.960, "dur": 45.865, + "args": { + "External id": 4050497,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [1, 5632]], "Input Dims": [[65536, 5632], [5632, 2048]], "Ev Idx": 8408 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 1336756, "tid": 1336756, + "ts": 1655274282201.691, "dur": 1.067, + "args": { + "External id": 4050498,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 8409 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add", "pid": 1336756, "tid": 1336756, + "ts": 1655274282225.597, "dur": 23.153, + "args": { + "External id": 4050499,"Sequence number": 40618478, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[8388608, 2048, 1], [8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], [16, 4096, 2048], []], "Ev Idx": 8410 + } + }, + { + "ph": "s", "id": 102, "pid": 1336756, "tid": 1336756, "ts": 1655274282225.597, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunction", "pid": 1336756, "tid": 1336756, + "ts": 1655274282281.223, "dur": 199.937, + "args": { + "External id": 4050500,"Sequence number": 40618479, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "9.9999999999999995e-07", "False", "False", "True"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 1], [1], [], [], [], [], [], []], "Input Dims": [[16, 4096, 2048], [2048], [], [], [], [], [], []], "Ev Idx": 8411 + } + }, + { + "ph": "s", "id": 101, "pid": 1336756, "tid": 1336756, "ts": 1655274282281.223, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1336756, + "ts": 1655274282299.775, "dur": 2.908, + "args": { + "External id": 4050501,"Record function id": 0, "Concrete Inputs": ["", "[-1, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8412 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274282300.485, "dur": 2.000, + "args": { + "External id": 4050502,"Record function id": 0, "Concrete Inputs": ["", "[-1, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8413 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336756, "tid": 1336756, + "ts": 1655274282310.119, "dur": 6.636, + "args": { + "External id": 4050503,"Record function id": 0, "Concrete Inputs": ["", "15", "", "", "False", ""], "Input type": ["c10::BFloat16", "Scalar", "", "", "Scalar", ""], "Input Strides": [[2048, 1], [], [], [], [], []], "Input Dims": [[65536, 2048], [], [], [], [], []], "Ev Idx": 8414 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274282312.535, "dur": 3.870, + "args": { + "External id": 4050504,"Record function id": 0, "Concrete Inputs": ["[65536, 2048]", "[2048, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8415 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274282322.803, "dur": 3.188, + "args": { + "External id": 4050505,"Record function id": 0, "Concrete Inputs": ["[65536]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8416 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1336756, + "ts": 1655274282462.904, "dur": 3.712, + "args": { + "External id": 4050506,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 8417 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274282463.963, "dur": 2.368, + "args": { + "External id": 4050507,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 8418 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336756, "tid": 1336756, + "ts": 1655274282499.505, "dur": 87.215, + "args": { + "External id": 4050508,"Sequence number": 40618480, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[8388608, 2048, 1], [2048, 1], []], "Input Dims": [[16, 4096, 2048], [2048, 2048], []], "Ev Idx": 8419 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1336756, + "ts": 1655274282500.398, "dur": 6.750, + "args": { + "External id": 4050509,"Sequence number": 40618480, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 8420 + } + }, + { + "ph": "s", "id": 100, "pid": 1336756, "tid": 1336756, "ts": 1655274282500.398, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1336756, + "ts": 1655274282502.882, "dur": 3.080, + "args": { + "External id": 4050510,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[2048, 2048], [], []], "Ev Idx": 8421 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274282504.726, "dur": 1.019, + "args": { + "External id": 4050511,"Record function id": 0, "Concrete Inputs": ["", "[2048, 2048]", "[1, 2048]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[2048, 2048], [], [], []], "Ev Idx": 8422 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336756, "tid": 1336756, + "ts": 1655274282508.568, "dur": 77.836, + "args": { + "External id": 4050512,"Sequence number": 40618481, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[8388608, 2048, 1], [1, 2048]], "Input Dims": [[16, 4096, 2048], [2048, 2048]], "Ev Idx": 8423 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1336756, + "ts": 1655274282511.943, "dur": 3.740, + "args": { + "External id": 4050513,"Sequence number": 40618481, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[65536, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8424 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274282512.879, "dur": 2.693, + "args": { + "External id": 4050514,"Sequence number": 40618481, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[65536, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8425 + } + }, + { + "ph": "s", "id": 99, "pid": 1336756, "tid": 1336756, "ts": 1655274282512.879, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274282516.442, "dur": 62.121, + "args": { + "External id": 4050515,"Sequence number": 40618482, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048]], "Input Dims": [[65536, 2048], [2048, 2048]], "Ev Idx": 8426 + } + }, + { + "ph": "s", "id": 98, "pid": 1336756, "tid": 1336756, "ts": 1655274282516.442, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 1336756, "tid": 1336756, + "ts": 1655274282580.628, "dur": 5.009, + "args": { + "External id": 4050516,"Sequence number": 40618483, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 8427 + } + }, + { + "ph": "s", "id": 97, "pid": 1336756, "tid": 1336756, "ts": 1655274282580.628, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336756, "tid": 1336756, + "ts": 1655274282594.014, "dur": 59.986, + "args": { + "External id": 4050517,"Sequence number": 40618484, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[8388608, 2048, 1], [2048, 1], []], "Input Dims": [[16, 4096, 2048], [2048, 2048], []], "Ev Idx": 8428 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1336756, + "ts": 1655274282596.248, "dur": 4.569, + "args": { + "External id": 4050518,"Sequence number": 40618484, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 8429 + } + }, + { + "ph": "s", "id": 96, "pid": 1336756, "tid": 1336756, "ts": 1655274282596.248, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1336756, + "ts": 1655274282597.450, "dur": 2.389, + "args": { + "External id": 4050519,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[2048, 2048], [], []], "Ev Idx": 8430 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274282598.936, "dur": 0.724, + "args": { + "External id": 4050520,"Record function id": 0, "Concrete Inputs": ["", "[2048, 2048]", "[1, 2048]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[2048, 2048], [], [], []], "Ev Idx": 8431 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336756, "tid": 1336756, + "ts": 1655274282601.546, "dur": 52.181, + "args": { + "External id": 4050521,"Sequence number": 40618485, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[8388608, 2048, 1], [1, 2048]], "Input Dims": [[16, 4096, 2048], [2048, 2048]], "Ev Idx": 8432 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1336756, + "ts": 1655274282602.975, "dur": 4.795, + "args": { + "External id": 4050522,"Sequence number": 40618485, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[65536, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8433 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274282605.487, "dur": 2.144, + "args": { + "External id": 4050523,"Sequence number": 40618485, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[65536, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8434 + } + }, + { + "ph": "s", "id": 95, "pid": 1336756, "tid": 1336756, "ts": 1655274282605.487, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274282608.541, "dur": 40.689, + "args": { + "External id": 4050524,"Sequence number": 40618486, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048]], "Input Dims": [[65536, 2048], [2048, 2048]], "Ev Idx": 8435 + } + }, + { + "ph": "s", "id": 94, "pid": 1336756, "tid": 1336756, "ts": 1655274282608.541, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 1336756, "tid": 1336756, + "ts": 1655274282650.868, "dur": 2.513, + "args": { + "External id": 4050525,"Sequence number": 40618487, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 8436 + } + }, + { + "ph": "s", "id": 93, "pid": 1336756, "tid": 1336756, "ts": 1655274282650.868, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336756, "tid": 1336756, + "ts": 1655274282659.885, "dur": 60.952, + "args": { + "External id": 4050526,"Sequence number": 40618488, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[8388608, 2048, 1], [2048, 1], []], "Input Dims": [[16, 4096, 2048], [2048, 2048], []], "Ev Idx": 8437 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1336756, + "ts": 1655274282660.525, "dur": 7.557, + "args": { + "External id": 4050527,"Sequence number": 40618488, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 8438 + } + }, + { + "ph": "s", "id": 92, "pid": 1336756, "tid": 1336756, "ts": 1655274282660.525, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1336756, + "ts": 1655274282663.003, "dur": 4.186, + "args": { + "External id": 4050528,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[2048, 2048], [], []], "Ev Idx": 8439 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274282664.314, "dur": 2.419, + "args": { + "External id": 4050529,"Record function id": 0, "Concrete Inputs": ["", "[2048, 2048]", "[1, 2048]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[2048, 2048], [], [], []], "Ev Idx": 8440 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336756, "tid": 1336756, + "ts": 1655274282668.954, "dur": 51.556, + "args": { + "External id": 4050530,"Sequence number": 40618489, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[8388608, 2048, 1], [1, 2048]], "Input Dims": [[16, 4096, 2048], [2048, 2048]], "Ev Idx": 8441 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1336756, + "ts": 1655274282669.904, "dur": 6.318, + "args": { + "External id": 4050531,"Sequence number": 40618489, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[65536, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8442 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274282672.611, "dur": 3.464, + "args": { + "External id": 4050532,"Sequence number": 40618489, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[65536, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8443 + } + }, + { + "ph": "s", "id": 91, "pid": 1336756, "tid": 1336756, "ts": 1655274282672.611, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274282676.970, "dur": 38.457, + "args": { + "External id": 4050533,"Sequence number": 40618490, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048]], "Input Dims": [[65536, 2048], [2048, 2048]], "Ev Idx": 8444 + } + }, + { + "ph": "s", "id": 90, "pid": 1336756, "tid": 1336756, "ts": 1655274282676.970, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 1336756, "tid": 1336756, + "ts": 1655274282716.870, "dur": 3.325, + "args": { + "External id": 4050534,"Sequence number": 40618491, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 8445 + } + }, + { + "ph": "s", "id": 89, "pid": 1336756, "tid": 1336756, "ts": 1655274282716.870, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1336756, + "ts": 1655274282735.199, "dur": 4.926, + "args": { + "External id": 4050535,"Sequence number": 40618492, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 32, 64]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8446 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274282736.068, "dur": 3.862, + "args": { + "External id": 4050536,"Sequence number": 40618492, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 32, 64]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8447 + } + }, + { + "ph": "s", "id": 88, "pid": 1336756, "tid": 1336756, "ts": 1655274282736.068, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1336756, + "ts": 1655274282746.045, "dur": 2.709, + "args": { + "External id": 4050537,"Sequence number": 40618493, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 32, 64]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8448 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274282747.069, "dur": 1.560, + "args": { + "External id": 4050538,"Sequence number": 40618493, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 32, 64]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8449 + } + }, + { + "ph": "s", "id": 87, "pid": 1336756, "tid": 1336756, "ts": 1655274282747.069, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1336756, + "ts": 1655274282752.813, "dur": 2.790, + "args": { + "External id": 4050539,"Sequence number": 40618494, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 32, 64]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8450 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274282753.745, "dur": 1.723, + "args": { + "External id": 4050540,"Sequence number": 40618494, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 32, 64]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8451 + } + }, + { + "ph": "s", "id": 86, "pid": 1336756, "tid": 1336756, "ts": 1655274282753.745, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunction", "pid": 1336756, "tid": 1336756, + "ts": 1655274282781.459, "dur": 146.259, + "args": { + "External id": 4050541,"Sequence number": 40618495, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "False", "False", "0", "", "8192"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [], [], [], [], []], "Ev Idx": 8452 + } + }, + { + "ph": "s", "id": 85, "pid": 1336756, "tid": 1336756, "ts": 1655274282781.459, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336756, "tid": 1336756, + "ts": 1655274282799.820, "dur": 9.710, + "args": { + "External id": 4050542,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[8388608, 2048, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [], [], [], [], []], "Ev Idx": 8453 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274282802.451, "dur": 6.591, + "args": { + "External id": 4050543,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "[8388608, 2048, 64, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8454 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunction", "pid": 1336756, "tid": 1336756, + "ts": 1655274282939.098, "dur": 148.549, + "args": { + "External id": 4050544,"Sequence number": 40618496, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "False", "False", "0", "", "8192"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [], [], [], [], []], "Ev Idx": 8455 + } + }, + { + "ph": "s", "id": 84, "pid": 1336756, "tid": 1336756, "ts": 1655274282939.098, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336756, "tid": 1336756, + "ts": 1655274282952.828, "dur": 6.605, + "args": { + "External id": 4050545,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[8388608, 2048, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [], [], [], [], []], "Ev Idx": 8456 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274282955.035, "dur": 4.030, + "args": { + "External id": 4050546,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "[8388608, 2048, 64, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8457 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "FlashAttnFunc", "pid": 1336756, "tid": 1336756, + "ts": 1655274283116.789, "dur": 165.788, + "args": { + "External id": 4050547,"Sequence number": 40618497, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "", "True", "", "0.", "", "False", "False", "True"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "", "Scalar", "", "Scalar", "", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], []], "Ev Idx": 8458 + } + }, + { + "ph": "s", "id": 83, "pid": 1336756, "tid": 1336756, "ts": 1655274283116.789, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 1336756, "tid": 1336756, + "ts": 1655274283142.383, "dur": 116.534, + "args": { + "External id": 4050548,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.125", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [], [], [], [], [], [], [], []], "Ev Idx": 8459 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336756, "tid": 1336756, + "ts": 1655274283185.779, "dur": 7.895, + "args": { + "External id": 4050549,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[8388608, 2048, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [], [], [], [], []], "Ev Idx": 8460 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274283188.219, "dur": 4.985, + "args": { + "External id": 4050550,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "[8388608, 2048, 64, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8461 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274283196.207, "dur": 4.099, + "args": { + "External id": 4050551,"Record function id": 0, "Concrete Inputs": ["[16, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8462 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274283201.404, "dur": 1.518, + "args": { + "External id": 4050552,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8463 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274283205.611, "dur": 3.098, + "args": { + "External id": 4050553,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8464 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::alias", "pid": 1336756, "tid": 1336756, + "ts": 1655274283269.608, "dur": 4.226, + "args": { + "External id": 4050554,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 64, 1]], "Input Dims": [[16, 4096, 32, 64]], "Ev Idx": 8465 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1336756, + "ts": 1655274283287.575, "dur": 5.581, + "args": { + "External id": 4050555,"Sequence number": 40618498, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[16, 4096, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 64, 1], []], "Input Dims": [[16, 4096, 32, 64], []], "Ev Idx": 8466 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274283289.023, "dur": 3.990, + "args": { + "External id": 4050556,"Sequence number": 40618498, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[16, 4096, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 64, 1], []], "Input Dims": [[16, 4096, 32, 64], []], "Ev Idx": 8467 + } + }, + { + "ph": "s", "id": 82, "pid": 1336756, "tid": 1336756, "ts": 1655274283289.023, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336756, "tid": 1336756, + "ts": 1655274283304.423, "dur": 106.102, + "args": { + "External id": 4050557,"Sequence number": 40618499, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[8388608, 2048, 1], [2048, 1], []], "Input Dims": [[16, 4096, 2048], [2048, 2048], []], "Ev Idx": 8468 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1336756, + "ts": 1655274283305.529, "dur": 11.213, + "args": { + "External id": 4050558,"Sequence number": 40618499, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 8469 + } + }, + { + "ph": "s", "id": 81, "pid": 1336756, "tid": 1336756, "ts": 1655274283305.529, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1336756, + "ts": 1655274283310.128, "dur": 5.516, + "args": { + "External id": 4050559,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[2048, 2048], [], []], "Ev Idx": 8470 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274283313.808, "dur": 1.579, + "args": { + "External id": 4050560,"Record function id": 0, "Concrete Inputs": ["", "[2048, 2048]", "[1, 2048]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[2048, 2048], [], [], []], "Ev Idx": 8471 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336756, "tid": 1336756, + "ts": 1655274283318.174, "dur": 92.022, + "args": { + "External id": 4050561,"Sequence number": 40618500, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[8388608, 2048, 1], [1, 2048]], "Input Dims": [[16, 4096, 2048], [2048, 2048]], "Ev Idx": 8472 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1336756, + "ts": 1655274283319.972, "dur": 2.967, + "args": { + "External id": 4050562,"Sequence number": 40618500, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[65536, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8473 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274283320.781, "dur": 2.000, + "args": { + "External id": 4050563,"Sequence number": 40618500, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[65536, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8474 + } + }, + { + "ph": "s", "id": 80, "pid": 1336756, "tid": 1336756, "ts": 1655274283320.781, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274283324.277, "dur": 78.345, + "args": { + "External id": 4050564,"Sequence number": 40618501, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048]], "Input Dims": [[65536, 2048], [2048, 2048]], "Ev Idx": 8475 + } + }, + { + "ph": "s", "id": 79, "pid": 1336756, "tid": 1336756, "ts": 1655274283324.277, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 1336756, "tid": 1336756, + "ts": 1655274283404.726, "dur": 4.721, + "args": { + "External id": 4050565,"Sequence number": 40618502, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 8476 + } + }, + { + "ph": "s", "id": 78, "pid": 1336756, "tid": 1336756, "ts": 1655274283404.726, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunction", "pid": 1336756, "tid": 1336756, + "ts": 1655274283463.056, "dur": 211.618, + "args": { + "External id": 4050566,"Sequence number": 40618503, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "9.9999999999999995e-07", "True", "False", "True"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 1], [1], [], [8388608, 2048, 1], [], [], [], []], "Input Dims": [[16, 4096, 2048], [2048], [], [16, 4096, 2048], [], [], [], []], "Ev Idx": 8477 + } + }, + { + "ph": "s", "id": 77, "pid": 1336756, "tid": 1336756, "ts": 1655274283463.056, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1336756, + "ts": 1655274283481.552, "dur": 3.635, + "args": { + "External id": 4050567,"Record function id": 0, "Concrete Inputs": ["", "[-1, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8478 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274283482.673, "dur": 2.218, + "args": { + "External id": 4050568,"Record function id": 0, "Concrete Inputs": ["", "[-1, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8479 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape_as", "pid": 1336756, "tid": 1336756, + "ts": 1655274283489.027, "dur": 4.995, + "args": { + "External id": 4050569,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[8388608, 2048, 1], [2048, 1]], "Input Dims": [[16, 4096, 2048], [65536, 2048]], "Ev Idx": 8480 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1336756, + "ts": 1655274283492.083, "dur": 1.833, + "args": { + "External id": 4050570,"Record function id": 0, "Concrete Inputs": ["", "[65536, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8481 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274283492.930, "dur": 0.872, + "args": { + "External id": 4050571,"Record function id": 0, "Concrete Inputs": ["", "[65536, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8482 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336756, "tid": 1336756, + "ts": 1655274283501.780, "dur": 7.525, + "args": { + "External id": 4050572,"Record function id": 0, "Concrete Inputs": ["", "15", "", "", "False", ""], "Input type": ["c10::BFloat16", "Scalar", "", "", "Scalar", ""], "Input Strides": [[2048, 1], [], [], [], [], []], "Input Dims": [[65536, 2048], [], [], [], [], []], "Ev Idx": 8483 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274283503.972, "dur": 5.029, + "args": { + "External id": 4050573,"Record function id": 0, "Concrete Inputs": ["[65536, 2048]", "[2048, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8484 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274283515.157, "dur": 3.664, + "args": { + "External id": 4050574,"Record function id": 0, "Concrete Inputs": ["[65536, 2048]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8485 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274283522.328, "dur": 2.885, + "args": { + "External id": 4050575,"Record function id": 0, "Concrete Inputs": ["[65536]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8486 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1336756, + "ts": 1655274283653.735, "dur": 3.055, + "args": { + "External id": 4050576,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 8487 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274283654.860, "dur": 1.770, + "args": { + "External id": 4050577,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 8488 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1336756, + "ts": 1655274283659.368, "dur": 1.849, + "args": { + "External id": 4050578,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 8489 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274283660.314, "dur": 0.798, + "args": { + "External id": 4050579,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 8490 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336756, "tid": 1336756, + "ts": 1655274283691.475, "dur": 95.016, + "args": { + "External id": 4050580,"Sequence number": 40618504, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[8388608, 2048, 1], [2048, 1], []], "Input Dims": [[16, 4096, 2048], [5632, 2048], []], "Ev Idx": 8491 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1336756, + "ts": 1655274283692.434, "dur": 9.202, + "args": { + "External id": 4050581,"Sequence number": 40618504, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 8492 + } + }, + { + "ph": "s", "id": 76, "pid": 1336756, "tid": 1336756, "ts": 1655274283692.434, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1336756, + "ts": 1655274283694.907, "dur": 5.625, + "args": { + "External id": 4050582,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[5632, 2048], [], []], "Ev Idx": 8493 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274283698.897, "dur": 1.335, + "args": { + "External id": 4050583,"Record function id": 0, "Concrete Inputs": ["", "[2048, 5632]", "[1, 2048]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[5632, 2048], [], [], []], "Ev Idx": 8494 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336756, "tid": 1336756, + "ts": 1655274283702.713, "dur": 83.403, + "args": { + "External id": 4050584,"Sequence number": 40618505, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[8388608, 2048, 1], [1, 2048]], "Input Dims": [[16, 4096, 2048], [2048, 5632]], "Ev Idx": 8495 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1336756, + "ts": 1655274283704.145, "dur": 3.298, + "args": { + "External id": 4050585,"Sequence number": 40618505, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[65536, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8496 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274283705.006, "dur": 2.299, + "args": { + "External id": 4050586,"Sequence number": 40618505, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[65536, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8497 + } + }, + { + "ph": "s", "id": 75, "pid": 1336756, "tid": 1336756, "ts": 1655274283705.006, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274283709.795, "dur": 69.174, + "args": { + "External id": 4050587,"Sequence number": 40618506, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048]], "Input Dims": [[65536, 2048], [2048, 5632]], "Ev Idx": 8498 + } + }, + { + "ph": "s", "id": 74, "pid": 1336756, "tid": 1336756, "ts": 1655274283709.795, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 1336756, "tid": 1336756, + "ts": 1655274283780.905, "dur": 4.550, + "args": { + "External id": 4050588,"Sequence number": 40618507, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 5632]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[5632, 1], []], "Input Dims": [[65536, 5632], []], "Ev Idx": 8499 + } + }, + { + "ph": "s", "id": 73, "pid": 1336756, "tid": 1336756, "ts": 1655274283780.905, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336756, "tid": 1336756, + "ts": 1655274283793.745, "dur": 73.277, + "args": { + "External id": 4050589,"Sequence number": 40618508, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[8388608, 2048, 1], [2048, 1], []], "Input Dims": [[16, 4096, 2048], [5632, 2048], []], "Ev Idx": 8500 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1336756, + "ts": 1655274283794.382, "dur": 14.433, + "args": { + "External id": 4050590,"Sequence number": 40618508, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 8501 + } + }, + { + "ph": "s", "id": 72, "pid": 1336756, "tid": 1336756, "ts": 1655274283794.382, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1336756, + "ts": 1655274283795.940, "dur": 11.757, + "args": { + "External id": 4050591,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[5632, 2048], [], []], "Ev Idx": 8502 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274283805.325, "dur": 2.144, + "args": { + "External id": 4050592,"Record function id": 0, "Concrete Inputs": ["", "[2048, 5632]", "[1, 2048]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[5632, 2048], [], [], []], "Ev Idx": 8503 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336756, "tid": 1336756, + "ts": 1655274283809.586, "dur": 57.169, + "args": { + "External id": 4050593,"Sequence number": 40618509, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[8388608, 2048, 1], [1, 2048]], "Input Dims": [[16, 4096, 2048], [2048, 5632]], "Ev Idx": 8504 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1336756, + "ts": 1655274283810.894, "dur": 3.681, + "args": { + "External id": 4050594,"Sequence number": 40618509, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[65536, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8505 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274283811.656, "dur": 2.793, + "args": { + "External id": 4050595,"Sequence number": 40618509, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[65536, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8506 + } + }, + { + "ph": "s", "id": 71, "pid": 1336756, "tid": 1336756, "ts": 1655274283811.656, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274283815.360, "dur": 45.919, + "args": { + "External id": 4050596,"Sequence number": 40618510, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048]], "Input Dims": [[65536, 2048], [2048, 5632]], "Ev Idx": 8507 + } + }, + { + "ph": "s", "id": 70, "pid": 1336756, "tid": 1336756, "ts": 1655274283815.360, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 1336756, "tid": 1336756, + "ts": 1655274283862.867, "dur": 3.543, + "args": { + "External id": 4050597,"Sequence number": 40618511, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 5632]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[5632, 1], []], "Input Dims": [[65536, 5632], []], "Ev Idx": 8508 + } + }, + { + "ph": "s", "id": 69, "pid": 1336756, "tid": 1336756, "ts": 1655274283862.867, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "SwiGLULinearFunction", "pid": 1336756, "tid": 1336756, + "ts": 1655274283885.783, "dur": 179.349, + "args": { + "External id": 4050598,"Sequence number": 40618512, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[23068672, 5632, 1], [23068672, 5632, 1], [5632, 1], []], "Input Dims": [[16, 4096, 5632], [16, 4096, 5632], [2048, 5632], []], "Ev Idx": 8509 + } + }, + { + "ph": "s", "id": 68, "pid": 1336756, "tid": 1336756, "ts": 1655274283885.783, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274283919.621, "dur": 3.836, + "args": { + "External id": 4050599,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 5632]", "15", "", "", "", "0"], "Input type": ["ScalarList", "Scalar", "", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8510 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336756, "tid": 1336756, + "ts": 1655274283952.805, "dur": 97.770, + "args": { + "External id": 4050600,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[23068672, 5632, 1], [5632, 1], []], "Input Dims": [[16, 4096, 5632], [2048, 5632], []], "Ev Idx": 8511 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1336756, + "ts": 1655274283953.646, "dur": 4.487, + "args": { + "External id": 4050601,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 8512 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1336756, + "ts": 1655274283954.935, "dur": 2.435, + "args": { + "External id": 4050602,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[5632, 1], [], []], "Input Dims": [[2048, 5632], [], []], "Ev Idx": 8513 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274283956.473, "dur": 0.731, + "args": { + "External id": 4050603,"Record function id": 0, "Concrete Inputs": ["", "[5632, 2048]", "[1, 5632]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[5632, 1], [], [], []], "Input Dims": [[2048, 5632], [], [], []], "Ev Idx": 8514 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336756, "tid": 1336756, + "ts": 1655274283959.115, "dur": 91.118, + "args": { + "External id": 4050604,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[23068672, 5632, 1], [1, 5632]], "Input Dims": [[16, 4096, 5632], [5632, 2048]], "Ev Idx": 8515 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1336756, + "ts": 1655274283960.472, "dur": 2.178, + "args": { + "External id": 4050605,"Record function id": 0, "Concrete Inputs": ["", "[65536, 5632]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[23068672, 5632, 1], []], "Input Dims": [[16, 4096, 5632], []], "Ev Idx": 8516 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274283961.360, "dur": 1.175, + "args": { + "External id": 4050606,"Record function id": 0, "Concrete Inputs": ["", "[65536, 5632]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[23068672, 5632, 1], []], "Input Dims": [[16, 4096, 5632], []], "Ev Idx": 8517 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274283963.382, "dur": 81.817, + "args": { + "External id": 4050607,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [1, 5632]], "Input Dims": [[65536, 5632], [5632, 2048]], "Ev Idx": 8518 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 1336756, "tid": 1336756, + "ts": 1655274284048.254, "dur": 1.378, + "args": { + "External id": 4050608,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 8519 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add", "pid": 1336756, "tid": 1336756, + "ts": 1655274284074.357, "dur": 25.492, + "args": { + "External id": 4050609,"Sequence number": 40618513, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[8388608, 2048, 1], [8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], [16, 4096, 2048], []], "Ev Idx": 8520 + } + }, + { + "ph": "s", "id": 67, "pid": 1336756, "tid": 1336756, "ts": 1655274284074.357, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunction", "pid": 1336756, "tid": 1336756, + "ts": 1655274284135.776, "dur": 181.803, + "args": { + "External id": 4050610,"Sequence number": 40618514, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "9.9999999999999995e-07", "False", "False", "True"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 1], [1], [], [], [], [], [], []], "Input Dims": [[16, 4096, 2048], [2048], [], [], [], [], [], []], "Ev Idx": 8521 + } + }, + { + "ph": "s", "id": 66, "pid": 1336756, "tid": 1336756, "ts": 1655274284135.776, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1336756, + "ts": 1655274284153.750, "dur": 3.095, + "args": { + "External id": 4050611,"Record function id": 0, "Concrete Inputs": ["", "[-1, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8522 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274284154.595, "dur": 2.122, + "args": { + "External id": 4050612,"Record function id": 0, "Concrete Inputs": ["", "[-1, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8523 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336756, "tid": 1336756, + "ts": 1655274284164.237, "dur": 6.394, + "args": { + "External id": 4050613,"Record function id": 0, "Concrete Inputs": ["", "15", "", "", "False", ""], "Input type": ["c10::BFloat16", "Scalar", "", "", "Scalar", ""], "Input Strides": [[2048, 1], [], [], [], [], []], "Input Dims": [[65536, 2048], [], [], [], [], []], "Ev Idx": 8524 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274284166.447, "dur": 3.748, + "args": { + "External id": 4050614,"Record function id": 0, "Concrete Inputs": ["[65536, 2048]", "[2048, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8525 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274284176.567, "dur": 3.634, + "args": { + "External id": 4050615,"Record function id": 0, "Concrete Inputs": ["[65536]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8526 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1336756, + "ts": 1655274284298.883, "dur": 9.186, + "args": { + "External id": 4050616,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 8527 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274284303.540, "dur": 4.296, + "args": { + "External id": 4050617,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 8528 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336756, "tid": 1336756, + "ts": 1655274284335.366, "dur": 107.462, + "args": { + "External id": 4050618,"Sequence number": 40618515, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[8388608, 2048, 1], [2048, 1], []], "Input Dims": [[16, 4096, 2048], [2048, 2048], []], "Ev Idx": 8529 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1336756, + "ts": 1655274284336.363, "dur": 8.038, + "args": { + "External id": 4050619,"Sequence number": 40618515, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 8530 + } + }, + { + "ph": "s", "id": 65, "pid": 1336756, "tid": 1336756, "ts": 1655274284336.363, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1336756, + "ts": 1655274284338.119, "dur": 5.246, + "args": { + "External id": 4050620,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[2048, 2048], [], []], "Ev Idx": 8531 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274284341.844, "dur": 1.332, + "args": { + "External id": 4050621,"Record function id": 0, "Concrete Inputs": ["", "[2048, 2048]", "[1, 2048]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[2048, 2048], [], [], []], "Ev Idx": 8532 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336756, "tid": 1336756, + "ts": 1655274284345.792, "dur": 96.702, + "args": { + "External id": 4050622,"Sequence number": 40618516, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[8388608, 2048, 1], [1, 2048]], "Input Dims": [[16, 4096, 2048], [2048, 2048]], "Ev Idx": 8533 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1336756, + "ts": 1655274284347.249, "dur": 3.576, + "args": { + "External id": 4050623,"Sequence number": 40618516, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[65536, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8534 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274284348.076, "dur": 2.574, + "args": { + "External id": 4050624,"Sequence number": 40618516, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[65536, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8535 + } + }, + { + "ph": "s", "id": 64, "pid": 1336756, "tid": 1336756, "ts": 1655274284348.076, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274284351.491, "dur": 84.216, + "args": { + "External id": 4050625,"Sequence number": 40618517, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048]], "Input Dims": [[65536, 2048], [2048, 2048]], "Ev Idx": 8536 + } + }, + { + "ph": "s", "id": 63, "pid": 1336756, "tid": 1336756, "ts": 1655274284351.491, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 1336756, "tid": 1336756, + "ts": 1655274284438.938, "dur": 2.871, + "args": { + "External id": 4050626,"Sequence number": 40618518, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 8537 + } + }, + { + "ph": "s", "id": 62, "pid": 1336756, "tid": 1336756, "ts": 1655274284438.938, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336756, "tid": 1336756, + "ts": 1655274284452.455, "dur": 67.951, + "args": { + "External id": 4050627,"Sequence number": 40618519, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[8388608, 2048, 1], [2048, 1], []], "Input Dims": [[16, 4096, 2048], [2048, 2048], []], "Ev Idx": 8538 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1336756, + "ts": 1655274284453.135, "dur": 5.283, + "args": { + "External id": 4050628,"Sequence number": 40618519, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 8539 + } + }, + { + "ph": "s", "id": 61, "pid": 1336756, "tid": 1336756, "ts": 1655274284453.135, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1336756, + "ts": 1655274284454.469, "dur": 2.977, + "args": { + "External id": 4050629,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[2048, 2048], [], []], "Ev Idx": 8540 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274284456.299, "dur": 0.938, + "args": { + "External id": 4050630,"Record function id": 0, "Concrete Inputs": ["", "[2048, 2048]", "[1, 2048]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[2048, 2048], [], [], []], "Ev Idx": 8541 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336756, "tid": 1336756, + "ts": 1655274284460.765, "dur": 59.298, + "args": { + "External id": 4050631,"Sequence number": 40618520, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[8388608, 2048, 1], [1, 2048]], "Input Dims": [[16, 4096, 2048], [2048, 2048]], "Ev Idx": 8542 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1336756, + "ts": 1655274284462.144, "dur": 4.967, + "args": { + "External id": 4050632,"Sequence number": 40618520, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[65536, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8543 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274284462.866, "dur": 4.117, + "args": { + "External id": 4050633,"Sequence number": 40618520, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[65536, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8544 + } + }, + { + "ph": "s", "id": 60, "pid": 1336756, "tid": 1336756, "ts": 1655274284462.866, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274284467.599, "dur": 46.307, + "args": { + "External id": 4050634,"Sequence number": 40618521, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048]], "Input Dims": [[65536, 2048], [2048, 2048]], "Ev Idx": 8545 + } + }, + { + "ph": "s", "id": 59, "pid": 1336756, "tid": 1336756, "ts": 1655274284467.599, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 1336756, "tid": 1336756, + "ts": 1655274284515.638, "dur": 4.117, + "args": { + "External id": 4050635,"Sequence number": 40618522, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 8546 + } + }, + { + "ph": "s", "id": 58, "pid": 1336756, "tid": 1336756, "ts": 1655274284515.638, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336756, "tid": 1336756, + "ts": 1655274284526.313, "dur": 60.915, + "args": { + "External id": 4050636,"Sequence number": 40618523, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[8388608, 2048, 1], [2048, 1], []], "Input Dims": [[16, 4096, 2048], [2048, 2048], []], "Ev Idx": 8547 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1336756, + "ts": 1655274284526.990, "dur": 10.098, + "args": { + "External id": 4050637,"Sequence number": 40618523, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 8548 + } + }, + { + "ph": "s", "id": 57, "pid": 1336756, "tid": 1336756, "ts": 1655274284526.990, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1336756, + "ts": 1655274284531.989, "dur": 4.156, + "args": { + "External id": 4050638,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[2048, 2048], [], []], "Ev Idx": 8549 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274284535.262, "dur": 0.744, + "args": { + "External id": 4050639,"Record function id": 0, "Concrete Inputs": ["", "[2048, 2048]", "[1, 2048]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[2048, 2048], [], [], []], "Ev Idx": 8550 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336756, "tid": 1336756, + "ts": 1655274284538.107, "dur": 48.812, + "args": { + "External id": 4050640,"Sequence number": 40618524, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[8388608, 2048, 1], [1, 2048]], "Input Dims": [[16, 4096, 2048], [2048, 2048]], "Ev Idx": 8551 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1336756, + "ts": 1655274284540.626, "dur": 3.354, + "args": { + "External id": 4050641,"Sequence number": 40618524, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[65536, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8552 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274284541.542, "dur": 2.181, + "args": { + "External id": 4050642,"Sequence number": 40618524, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[65536, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8553 + } + }, + { + "ph": "s", "id": 56, "pid": 1336756, "tid": 1336756, "ts": 1655274284541.542, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274284544.417, "dur": 37.313, + "args": { + "External id": 4050643,"Sequence number": 40618525, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048]], "Input Dims": [[65536, 2048], [2048, 2048]], "Ev Idx": 8554 + } + }, + { + "ph": "s", "id": 55, "pid": 1336756, "tid": 1336756, "ts": 1655274284544.417, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 1336756, "tid": 1336756, + "ts": 1655274284583.148, "dur": 3.480, + "args": { + "External id": 4050644,"Sequence number": 40618526, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 8555 + } + }, + { + "ph": "s", "id": 54, "pid": 1336756, "tid": 1336756, "ts": 1655274284583.148, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1336756, + "ts": 1655274284604.337, "dur": 3.307, + "args": { + "External id": 4050645,"Sequence number": 40618527, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 32, 64]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8556 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274284605.169, "dur": 2.336, + "args": { + "External id": 4050646,"Sequence number": 40618527, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 32, 64]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8557 + } + }, + { + "ph": "s", "id": 53, "pid": 1336756, "tid": 1336756, "ts": 1655274284605.169, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1336756, + "ts": 1655274284614.125, "dur": 2.725, + "args": { + "External id": 4050647,"Sequence number": 40618528, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 32, 64]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8558 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274284615.110, "dur": 1.603, + "args": { + "External id": 4050648,"Sequence number": 40618528, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 32, 64]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8559 + } + }, + { + "ph": "s", "id": 52, "pid": 1336756, "tid": 1336756, "ts": 1655274284615.110, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1336756, + "ts": 1655274284620.932, "dur": 4.499, + "args": { + "External id": 4050649,"Sequence number": 40618529, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 32, 64]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8560 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274284623.537, "dur": 1.757, + "args": { + "External id": 4050650,"Sequence number": 40618529, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 32, 64]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8561 + } + }, + { + "ph": "s", "id": 51, "pid": 1336756, "tid": 1336756, "ts": 1655274284623.537, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunction", "pid": 1336756, "tid": 1336756, + "ts": 1655274284653.924, "dur": 146.514, + "args": { + "External id": 4050651,"Sequence number": 40618530, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "False", "False", "0", "", "8192"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [], [], [], [], []], "Ev Idx": 8562 + } + }, + { + "ph": "s", "id": 50, "pid": 1336756, "tid": 1336756, "ts": 1655274284653.924, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336756, "tid": 1336756, + "ts": 1655274284672.428, "dur": 7.881, + "args": { + "External id": 4050652,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[8388608, 2048, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [], [], [], [], []], "Ev Idx": 8563 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274284674.867, "dur": 4.953, + "args": { + "External id": 4050653,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "[8388608, 2048, 64, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8564 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunction", "pid": 1336756, "tid": 1336756, + "ts": 1655274284812.122, "dur": 98.635, + "args": { + "External id": 4050654,"Sequence number": 40618531, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "False", "False", "0", "", "8192"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [32, 1], [32, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [8192, 32], [8192, 32], [], [], [], [], []], "Ev Idx": 8565 + } + }, + { + "ph": "s", "id": 49, "pid": 1336756, "tid": 1336756, "ts": 1655274284812.122, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336756, "tid": 1336756, + "ts": 1655274284825.075, "dur": 6.381, + "args": { + "External id": 4050655,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[8388608, 2048, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [], [], [], [], []], "Ev Idx": 8566 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274284827.305, "dur": 3.770, + "args": { + "External id": 4050656,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "[8388608, 2048, 64, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8567 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "FlashAttnFunc", "pid": 1336756, "tid": 1336756, + "ts": 1655274284937.872, "dur": 212.686, + "args": { + "External id": 4050657,"Sequence number": 40618532, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "", "True", "", "0.", "", "False", "False", "True"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "", "Scalar", "", "Scalar", "", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [], [], [], [], [], [], [], [], []], "Ev Idx": 8568 + } + }, + { + "ph": "s", "id": 48, "pid": 1336756, "tid": 1336756, "ts": 1655274284937.872, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 1336756, "tid": 1336756, + "ts": 1655274284962.778, "dur": 162.929, + "args": { + "External id": 4050658,"Record function id": 0, "Concrete Inputs": ["", "", "", "0.", "0.125", "True", "-1", "-1", "0.", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [8388608, 2048, 64, 1], [], [], [], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [16, 4096, 32, 64], [16, 4096, 32, 64], [], [], [], [], [], [], [], []], "Ev Idx": 8569 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336756, "tid": 1336756, + "ts": 1655274285049.734, "dur": 7.971, + "args": { + "External id": 4050659,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", ""], "Input type": ["c10::BFloat16", "", "", "", "", ""], "Input Strides": [[8388608, 2048, 64, 1], [], [], [], [], []], "Input Dims": [[16, 4096, 32, 64], [], [], [], [], []], "Ev Idx": 8570 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274285052.213, "dur": 4.926, + "args": { + "External id": 4050660,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 32, 64]", "[8388608, 2048, 64, 1]", "15", "0", "", ""], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8571 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274285061.601, "dur": 3.613, + "args": { + "External id": 4050661,"Record function id": 0, "Concrete Inputs": ["[16, 32, 4096]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8572 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274285066.565, "dur": 1.440, + "args": { + "External id": 4050662,"Record function id": 0, "Concrete Inputs": ["[0]", "15", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8573 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274285070.374, "dur": 4.426, + "args": { + "External id": 4050663,"Record function id": 0, "Concrete Inputs": ["[2]", "4", "", "", "", ""], "Input type": ["ScalarList", "Scalar", "", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8574 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::alias", "pid": 1336756, "tid": 1336756, + "ts": 1655274285136.813, "dur": 4.424, + "args": { + "External id": 4050664,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[8388608, 2048, 64, 1]], "Input Dims": [[16, 4096, 32, 64]], "Ev Idx": 8575 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1336756, + "ts": 1655274285155.356, "dur": 5.821, + "args": { + "External id": 4050665,"Sequence number": 40618533, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[16, 4096, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 64, 1], []], "Input Dims": [[16, 4096, 32, 64], []], "Ev Idx": 8576 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274285156.785, "dur": 4.233, + "args": { + "External id": 4050666,"Sequence number": 40618533, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[16, 4096, -1]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 64, 1], []], "Input Dims": [[16, 4096, 32, 64], []], "Ev Idx": 8577 + } + }, + { + "ph": "s", "id": 47, "pid": 1336756, "tid": 1336756, "ts": 1655274285156.785, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336756, "tid": 1336756, + "ts": 1655274285171.969, "dur": 96.261, + "args": { + "External id": 4050667,"Sequence number": 40618534, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[8388608, 2048, 1], [2048, 1], []], "Input Dims": [[16, 4096, 2048], [2048, 2048], []], "Ev Idx": 8578 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1336756, + "ts": 1655274285173.115, "dur": 8.040, + "args": { + "External id": 4050668,"Sequence number": 40618534, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[2048, 2048]], "Ev Idx": 8579 + } + }, + { + "ph": "s", "id": 46, "pid": 1336756, "tid": 1336756, "ts": 1655274285173.115, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1336756, + "ts": 1655274285176.321, "dur": 3.836, + "args": { + "External id": 4050669,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[2048, 2048], [], []], "Ev Idx": 8580 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274285178.536, "dur": 1.386, + "args": { + "External id": 4050670,"Record function id": 0, "Concrete Inputs": ["", "[2048, 2048]", "[1, 2048]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[2048, 2048], [], [], []], "Ev Idx": 8581 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336756, "tid": 1336756, + "ts": 1655274285182.456, "dur": 85.402, + "args": { + "External id": 4050671,"Sequence number": 40618535, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[8388608, 2048, 1], [1, 2048]], "Input Dims": [[16, 4096, 2048], [2048, 2048]], "Ev Idx": 8582 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1336756, + "ts": 1655274285184.388, "dur": 4.704, + "args": { + "External id": 4050672,"Sequence number": 40618535, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[65536, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8583 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274285187.203, "dur": 1.744, + "args": { + "External id": 4050673,"Sequence number": 40618535, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[65536, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8584 + } + }, + { + "ph": "s", "id": 45, "pid": 1336756, "tid": 1336756, "ts": 1655274285187.203, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274285190.220, "dur": 71.377, + "args": { + "External id": 4050674,"Sequence number": 40618536, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048]], "Input Dims": [[65536, 2048], [2048, 2048]], "Ev Idx": 8585 + } + }, + { + "ph": "s", "id": 44, "pid": 1336756, "tid": 1336756, "ts": 1655274285190.220, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 1336756, "tid": 1336756, + "ts": 1655274285263.763, "dur": 3.402, + "args": { + "External id": 4050675,"Sequence number": 40618537, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 8586 + } + }, + { + "ph": "s", "id": 43, "pid": 1336756, "tid": 1336756, "ts": 1655274285263.763, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunction", "pid": 1336756, "tid": 1336756, + "ts": 1655274285299.542, "dur": 213.788, + "args": { + "External id": 4050676,"Sequence number": 40618538, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "9.9999999999999995e-07", "True", "False", "True"], "Input type": ["c10::BFloat16", "c10::BFloat16", "", "c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8388608, 2048, 1], [1], [], [8388608, 2048, 1], [], [], [], []], "Input Dims": [[16, 4096, 2048], [2048], [], [16, 4096, 2048], [], [], [], []], "Ev Idx": 8587 + } + }, + { + "ph": "s", "id": 42, "pid": 1336756, "tid": 1336756, "ts": 1655274285299.542, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1336756, + "ts": 1655274285315.925, "dur": 3.949, + "args": { + "External id": 4050677,"Record function id": 0, "Concrete Inputs": ["", "[-1, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8588 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274285318.306, "dur": 1.435, + "args": { + "External id": 4050678,"Record function id": 0, "Concrete Inputs": ["", "[-1, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8589 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape_as", "pid": 1336756, "tid": 1336756, + "ts": 1655274285323.262, "dur": 3.659, + "args": { + "External id": 4050679,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[8388608, 2048, 1], [2048, 1]], "Input Dims": [[16, 4096, 2048], [65536, 2048]], "Ev Idx": 8590 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1336756, + "ts": 1655274285324.531, "dur": 2.276, + "args": { + "External id": 4050680,"Record function id": 0, "Concrete Inputs": ["", "[65536, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8591 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274285325.554, "dur": 1.133, + "args": { + "External id": 4050681,"Record function id": 0, "Concrete Inputs": ["", "[65536, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8592 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336756, "tid": 1336756, + "ts": 1655274285333.795, "dur": 6.320, + "args": { + "External id": 4050682,"Record function id": 0, "Concrete Inputs": ["", "15", "", "", "False", ""], "Input type": ["c10::BFloat16", "Scalar", "", "", "Scalar", ""], "Input Strides": [[2048, 1], [], [], [], [], []], "Input Dims": [[65536, 2048], [], [], [], [], []], "Ev Idx": 8593 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274285335.619, "dur": 4.184, + "args": { + "External id": 4050683,"Record function id": 0, "Concrete Inputs": ["[65536, 2048]", "[2048, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8594 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274285347.382, "dur": 2.487, + "args": { + "External id": 4050684,"Record function id": 0, "Concrete Inputs": ["[65536, 2048]", "15", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8595 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274285353.285, "dur": 2.300, + "args": { + "External id": 4050685,"Record function id": 0, "Concrete Inputs": ["[65536]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8596 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1336756, + "ts": 1655274285490.532, "dur": 5.726, + "args": { + "External id": 4050686,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 8597 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274285491.563, "dur": 4.386, + "args": { + "External id": 4050687,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 8598 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1336756, + "ts": 1655274285499.166, "dur": 2.362, + "args": { + "External id": 4050688,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 8599 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274285500.148, "dur": 1.276, + "args": { + "External id": 4050689,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 8600 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336756, "tid": 1336756, + "ts": 1655274285531.671, "dur": 93.207, + "args": { + "External id": 4050690,"Sequence number": 40618539, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[8388608, 2048, 1], [2048, 1], []], "Input Dims": [[16, 4096, 2048], [5632, 2048], []], "Ev Idx": 8601 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1336756, + "ts": 1655274285532.654, "dur": 8.012, + "args": { + "External id": 4050691,"Sequence number": 40618539, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 8602 + } + }, + { + "ph": "s", "id": 41, "pid": 1336756, "tid": 1336756, "ts": 1655274285532.654, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1336756, + "ts": 1655274285536.252, "dur": 3.399, + "args": { + "External id": 4050692,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[5632, 2048], [], []], "Ev Idx": 8603 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274285538.248, "dur": 1.220, + "args": { + "External id": 4050693,"Record function id": 0, "Concrete Inputs": ["", "[2048, 5632]", "[1, 2048]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[5632, 2048], [], [], []], "Ev Idx": 8604 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336756, "tid": 1336756, + "ts": 1655274285541.983, "dur": 82.600, + "args": { + "External id": 4050694,"Sequence number": 40618540, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[8388608, 2048, 1], [1, 2048]], "Input Dims": [[16, 4096, 2048], [2048, 5632]], "Ev Idx": 8605 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1336756, + "ts": 1655274285543.477, "dur": 7.118, + "args": { + "External id": 4050695,"Sequence number": 40618540, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[65536, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8606 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274285546.231, "dur": 4.237, + "args": { + "External id": 4050696,"Sequence number": 40618540, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[65536, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8607 + } + }, + { + "ph": "s", "id": 40, "pid": 1336756, "tid": 1336756, "ts": 1655274285546.231, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274285551.735, "dur": 67.332, + "args": { + "External id": 4050697,"Sequence number": 40618541, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048]], "Input Dims": [[65536, 2048], [2048, 5632]], "Ev Idx": 8608 + } + }, + { + "ph": "s", "id": 39, "pid": 1336756, "tid": 1336756, "ts": 1655274285551.735, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 1336756, "tid": 1336756, + "ts": 1655274285621.233, "dur": 2.745, + "args": { + "External id": 4050698,"Sequence number": 40618542, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 5632]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[5632, 1], []], "Input Dims": [[65536, 5632], []], "Ev Idx": 8609 + } + }, + { + "ph": "s", "id": 38, "pid": 1336756, "tid": 1336756, "ts": 1655274285621.233, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336756, "tid": 1336756, + "ts": 1655274285632.073, "dur": 70.596, + "args": { + "External id": 4050699,"Sequence number": 40618543, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[8388608, 2048, 1], [2048, 1], []], "Input Dims": [[16, 4096, 2048], [5632, 2048], []], "Ev Idx": 8610 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1336756, + "ts": 1655274285632.854, "dur": 9.524, + "args": { + "External id": 4050700,"Sequence number": 40618543, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[5632, 2048]], "Ev Idx": 8611 + } + }, + { + "ph": "s", "id": 37, "pid": 1336756, "tid": 1336756, "ts": 1655274285632.854, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1336756, + "ts": 1655274285636.890, "dur": 4.326, + "args": { + "External id": 4050701,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[5632, 2048], [], []], "Ev Idx": 8612 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274285640.252, "dur": 0.816, + "args": { + "External id": 4050702,"Record function id": 0, "Concrete Inputs": ["", "[2048, 5632]", "[1, 2048]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[5632, 2048], [], [], []], "Ev Idx": 8613 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336756, "tid": 1336756, + "ts": 1655274285643.489, "dur": 58.869, + "args": { + "External id": 4050703,"Sequence number": 40618544, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[8388608, 2048, 1], [1, 2048]], "Input Dims": [[16, 4096, 2048], [2048, 5632]], "Ev Idx": 8614 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1336756, + "ts": 1655274285644.612, "dur": 6.177, + "args": { + "External id": 4050704,"Sequence number": 40618544, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[65536, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8615 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274285646.026, "dur": 4.635, + "args": { + "External id": 4050705,"Sequence number": 40618544, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[65536, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8616 + } + }, + { + "ph": "s", "id": 36, "pid": 1336756, "tid": 1336756, "ts": 1655274285646.026, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274285651.635, "dur": 44.823, + "args": { + "External id": 4050706,"Sequence number": 40618545, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048]], "Input Dims": [[65536, 2048], [2048, 5632]], "Ev Idx": 8617 + } + }, + { + "ph": "s", "id": 35, "pid": 1336756, "tid": 1336756, "ts": 1655274285651.635, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 1336756, "tid": 1336756, + "ts": 1655274285698.329, "dur": 3.699, + "args": { + "External id": 4050707,"Sequence number": 40618546, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 5632]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[5632, 1], []], "Input Dims": [[65536, 5632], []], "Ev Idx": 8618 + } + }, + { + "ph": "s", "id": 34, "pid": 1336756, "tid": 1336756, "ts": 1655274285698.329, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "SwiGLULinearFunction", "pid": 1336756, "tid": 1336756, + "ts": 1655274285721.315, "dur": 135.474, + "args": { + "External id": 4050708,"Sequence number": 40618547, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[23068672, 5632, 1], [23068672, 5632, 1], [5632, 1], []], "Input Dims": [[16, 4096, 5632], [16, 4096, 5632], [2048, 5632], []], "Ev Idx": 8619 + } + }, + { + "ph": "s", "id": 33, "pid": 1336756, "tid": 1336756, "ts": 1655274285721.315, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274285757.185, "dur": 4.539, + "args": { + "External id": 4050709,"Record function id": 0, "Concrete Inputs": ["[16, 4096, 5632]", "15", "", "", "", "0"], "Input type": ["ScalarList", "Scalar", "", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8620 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336756, "tid": 1336756, + "ts": 1655274285790.962, "dur": 54.066, + "args": { + "External id": 4050710,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[23068672, 5632, 1], [5632, 1], []], "Input Dims": [[16, 4096, 5632], [2048, 5632], []], "Ev Idx": 8621 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1336756, + "ts": 1655274285791.716, "dur": 4.213, + "args": { + "External id": 4050711,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[5632, 1]], "Input Dims": [[2048, 5632]], "Ev Idx": 8622 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1336756, + "ts": 1655274285792.770, "dur": 2.401, + "args": { + "External id": 4050712,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[5632, 1], [], []], "Input Dims": [[2048, 5632], [], []], "Ev Idx": 8623 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274285794.216, "dur": 0.786, + "args": { + "External id": 4050713,"Record function id": 0, "Concrete Inputs": ["", "[5632, 2048]", "[1, 5632]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[5632, 1], [], [], []], "Input Dims": [[2048, 5632], [], [], []], "Ev Idx": 8624 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336756, "tid": 1336756, + "ts": 1655274285796.823, "dur": 47.936, + "args": { + "External id": 4050714,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[23068672, 5632, 1], [1, 5632]], "Input Dims": [[16, 4096, 5632], [5632, 2048]], "Ev Idx": 8625 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1336756, + "ts": 1655274285798.184, "dur": 3.169, + "args": { + "External id": 4050715,"Record function id": 0, "Concrete Inputs": ["", "[65536, 5632]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[23068672, 5632, 1], []], "Input Dims": [[16, 4096, 5632], []], "Ev Idx": 8626 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274285800.275, "dur": 0.965, + "args": { + "External id": 4050716,"Record function id": 0, "Concrete Inputs": ["", "[65536, 5632]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[23068672, 5632, 1], []], "Input Dims": [[16, 4096, 5632], []], "Ev Idx": 8627 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274285801.846, "dur": 39.213, + "args": { + "External id": 4050717,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[5632, 1], [1, 5632]], "Input Dims": [[65536, 5632], [5632, 2048]], "Ev Idx": 8628 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 1336756, "tid": 1336756, + "ts": 1655274285843.028, "dur": 1.138, + "args": { + "External id": 4050718,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 8629 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add", "pid": 1336756, "tid": 1336756, + "ts": 1655274285864.951, "dur": 22.230, + "args": { + "External id": 4050719,"Sequence number": 40618548, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[8388608, 2048, 1], [8388608, 2048, 1], []], "Input Dims": [[16, 4096, 2048], [16, 4096, 2048], []], "Ev Idx": 8630 + } + }, + { + "ph": "s", "id": 32, "pid": 1336756, "tid": 1336756, "ts": 1655274285864.951, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::stack", "pid": 1336756, "tid": 1336756, + "ts": 1655274285903.243, "dur": 37.263, + "args": { + "External id": 4050720,"Sequence number": 40618549, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "-2"], "Input type": ["TensorList", "Scalar"], "Input Strides": [[[8388608, 2048, 1], [8388608, 2048, 1], [8388608, 2048, 1], [8388608, 2048, 1]], []], "Input Dims": [[[16, 4096, 2048], [16, 4096, 2048], [16, 4096, 2048], [16, 4096, 2048]], []], "Ev Idx": 8631 + } + }, + { + "ph": "s", "id": 31, "pid": 1336756, "tid": 1336756, "ts": 1655274285903.243, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::cat", "pid": 1336756, "tid": 1336756, + "ts": 1655274285911.226, "dur": 25.313, + "args": { + "External id": 4050721,"Record function id": 0, "Concrete Inputs": ["", "2"], "Input type": ["TensorList", "Scalar"], "Input Strides": [[[8388608, 2048, 1], [8388608, 2048, 1], [8388608, 2048, 1], [8388608, 2048, 1]], []], "Input Dims": [[[16, 4096, 2048], [16, 4096, 2048], [16, 4096, 2048], [16, 4096, 2048]], []], "Ev Idx": 8632 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274285937.837, "dur": 1.229, + "args": { + "External id": 4050722,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 4, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[33554432, 8192, 1], []], "Input Dims": [[16, 4096, 8192], []], "Ev Idx": 8633 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TorchDynamo Cache Lookup", "pid": 1336756, "tid": 1336756, + "ts": 1655274285971.720, "dur": 73.749, + "args": { + "External id": 4050723,"Record function id": 0, "Ev Idx": 8634 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 2/0", "pid": 1336756, "tid": 1336756, + "ts": 1655274286047.713, "dur": 176.714, + "args": { + "External id": 4050724,"Record function id": 0, "Ev Idx": 8635 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 1336756, "tid": 1336756, + "ts": 1655274286081.311, "dur": 134.882, + "args": { + "External id": 4050725,"Sequence number": 40618550, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1], [33554432, 8192, 2048, 1]], "Input Dims": [[2048], [16, 4096, 4, 2048]], "Ev Idx": 8636 + } + }, + { + "ph": "s", "id": 30, "pid": 1336756, "tid": 1336756, "ts": 1655274286081.311, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 1336756, "tid": 1336756, + "ts": 1655274286144.344, "dur": 34.599, + "args": { + "External id": 4050726,"kernel_hash": "cd26ogptnjelaibpl2zumx5nxdttspqepvjkh7lpmsxbzrrexbxm", "Record function id": 0, "stream": 0, "Concrete Inputs": ["", "", "", "", "2048", "1", "9.9999999999999995e-07", "True", "2048", "False", "False", "True", "False"], "kernel_file": "/tmp/torchinductor_cvm/d2/cd26ogptnjelaibpl2zumx5nxdttspqepvjkh7lpmsxbzrrexbxm.py", "kernel_backend": "triton", "Input type": ["c10::BFloat16", "c10::BFloat16", "c10::BFloat16", "float", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], [1], [1], [], [], [], [], [], [], [], [], []], "Input Dims": [[262144, 2048], [262144, 2048], [2048], [262144], [], [], [], [], [], [], [], [], []], "Ev Idx": 8637 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros", "pid": 1336756, "tid": 1336756, + "ts": 1655274286302.794, "dur": 35.846, + "args": { + "External id": 4050727,"Record function id": 0, "Concrete Inputs": ["[1]", "", "", "", "False"], "Input type": ["ScalarList", "", "", "", "Scalar"], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 8638 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274286305.737, "dur": 5.471, + "args": { + "External id": 4050728,"Record function id": 0, "Concrete Inputs": ["[1]", "", "", "", "False", ""], "Input type": ["ScalarList", "", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8639 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 1336756, "tid": 1336756, + "ts": 1655274286314.096, "dur": 24.194, + "args": { + "External id": 4050729,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[1]], "Ev Idx": 8640 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 1336756, "tid": 1336756, + "ts": 1655274286317.018, "dur": 20.792, + "args": { + "External id": 4050730,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[1], []], "Ev Idx": 8641 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros", "pid": 1336756, "tid": 1336756, + "ts": 1655274286343.008, "dur": 20.061, + "args": { + "External id": 4050731,"Record function id": 0, "Concrete Inputs": ["[1]", "", "", "", "False"], "Input type": ["ScalarList", "", "", "", "Scalar"], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 8642 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274286343.816, "dur": 2.684, + "args": { + "External id": 4050732,"Record function id": 0, "Concrete Inputs": ["[1]", "", "", "", "False", ""], "Input type": ["ScalarList", "", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8643 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 1336756, "tid": 1336756, + "ts": 1655274286347.055, "dur": 15.712, + "args": { + "External id": 4050733,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[1]], "Ev Idx": 8644 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 1336756, "tid": 1336756, + "ts": 1655274286349.522, "dur": 12.824, + "args": { + "External id": 4050734,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[1], []], "Ev Idx": 8645 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros", "pid": 1336756, "tid": 1336756, + "ts": 1655274286365.782, "dur": 14.353, + "args": { + "External id": 4050735,"Record function id": 0, "Concrete Inputs": ["[1]", "", "", "", "False"], "Input type": ["ScalarList", "", "", "", "Scalar"], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 8646 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274286366.740, "dur": 2.254, + "args": { + "External id": 4050736,"Record function id": 0, "Concrete Inputs": ["[1]", "", "", "", "False", ""], "Input type": ["ScalarList", "", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8647 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 1336756, "tid": 1336756, + "ts": 1655274286369.686, "dur": 10.185, + "args": { + "External id": 4050737,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[1]], "Ev Idx": 8648 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 1336756, "tid": 1336756, + "ts": 1655274286370.416, "dur": 9.102, + "args": { + "External id": 4050738,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[1], []], "Ev Idx": 8649 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655274286388.224, "dur": 0.638, + "args": { + "External id": 4050739,"Sequence number": 40618551, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "4", "0", "", "", "False", "False", ""], "Input type": ["long int", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[8192, 1], [], [], [], [], [], [], []], "Input Dims": [[16, 8192], [], [], [], [], [], [], []], "Ev Idx": 8650 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unfold", "pid": 1336756, "tid": 1336756, + "ts": 1655274286396.327, "dur": 9.730, + "args": { + "External id": 4050740,"Sequence number": 40618551, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "1", "5", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8192, 1], [], [], []], "Input Dims": [[16, 8192], [], [], []], "Ev Idx": 8651 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274286402.522, "dur": 2.007, + "args": { + "External id": 4050741,"Record function id": 0, "Concrete Inputs": ["", "[16, 8188, 5]", "[8192, 1, 1]", ""], "Input type": ["long int", "ScalarList", "ScalarList", ""], "Input Strides": [[8192, 1], [], [], []], "Input Dims": [[16, 8192], [], [], []], "Ev Idx": 8652 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1336756, + "ts": 1655274286412.174, "dur": 24.243, + "args": { + "External id": 4050742,"Sequence number": 40618551, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "0", "0", "9223372036854775807", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 1], [], [], [], []], "Input Dims": [[16, 8188, 5], [], [], [], []], "Ev Idx": 8653 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274286433.102, "dur": 1.230, + "args": { + "External id": 4050743,"Record function id": 0, "Concrete Inputs": ["", "[16, 8188, 5]", "[8192, 1, 1]", "0"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[8192, 1, 1], [], [], []], "Input Dims": [[16, 8188, 5], [], [], []], "Ev Idx": 8654 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1336756, + "ts": 1655274286438.227, "dur": 3.915, + "args": { + "External id": 4050744,"Sequence number": 40618551, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "1", "0", "9223372036854775807", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 1], [], [], [], []], "Input Dims": [[16, 8188, 5], [], [], [], []], "Ev Idx": 8655 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274286440.655, "dur": 0.836, + "args": { + "External id": 4050745,"Record function id": 0, "Concrete Inputs": ["", "[16, 8188, 5]", "[8192, 1, 1]", "0"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[8192, 1, 1], [], [], []], "Input Dims": [[16, 8188, 5], [], [], []], "Ev Idx": 8656 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1336756, + "ts": 1655274286443.598, "dur": 2.924, + "args": { + "External id": 4050746,"Sequence number": 40618551, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "2", "1", "9223372036854775807", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 1], [], [], [], []], "Input Dims": [[16, 8188, 5], [], [], [], []], "Ev Idx": 8657 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274286445.355, "dur": 0.601, + "args": { + "External id": 4050747,"Record function id": 0, "Concrete Inputs": ["", "[16, 8188, 4]", "[8192, 1, 1]", "1"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[8192, 1, 1], [], [], []], "Input Dims": [[16, 8188, 5], [], [], []], "Ev Idx": 8658 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1336756, + "ts": 1655274286450.470, "dur": 2.813, + "args": { + "External id": 4050748,"Sequence number": 40618551, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "0", "0", "9223372036854775807", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 1], [], [], [], []], "Input Dims": [[16, 8188, 4], [], [], [], []], "Ev Idx": 8659 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274286452.048, "dur": 0.720, + "args": { + "External id": 4050749,"Record function id": 0, "Concrete Inputs": ["", "[16, 8188, 4]", "[8192, 1, 1]", "1"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[8192, 1, 1], [], [], []], "Input Dims": [[16, 8188, 4], [], [], []], "Ev Idx": 8660 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1336756, + "ts": 1655274286454.293, "dur": 3.070, + "args": { + "External id": 4050750,"Sequence number": 40618551, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "1", "0", "4096", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 1], [], [], [], []], "Input Dims": [[16, 8188, 4], [], [], [], []], "Ev Idx": 8661 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274286455.975, "dur": 0.712, + "args": { + "External id": 4050751,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 4]", "[8192, 1, 1]", "1"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[8192, 1, 1], [], [], []], "Input Dims": [[16, 8188, 4], [], [], []], "Ev Idx": 8662 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1336756, + "ts": 1655274286458.401, "dur": 2.495, + "args": { + "External id": 4050752,"Sequence number": 40618551, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "2", "0", "9223372036854775807", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 1], [], [], [], []], "Input Dims": [[16, 4096, 4], [], [], [], []], "Ev Idx": 8663 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274286459.804, "dur": 0.606, + "args": { + "External id": 4050753,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 4]", "[8192, 1, 1]", "1"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[8192, 1, 1], [], [], []], "Input Dims": [[16, 4096, 4], [], [], []], "Ev Idx": 8664 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1336756, + "ts": 1655274286465.871, "dur": 4.764, + "args": { + "External id": 4050754,"Sequence number": 40618551, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "1", "2"], "Input type": ["long int", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 1], [], []], "Input Dims": [[16, 4096, 4], [], []], "Ev Idx": 8665 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274286469.135, "dur": 0.651, + "args": { + "External id": 4050755,"Record function id": 0, "Concrete Inputs": ["", "[16, 4, 4096]", "[8192, 1, 1]", ""], "Input type": ["long int", "ScalarList", "ScalarList", ""], "Input Strides": [[8192, 1, 1], [], [], []], "Input Dims": [[16, 4096, 4], [], [], []], "Ev Idx": 8666 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1336756, + "ts": 1655274286475.862, "dur": 2.783, + "args": { + "External id": 4050756,"Sequence number": 40618551, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "0", "0", "9223372036854775807", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 1], [], [], [], []], "Input Dims": [[16, 4, 4096], [], [], [], []], "Ev Idx": 8667 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274286477.568, "dur": 0.527, + "args": { + "External id": 4050757,"Record function id": 0, "Concrete Inputs": ["", "[16, 4, 4096]", "[8192, 1, 1]", "1"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[8192, 1, 1], [], [], []], "Input Dims": [[16, 4, 4096], [], [], []], "Ev Idx": 8668 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select", "pid": 1336756, "tid": 1336756, + "ts": 1655274286482.933, "dur": 8.693, + "args": { + "External id": 4050758,"Sequence number": 40618551, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "1", "0"], "Input type": ["long int", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 1], [], []], "Input Dims": [[16, 4, 4096], [], []], "Ev Idx": 8669 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274286489.535, "dur": 0.822, + "args": { + "External id": 4050759,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096]", "[8192, 1]", "1"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[8192, 1, 1], [], [], []], "Input Dims": [[16, 4, 4096], [], [], []], "Ev Idx": 8670 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1336756, + "ts": 1655274286493.015, "dur": 2.658, + "args": { + "External id": 4050760,"Sequence number": 40618551, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "1", "0", "9223372036854775807", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8192, 1], [], [], [], []], "Input Dims": [[16, 4096], [], [], [], []], "Ev Idx": 8671 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274286494.447, "dur": 0.699, + "args": { + "External id": 4050761,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096]", "[8192, 1]", "1"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[8192, 1], [], [], []], "Input Dims": [[16, 4096], [], [], []], "Ev Idx": 8672 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1336756, + "ts": 1655274286498.189, "dur": 6.413, + "args": { + "External id": 4050762,"Sequence number": 40618551, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "0", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[33554432, 8192, 2048, 1], [], [], [], []], "Input Dims": [[16, 4096, 4, 2048], [], [], [], []], "Ev Idx": 8673 + } + }, + { + "ph": "s", "id": 29, "pid": 1336756, "tid": 1336756, "ts": 1655274286498.189, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274286502.124, "dur": 0.887, + "args": { + "External id": 4050763,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 4, 2048]", "[33554432, 8192, 2048, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[33554432, 8192, 2048, 1], [], [], []], "Input Dims": [[16, 4096, 4, 2048], [], [], []], "Ev Idx": 8674 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1336756, + "ts": 1655274286507.364, "dur": 4.295, + "args": { + "External id": 4050764,"Sequence number": 40618552, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "1", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[33554432, 8192, 2048, 1], [], [], [], []], "Input Dims": [[16, 4096, 4, 2048], [], [], [], []], "Ev Idx": 8675 + } + }, + { + "ph": "s", "id": 28, "pid": 1336756, "tid": 1336756, "ts": 1655274286507.364, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274286510.171, "dur": 0.801, + "args": { + "External id": 4050765,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 4, 2048]", "[33554432, 8192, 2048, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[33554432, 8192, 2048, 1], [], [], []], "Input Dims": [[16, 4096, 4, 2048], [], [], []], "Ev Idx": 8676 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select", "pid": 1336756, "tid": 1336756, + "ts": 1655274286512.984, "dur": 4.672, + "args": { + "External id": 4050766,"Sequence number": 40618553, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "2", "0"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[33554432, 8192, 2048, 1], [], []], "Input Dims": [[16, 4096, 4, 2048], [], []], "Ev Idx": 8677 + } + }, + { + "ph": "s", "id": 27, "pid": 1336756, "tid": 1336756, "ts": 1655274286512.984, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274286516.046, "dur": 0.785, + "args": { + "External id": 4050767,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]", "[33554432, 8192, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[33554432, 8192, 2048, 1], [], [], []], "Input Dims": [[16, 4096, 4, 2048], [], [], []], "Ev Idx": 8678 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1336756, + "ts": 1655274286518.718, "dur": 4.261, + "args": { + "External id": 4050768,"Sequence number": 40618554, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "2", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[33554432, 8192, 1], [], [], [], []], "Input Dims": [[16, 4096, 2048], [], [], [], []], "Ev Idx": 8679 + } + }, + { + "ph": "s", "id": 26, "pid": 1336756, "tid": 1336756, "ts": 1655274286518.718, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274286521.631, "dur": 0.633, + "args": { + "External id": 4050769,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]", "[33554432, 8192, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[33554432, 8192, 1], [], [], []], "Input Dims": [[16, 4096, 2048], [], [], []], "Ev Idx": 8680 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::contiguous", "pid": 1336756, "tid": 1336756, + "ts": 1655274286527.372, "dur": 42.412, + "args": { + "External id": 4050770,"Sequence number": 40618555, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["long int", "Scalar"], "Input Strides": [[8192, 1], []], "Input Dims": [[16, 4096], []], "Ev Idx": 8681 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 1336756, "tid": 1336756, + "ts": 1655274286530.895, "dur": 38.616, + "args": { + "External id": 4050771,"Sequence number": 40618555, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["long int", "Scalar"], "Input Strides": [[8192, 1], []], "Input Dims": [[16, 4096], []], "Ev Idx": 8682 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336756, "tid": 1336756, + "ts": 1655274286533.317, "dur": 7.249, + "args": { + "External id": 4050772,"Record function id": 0, "Concrete Inputs": ["", "4", "0", "", "", "0"], "Input type": ["long int", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[8192, 1], [], [], [], [], []], "Input Dims": [[16, 4096], [], [], [], [], []], "Ev Idx": 8683 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274286535.330, "dur": 4.612, + "args": { + "External id": 4050773,"Record function id": 0, "Concrete Inputs": ["[16, 4096]", "4", "0", "", "", "0"], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8684 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1336756, + "ts": 1655274286542.116, "dur": 26.952, + "args": { + "External id": 4050774,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[4096, 1], [8192, 1], []], "Input Dims": [[16, 4096], [16, 4096], []], "Ev Idx": 8685 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274286591.345, "dur": 4.026, + "args": { + "External id": 4050775,"Sequence number": 40618555, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[-1, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[33554432, 8192, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 8686 + } + }, + { + "ph": "s", "id": 25, "pid": 1336756, "tid": 1336756, "ts": 1655274286591.345, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274286598.124, "dur": 1.009, + "args": { + "External id": 4050776,"Sequence number": 40618556, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["long int", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[16, 4096], []], "Ev Idx": 8687 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "FusedLinearCrossEntropyFunction", "pid": 1336756, "tid": 1336756, + "ts": 1655274286625.260, "dur": 70813.461, + "args": { + "External id": 4050777,"Sequence number": 40618556, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "-100", "0.", "1.", "8"], "Input type": ["c10::BFloat16", "long int", "c10::BFloat16", "", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8192, 1], [1], [2048, 1], [], [], [], [], []], "Input Dims": [[65536, 2048], [65536], [32000, 2048], [], [], [], [], []], "Ev Idx": 8688 + } + }, + { + "ph": "s", "id": 24, "pid": 1336756, "tid": 1336756, "ts": 1655274286625.260, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::contiguous", "pid": 1336756, "tid": 1336756, + "ts": 1655274286638.444, "dur": 24.617, + "args": { + "External id": 4050778,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[8192, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 8689 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 1336756, "tid": 1336756, + "ts": 1655274286639.060, "dur": 23.745, + "args": { + "External id": 4050779,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[8192, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 8690 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336756, "tid": 1336756, + "ts": 1655274286640.511, "dur": 4.852, + "args": { + "External id": 4050780,"Record function id": 0, "Concrete Inputs": ["", "15", "0", "", "", "0"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[8192, 1], [], [], [], [], []], "Input Dims": [[65536, 2048], [], [], [], [], []], "Ev Idx": 8691 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274286641.833, "dur": 3.100, + "args": { + "External id": 4050781,"Record function id": 0, "Concrete Inputs": ["[65536, 2048]", "15", "0", "", "", "0"], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8692 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1336756, + "ts": 1655274286646.194, "dur": 16.279, + "args": { + "External id": 4050782,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [8192, 1], []], "Input Dims": [[65536, 2048], [65536, 2048], []], "Ev Idx": 8693 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros_like", "pid": 1336756, "tid": 1336756, + "ts": 1655274286678.484, "dur": 24.202, + "args": { + "External id": 4050783,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[2048, 1], [], [], [], [], []], "Input Dims": [[65536, 2048], [], [], [], [], []], "Ev Idx": 8694 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336756, "tid": 1336756, + "ts": 1655274286680.028, "dur": 6.333, + "args": { + "External id": 4050784,"Record function id": 0, "Concrete Inputs": ["", "15", "0", "", "False", ""], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[2048, 1], [], [], [], [], []], "Input Dims": [[65536, 2048], [], [], [], [], []], "Ev Idx": 8695 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274286682.189, "dur": 3.843, + "args": { + "External id": 4050785,"Record function id": 0, "Concrete Inputs": ["[65536, 2048]", "[2048, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8696 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 1336756, "tid": 1336756, + "ts": 1655274286687.509, "dur": 14.968, + "args": { + "External id": 4050786,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[65536, 2048]], "Ev Idx": 8697 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 1336756, "tid": 1336756, + "ts": 1655274286688.847, "dur": 13.222, + "args": { + "External id": 4050787,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 8698 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros_like", "pid": 1336756, "tid": 1336756, + "ts": 1655274286705.999, "dur": 21.848, + "args": { + "External id": 4050788,"Record function id": 0, "Concrete Inputs": ["", "6", "", "", "False", ""], "Input type": ["c10::BFloat16", "Scalar", "", "", "Scalar", ""], "Input Strides": [[2048, 1], [], [], [], [], []], "Input Dims": [[32000, 2048], [], [], [], [], []], "Ev Idx": 8699 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336756, "tid": 1336756, + "ts": 1655274286706.922, "dur": 6.261, + "args": { + "External id": 4050789,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "False", ""], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[2048, 1], [], [], [], [], []], "Input Dims": [[32000, 2048], [], [], [], [], []], "Ev Idx": 8700 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274286709.983, "dur": 2.904, + "args": { + "External id": 4050790,"Record function id": 0, "Concrete Inputs": ["[32000, 2048]", "[2048, 1]", "6", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8701 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 1336756, "tid": 1336756, + "ts": 1655274286714.024, "dur": 13.591, + "args": { + "External id": 4050791,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[2048, 1]], "Input Dims": [[32000, 2048]], "Ev Idx": 8702 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 1336756, "tid": 1336756, + "ts": 1655274286715.106, "dur": 12.147, + "args": { + "External id": 4050792,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[2048, 1], []], "Input Dims": [[32000, 2048], []], "Ev Idx": 8703 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros", "pid": 1336756, "tid": 1336756, + "ts": 1655274286732.300, "dur": 24.892, + "args": { + "External id": 4050793,"Record function id": 0, "Concrete Inputs": ["[65536]", "6", "", "", "False"], "Input type": ["ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 8704 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274286733.713, "dur": 2.727, + "args": { + "External id": 4050794,"Record function id": 0, "Concrete Inputs": ["[65536]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8705 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 1336756, "tid": 1336756, + "ts": 1655274286744.272, "dur": 12.661, + "args": { + "External id": 4050795,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[65536]], "Ev Idx": 8706 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 1336756, "tid": 1336756, + "ts": 1655274286745.051, "dur": 11.498, + "args": { + "External id": 4050796,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[65536], []], "Ev Idx": 8707 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::ne", "pid": 1336756, "tid": 1336756, + "ts": 1655274286765.005, "dur": 24.346, + "args": { + "External id": 4050797,"Record function id": 0, "Concrete Inputs": ["", "-100"], "Input type": ["long int", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[65536], []], "Ev Idx": 8708 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 1336756, "tid": 1336756, + "ts": 1655274286794.535, "dur": 53.621, + "args": { + "External id": 4050798,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["bool", ""], "Input Strides": [[1], []], "Input Dims": [[65536], []], "Ev Idx": 8709 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 1336756, "tid": 1336756, + "ts": 1655274286797.753, "dur": 50.012, + "args": { + "External id": 4050799,"Record function id": 0, "Concrete Inputs": ["", "[]", "False", ""], "Input type": ["bool", "ScalarList", "Scalar", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 8710 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274286803.806, "dur": 1.264, + "args": { + "External id": 4050800,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[0]", ""], "Input type": ["long int", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 8711 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655274286806.619, "dur": 24.542, + "args": { + "External id": 4050801,"Record function id": 0, "Concrete Inputs": ["", "4", "False", "False", ""], "Input type": ["bool", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 8712 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336756, "tid": 1336756, + "ts": 1655274286808.418, "dur": 22.519, + "args": { + "External id": 4050802,"Record function id": 0, "Concrete Inputs": ["", "4", "", "", "", "False", ""], "Input type": ["bool", "Scalar", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[65536], [], [], [], [], [], []], "Ev Idx": 8713 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274286811.186, "dur": 3.958, + "args": { + "External id": 4050803,"Record function id": 0, "Concrete Inputs": ["[65536]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8714 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1336756, + "ts": 1655274286816.383, "dur": 14.230, + "args": { + "External id": 4050804,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["long int", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[65536], [65536], []], "Ev Idx": 8715 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::item", "pid": 1336756, "tid": 1336756, + "ts": 1655274286853.130, "dur": 65040.432, + "args": { + "External id": 4050805,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["long int"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 8716 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_local_scalar_dense", "pid": 1336756, "tid": 1336756, + "ts": 1655274286855.106, "dur": 65036.687, + "args": { + "External id": 4050806,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["long int"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 8717 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1336756, + "ts": 1655274351906.326, "dur": 9.112, + "args": { + "External id": 4050807,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "8192", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], [], [], []], "Input Dims": [[65536, 2048], [], [], [], []], "Ev Idx": 8718 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274351912.309, "dur": 1.263, + "args": { + "External id": 4050808,"Record function id": 0, "Concrete Inputs": ["", "[8192, 2048]", "[2048, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[65536, 2048], [], [], []], "Ev Idx": 8719 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336756, "tid": 1336756, + "ts": 1655274351920.338, "dur": 131.489, + "args": { + "External id": 4050809,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[8192, 2048], [32000, 2048], []], "Ev Idx": 8720 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1336756, + "ts": 1655274351922.258, "dur": 5.584, + "args": { + "External id": 4050810,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[32000, 2048]], "Ev Idx": 8721 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1336756, + "ts": 1655274351924.272, "dur": 2.707, + "args": { + "External id": 4050811,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[32000, 2048], [], []], "Ev Idx": 8722 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274351926.062, "dur": 0.664, + "args": { + "External id": 4050812,"Record function id": 0, "Concrete Inputs": ["", "[2048, 32000]", "[1, 2048]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[32000, 2048], [], [], []], "Ev Idx": 8723 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336756, "tid": 1336756, + "ts": 1655274351929.136, "dur": 121.768, + "args": { + "External id": 4050813,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048]], "Input Dims": [[8192, 2048], [2048, 32000]], "Ev Idx": 8724 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274351931.255, "dur": 118.190, + "args": { + "External id": 4050814,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048]], "Input Dims": [[8192, 2048], [2048, 32000]], "Ev Idx": 8725 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1336756, + "ts": 1655274352058.734, "dur": 4.820, + "args": { + "External id": 4050815,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "8192", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 8726 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274352061.138, "dur": 0.897, + "args": { + "External id": 4050816,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "0"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 8727 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274352071.081, "dur": 3.782, + "args": { + "External id": 4050817,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[8192, 32000], []], "Ev Idx": 8728 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274352085.203, "dur": 6.835, + "args": { + "External id": 4050818,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[8192, 32000], [], [], [], [], []], "Ev Idx": 8729 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274352087.363, "dur": 4.372, + "args": { + "External id": 4050819,"Record function id": 0, "Concrete Inputs": ["[8192, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8730 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 1336756, "tid": 1336756, + "ts": 1655274352229.495, "dur": 234.788, + "args": { + "External id": 4050820,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 8731 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274352234.589, "dur": 2.364, + "args": { + "External id": 4050821,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8732 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 1336756, "tid": 1336756, + "ts": 1655274352238.912, "dur": 224.480, + "args": { + "External id": 4050822,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[8192, 1], [], [], [0]], "Ev Idx": 8733 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 1336756, "tid": 1336756, + "ts": 1655274352241.761, "dur": 0.715, + "args": { + "External id": 4050823,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 8734 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 1336756, "tid": 1336756, + "ts": 1655274352245.232, "dur": 27.378, + "args": { + "External id": 4050824,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 8735 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 1336756, "tid": 1336756, + "ts": 1655274352275.267, "dur": 5.325, + "args": { + "External id": 4050825,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[8192, 1], []], "Ev Idx": 8736 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274352279.413, "dur": 0.852, + "args": { + "External id": 4050826,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[8192, 1], [], [], []], "Ev Idx": 8737 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336756, "tid": 1336756, + "ts": 1655274352282.719, "dur": 26.212, + "args": { + "External id": 4050827,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 8738 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274352285.648, "dur": 1.549, + "args": { + "External id": 4050828,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8739 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336756, "tid": 1336756, + "ts": 1655274352289.630, "dur": 19.035, + "args": { + "External id": 4050829,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[8192], [0]], "Ev Idx": 8740 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336756, "tid": 1336756, + "ts": 1655274352293.841, "dur": 3.088, + "args": { + "External id": 4050830,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 8741 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 1336756, "tid": 1336756, + "ts": 1655274352311.142, "dur": 24.533, + "args": { + "External id": 4050831,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 8742 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 1336756, "tid": 1336756, + "ts": 1655274352338.767, "dur": 16.713, + "args": { + "External id": 4050832,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 8743 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 1336756, "tid": 1336756, + "ts": 1655274352359.406, "dur": 16.755, + "args": { + "External id": 4050833,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[8192, 1], [8192, 1], []], "Ev Idx": 8744 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 1336756, "tid": 1336756, + "ts": 1655274352378.719, "dur": 14.437, + "args": { + "External id": 4050834,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 8745 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 1336756, "tid": 1336756, + "ts": 1655274352395.679, "dur": 35.759, + "args": { + "External id": 4050835,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[8192, 1], [], [], [], [0]], "Ev Idx": 8746 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336756, "tid": 1336756, + "ts": 1655274352398.006, "dur": 1.793, + "args": { + "External id": 4050836,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 8747 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274352403.469, "dur": 0.593, + "args": { + "External id": 4050837,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[8192], [], [], []], "Ev Idx": 8748 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 1336756, "tid": 1336756, + "ts": 1655274352434.989, "dur": 14.538, + "args": { + "External id": 4050838,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 8749 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336756, "tid": 1336756, + "ts": 1655274352451.379, "dur": 10.661, + "args": { + "External id": 4050839,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 8750 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274352472.316, "dur": 2.590, + "args": { + "External id": 4050840,"Record function id": 0, "Concrete Inputs": ["", "[8192]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 8751 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1336756, + "ts": 1655274352482.264, "dur": 4.727, + "args": { + "External id": 4050841,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "8192", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 8752 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274352485.119, "dur": 0.841, + "args": { + "External id": 4050842,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 8753 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274352569.850, "dur": 69.543, + "args": { + "External id": 4050843,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [2048, 1]], "Input Dims": [[8192, 32000], [32000, 2048]], "Ev Idx": 8754 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1336756, + "ts": 1655274352647.201, "dur": 4.497, + "args": { + "External id": 4050844,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "8192", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], [], [], []], "Input Dims": [[65536, 2048], [], [], [], []], "Ev Idx": 8755 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274352649.770, "dur": 0.815, + "args": { + "External id": 4050845,"Record function id": 0, "Concrete Inputs": ["", "[8192, 2048]", "[2048, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[65536, 2048], [], [], []], "Ev Idx": 8756 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1336756, + "ts": 1655274352653.594, "dur": 28.636, + "args": { + "External id": 4050846,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[8192, 2048], [8192, 2048], []], "Ev Idx": 8757 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1336756, + "ts": 1655274352688.277, "dur": 6.993, + "args": { + "External id": 4050847,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[8192, 32000]], "Ev Idx": 8758 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1336756, + "ts": 1655274352690.518, "dur": 4.129, + "args": { + "External id": 4050848,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[8192, 32000], [], []], "Ev Idx": 8759 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274352692.949, "dur": 1.479, + "args": { + "External id": 4050849,"Record function id": 0, "Concrete Inputs": ["", "[32000, 8192]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[8192, 32000], [], [], []], "Ev Idx": 8760 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336756, "tid": 1336756, + "ts": 1655274352701.390, "dur": 44.347, + "args": { + "External id": 4050850,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [2048, 1]], "Input Dims": [[32000, 8192], [8192, 2048]], "Ev Idx": 8761 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274352702.932, "dur": 42.133, + "args": { + "External id": 4050851,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [2048, 1]], "Input Dims": [[32000, 8192], [8192, 2048]], "Ev Idx": 8762 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336756, "tid": 1336756, + "ts": 1655274352750.821, "dur": 15.286, + "args": { + "External id": 4050852,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[32000, 2048], [32000, 2048], []], "Ev Idx": 8763 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1336756, + "ts": 1655274352772.954, "dur": 3.466, + "args": { + "External id": 4050853,"Record function id": 0, "Concrete Inputs": ["", "0", "8192", "16384", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], [], [], []], "Input Dims": [[65536, 2048], [], [], [], []], "Ev Idx": 8764 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274352775.024, "dur": 0.641, + "args": { + "External id": 4050854,"Record function id": 0, "Concrete Inputs": ["", "[8192, 2048]", "[2048, 1]", "16777216"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[65536, 2048], [], [], []], "Ev Idx": 8765 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336756, "tid": 1336756, + "ts": 1655274352780.526, "dur": 49.557, + "args": { + "External id": 4050855,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[8192, 2048], [32000, 2048], []], "Ev Idx": 8766 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1336756, + "ts": 1655274352781.549, "dur": 5.236, + "args": { + "External id": 4050856,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[32000, 2048]], "Ev Idx": 8767 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1336756, + "ts": 1655274352783.819, "dur": 2.313, + "args": { + "External id": 4050857,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[32000, 2048], [], []], "Ev Idx": 8768 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274352785.264, "dur": 0.709, + "args": { + "External id": 4050858,"Record function id": 0, "Concrete Inputs": ["", "[2048, 32000]", "[1, 2048]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[32000, 2048], [], [], []], "Ev Idx": 8769 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336756, "tid": 1336756, + "ts": 1655274352787.565, "dur": 42.181, + "args": { + "External id": 4050859,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048]], "Input Dims": [[8192, 2048], [2048, 32000]], "Ev Idx": 8770 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274352788.269, "dur": 40.913, + "args": { + "External id": 4050860,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048]], "Input Dims": [[8192, 2048], [2048, 32000]], "Ev Idx": 8771 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1336756, + "ts": 1655274352834.177, "dur": 5.403, + "args": { + "External id": 4050861,"Record function id": 0, "Concrete Inputs": ["", "0", "8192", "16384", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 8772 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274352836.214, "dur": 2.252, + "args": { + "External id": 4050862,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "8192"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 8773 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274352847.442, "dur": 1.745, + "args": { + "External id": 4050863,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[8192, 32000], []], "Ev Idx": 8774 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274352857.554, "dur": 6.126, + "args": { + "External id": 4050864,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[8192, 32000], [], [], [], [], []], "Ev Idx": 8775 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274352859.413, "dur": 3.999, + "args": { + "External id": 4050865,"Record function id": 0, "Concrete Inputs": ["[8192, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8776 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 1336756, "tid": 1336756, + "ts": 1655274352955.022, "dur": 221.697, + "args": { + "External id": 4050866,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 8777 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274352957.243, "dur": 1.940, + "args": { + "External id": 4050867,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8778 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 1336756, "tid": 1336756, + "ts": 1655274352960.890, "dur": 215.283, + "args": { + "External id": 4050868,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[8192, 1], [], [], [0]], "Ev Idx": 8779 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 1336756, "tid": 1336756, + "ts": 1655274352963.873, "dur": 0.412, + "args": { + "External id": 4050869,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 8780 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 1336756, "tid": 1336756, + "ts": 1655274352965.870, "dur": 57.997, + "args": { + "External id": 4050870,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 8781 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 1336756, "tid": 1336756, + "ts": 1655274353026.492, "dur": 4.777, + "args": { + "External id": 4050871,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[8192, 1], []], "Ev Idx": 8782 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274353029.207, "dur": 1.693, + "args": { + "External id": 4050872,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[8192, 1], [], [], []], "Ev Idx": 8783 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336756, "tid": 1336756, + "ts": 1655274353032.433, "dur": 25.386, + "args": { + "External id": 4050873,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 8784 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274353033.561, "dur": 2.004, + "args": { + "External id": 4050874,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8785 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336756, "tid": 1336756, + "ts": 1655274353037.050, "dur": 20.417, + "args": { + "External id": 4050875,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[8192], [0]], "Ev Idx": 8786 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336756, "tid": 1336756, + "ts": 1655274353042.279, "dur": 2.960, + "args": { + "External id": 4050876,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 8787 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 1336756, "tid": 1336756, + "ts": 1655274353059.588, "dur": 22.176, + "args": { + "External id": 4050877,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 8788 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 1336756, "tid": 1336756, + "ts": 1655274353083.263, "dur": 12.966, + "args": { + "External id": 4050878,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 8789 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 1336756, "tid": 1336756, + "ts": 1655274353101.156, "dur": 13.811, + "args": { + "External id": 4050879,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[8192, 1], [8192, 1], []], "Ev Idx": 8790 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 1336756, "tid": 1336756, + "ts": 1655274353116.595, "dur": 11.469, + "args": { + "External id": 4050880,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 8791 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 1336756, "tid": 1336756, + "ts": 1655274353129.949, "dur": 19.607, + "args": { + "External id": 4050881,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[8192, 1], [], [], [], [0]], "Ev Idx": 8792 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336756, "tid": 1336756, + "ts": 1655274353131.719, "dur": 1.435, + "args": { + "External id": 4050882,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 8793 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274353135.335, "dur": 0.840, + "args": { + "External id": 4050883,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[8192], [], [], []], "Ev Idx": 8794 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 1336756, "tid": 1336756, + "ts": 1655274353151.621, "dur": 10.895, + "args": { + "External id": 4050884,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 8795 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336756, "tid": 1336756, + "ts": 1655274353163.579, "dur": 11.384, + "args": { + "External id": 4050885,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 8796 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274353186.452, "dur": 2.330, + "args": { + "External id": 4050886,"Record function id": 0, "Concrete Inputs": ["", "[8192]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 8797 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1336756, + "ts": 1655274353198.818, "dur": 3.826, + "args": { + "External id": 4050887,"Record function id": 0, "Concrete Inputs": ["", "0", "8192", "16384", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 8798 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274353201.329, "dur": 0.517, + "args": { + "External id": 4050888,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "8192"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 8799 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274353273.880, "dur": 55.752, + "args": { + "External id": 4050889,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [2048, 1]], "Input Dims": [[8192, 32000], [32000, 2048]], "Ev Idx": 8800 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1336756, + "ts": 1655274353334.837, "dur": 4.221, + "args": { + "External id": 4050890,"Record function id": 0, "Concrete Inputs": ["", "0", "8192", "16384", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], [], [], []], "Input Dims": [[65536, 2048], [], [], [], []], "Ev Idx": 8801 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274353337.383, "dur": 0.834, + "args": { + "External id": 4050891,"Record function id": 0, "Concrete Inputs": ["", "[8192, 2048]", "[2048, 1]", "16777216"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[65536, 2048], [], [], []], "Ev Idx": 8802 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1336756, + "ts": 1655274353340.517, "dur": 23.578, + "args": { + "External id": 4050892,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[8192, 2048], [8192, 2048], []], "Ev Idx": 8803 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1336756, + "ts": 1655274353368.889, "dur": 7.033, + "args": { + "External id": 4050893,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[8192, 32000]], "Ev Idx": 8804 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1336756, + "ts": 1655274353372.132, "dur": 3.190, + "args": { + "External id": 4050894,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[8192, 32000], [], []], "Ev Idx": 8805 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274353373.857, "dur": 1.238, + "args": { + "External id": 4050895,"Record function id": 0, "Concrete Inputs": ["", "[32000, 8192]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[8192, 32000], [], [], []], "Ev Idx": 8806 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336756, "tid": 1336756, + "ts": 1655274353378.727, "dur": 53.882, + "args": { + "External id": 4050896,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [2048, 1]], "Input Dims": [[32000, 8192], [8192, 2048]], "Ev Idx": 8807 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274353380.033, "dur": 51.545, + "args": { + "External id": 4050897,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [2048, 1]], "Input Dims": [[32000, 8192], [8192, 2048]], "Ev Idx": 8808 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336756, "tid": 1336756, + "ts": 1655274353438.402, "dur": 16.585, + "args": { + "External id": 4050898,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[32000, 2048], [32000, 2048], []], "Ev Idx": 8809 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1336756, + "ts": 1655274353461.835, "dur": 5.885, + "args": { + "External id": 4050899,"Record function id": 0, "Concrete Inputs": ["", "0", "16384", "24576", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], [], [], []], "Input Dims": [[65536, 2048], [], [], [], []], "Ev Idx": 8810 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274353465.846, "dur": 0.833, + "args": { + "External id": 4050900,"Record function id": 0, "Concrete Inputs": ["", "[8192, 2048]", "[2048, 1]", "33554432"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[65536, 2048], [], [], []], "Ev Idx": 8811 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336756, "tid": 1336756, + "ts": 1655274353471.530, "dur": 57.035, + "args": { + "External id": 4050901,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[8192, 2048], [32000, 2048], []], "Ev Idx": 8812 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1336756, + "ts": 1655274353472.743, "dur": 5.944, + "args": { + "External id": 4050902,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[32000, 2048]], "Ev Idx": 8813 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1336756, + "ts": 1655274353473.705, "dur": 4.398, + "args": { + "External id": 4050903,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[32000, 2048], [], []], "Ev Idx": 8814 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274353475.404, "dur": 2.486, + "args": { + "External id": 4050904,"Record function id": 0, "Concrete Inputs": ["", "[2048, 32000]", "[1, 2048]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[32000, 2048], [], [], []], "Ev Idx": 8815 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336756, "tid": 1336756, + "ts": 1655274353479.413, "dur": 48.665, + "args": { + "External id": 4050905,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048]], "Input Dims": [[8192, 2048], [2048, 32000]], "Ev Idx": 8816 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274353479.994, "dur": 47.395, + "args": { + "External id": 4050906,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048]], "Input Dims": [[8192, 2048], [2048, 32000]], "Ev Idx": 8817 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1336756, + "ts": 1655274353532.561, "dur": 3.965, + "args": { + "External id": 4050907,"Record function id": 0, "Concrete Inputs": ["", "0", "16384", "24576", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 8818 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274353534.741, "dur": 0.745, + "args": { + "External id": 4050908,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "16384"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 8819 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274353544.757, "dur": 1.627, + "args": { + "External id": 4050909,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[8192, 32000], []], "Ev Idx": 8820 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274353554.487, "dur": 5.821, + "args": { + "External id": 4050910,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[8192, 32000], [], [], [], [], []], "Ev Idx": 8821 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274353556.499, "dur": 3.535, + "args": { + "External id": 4050911,"Record function id": 0, "Concrete Inputs": ["[8192, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8822 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 1336756, "tid": 1336756, + "ts": 1655274353650.543, "dur": 240.127, + "args": { + "External id": 4050912,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 8823 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274353653.184, "dur": 2.017, + "args": { + "External id": 4050913,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8824 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 1336756, "tid": 1336756, + "ts": 1655274353657.935, "dur": 232.393, + "args": { + "External id": 4050914,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[8192, 1], [], [], [0]], "Ev Idx": 8825 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 1336756, "tid": 1336756, + "ts": 1655274353659.521, "dur": 0.298, + "args": { + "External id": 4050915,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 8826 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 1336756, "tid": 1336756, + "ts": 1655274353662.412, "dur": 19.313, + "args": { + "External id": 4050916,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 8827 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 1336756, "tid": 1336756, + "ts": 1655274353683.405, "dur": 3.735, + "args": { + "External id": 4050917,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[8192, 1], []], "Ev Idx": 8828 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274353686.192, "dur": 0.693, + "args": { + "External id": 4050918,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[8192, 1], [], [], []], "Ev Idx": 8829 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336756, "tid": 1336756, + "ts": 1655274353688.316, "dur": 21.714, + "args": { + "External id": 4050919,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 8830 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274353689.285, "dur": 3.149, + "args": { + "External id": 4050920,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8831 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336756, "tid": 1336756, + "ts": 1655274353693.705, "dur": 16.029, + "args": { + "External id": 4050921,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[8192], [0]], "Ev Idx": 8832 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336756, "tid": 1336756, + "ts": 1655274353696.578, "dur": 2.373, + "args": { + "External id": 4050922,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 8833 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 1336756, "tid": 1336756, + "ts": 1655274353711.637, "dur": 18.543, + "args": { + "External id": 4050923,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 8834 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 1336756, "tid": 1336756, + "ts": 1655274353731.543, "dur": 12.931, + "args": { + "External id": 4050924,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 8835 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 1336756, "tid": 1336756, + "ts": 1655274353749.001, "dur": 13.432, + "args": { + "External id": 4050925,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[8192, 1], [8192, 1], []], "Ev Idx": 8836 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 1336756, "tid": 1336756, + "ts": 1655274353763.824, "dur": 12.633, + "args": { + "External id": 4050926,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 8837 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 1336756, "tid": 1336756, + "ts": 1655274353778.206, "dur": 25.505, + "args": { + "External id": 4050927,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[8192, 1], [], [], [], [0]], "Ev Idx": 8838 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336756, "tid": 1336756, + "ts": 1655274353780.101, "dur": 1.472, + "args": { + "External id": 4050928,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 8839 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274353783.556, "dur": 0.696, + "args": { + "External id": 4050929,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[8192], [], [], []], "Ev Idx": 8840 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 1336756, "tid": 1336756, + "ts": 1655274353805.132, "dur": 39.192, + "args": { + "External id": 4050930,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 8841 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336756, "tid": 1336756, + "ts": 1655274353847.338, "dur": 41.946, + "args": { + "External id": 4050931,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 8842 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274353896.772, "dur": 1.524, + "args": { + "External id": 4050932,"Record function id": 0, "Concrete Inputs": ["", "[8192]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 8843 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1336756, + "ts": 1655274353906.832, "dur": 3.269, + "args": { + "External id": 4050933,"Record function id": 0, "Concrete Inputs": ["", "0", "16384", "24576", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 8844 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274353908.984, "dur": 0.451, + "args": { + "External id": 4050934,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "16384"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 8845 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274353975.525, "dur": 90.436, + "args": { + "External id": 4050935,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [2048, 1]], "Input Dims": [[8192, 32000], [32000, 2048]], "Ev Idx": 8846 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1336756, + "ts": 1655274354073.179, "dur": 5.931, + "args": { + "External id": 4050936,"Record function id": 0, "Concrete Inputs": ["", "0", "16384", "24576", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], [], [], []], "Input Dims": [[65536, 2048], [], [], [], []], "Ev Idx": 8847 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274354076.578, "dur": 1.235, + "args": { + "External id": 4050937,"Record function id": 0, "Concrete Inputs": ["", "[8192, 2048]", "[2048, 1]", "33554432"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[65536, 2048], [], [], []], "Ev Idx": 8848 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1336756, + "ts": 1655274354080.677, "dur": 23.470, + "args": { + "External id": 4050938,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[8192, 2048], [8192, 2048], []], "Ev Idx": 8849 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1336756, + "ts": 1655274354111.538, "dur": 7.175, + "args": { + "External id": 4050939,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[8192, 32000]], "Ev Idx": 8850 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1336756, + "ts": 1655274354113.014, "dur": 5.043, + "args": { + "External id": 4050940,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[8192, 32000], [], []], "Ev Idx": 8851 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274354114.705, "dur": 3.101, + "args": { + "External id": 4050941,"Record function id": 0, "Concrete Inputs": ["", "[32000, 8192]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[8192, 32000], [], [], []], "Ev Idx": 8852 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336756, "tid": 1336756, + "ts": 1655274354121.982, "dur": 41.118, + "args": { + "External id": 4050942,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [2048, 1]], "Input Dims": [[32000, 8192], [8192, 2048]], "Ev Idx": 8853 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274354123.100, "dur": 39.327, + "args": { + "External id": 4050943,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [2048, 1]], "Input Dims": [[32000, 8192], [8192, 2048]], "Ev Idx": 8854 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336756, "tid": 1336756, + "ts": 1655274354167.028, "dur": 14.238, + "args": { + "External id": 4050944,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[32000, 2048], [32000, 2048], []], "Ev Idx": 8855 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1336756, + "ts": 1655274354219.997, "dur": 5.613, + "args": { + "External id": 4050945,"Record function id": 0, "Concrete Inputs": ["", "0", "24576", "32768", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], [], [], []], "Input Dims": [[65536, 2048], [], [], [], []], "Ev Idx": 8856 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274354224.149, "dur": 0.558, + "args": { + "External id": 4050946,"Record function id": 0, "Concrete Inputs": ["", "[8192, 2048]", "[2048, 1]", "50331648"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[65536, 2048], [], [], []], "Ev Idx": 8857 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336756, "tid": 1336756, + "ts": 1655274354229.277, "dur": 48.994, + "args": { + "External id": 4050947,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[8192, 2048], [32000, 2048], []], "Ev Idx": 8858 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1336756, + "ts": 1655274354229.980, "dur": 3.220, + "args": { + "External id": 4050948,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[32000, 2048]], "Ev Idx": 8859 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1336756, + "ts": 1655274354230.626, "dur": 2.082, + "args": { + "External id": 4050949,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[32000, 2048], [], []], "Ev Idx": 8860 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274354231.937, "dur": 0.612, + "args": { + "External id": 4050950,"Record function id": 0, "Concrete Inputs": ["", "[2048, 32000]", "[1, 2048]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[32000, 2048], [], [], []], "Ev Idx": 8861 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336756, "tid": 1336756, + "ts": 1655274354233.886, "dur": 44.014, + "args": { + "External id": 4050951,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048]], "Input Dims": [[8192, 2048], [2048, 32000]], "Ev Idx": 8862 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274354235.995, "dur": 41.326, + "args": { + "External id": 4050952,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048]], "Input Dims": [[8192, 2048], [2048, 32000]], "Ev Idx": 8863 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1336756, + "ts": 1655274354281.987, "dur": 3.549, + "args": { + "External id": 4050953,"Record function id": 0, "Concrete Inputs": ["", "0", "24576", "32768", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 8864 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274354283.614, "dur": 0.799, + "args": { + "External id": 4050954,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "24576"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 8865 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274354291.460, "dur": 1.427, + "args": { + "External id": 4050955,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[8192, 32000], []], "Ev Idx": 8866 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274354300.474, "dur": 9.561, + "args": { + "External id": 4050956,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[8192, 32000], [], [], [], [], []], "Ev Idx": 8867 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274354304.110, "dur": 5.633, + "args": { + "External id": 4050957,"Record function id": 0, "Concrete Inputs": ["[8192, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8868 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 1336756, "tid": 1336756, + "ts": 1655274354397.383, "dur": 189.834, + "args": { + "External id": 4050958,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 8869 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274354399.638, "dur": 2.109, + "args": { + "External id": 4050959,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8870 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 1336756, "tid": 1336756, + "ts": 1655274354402.978, "dur": 183.856, + "args": { + "External id": 4050960,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[8192, 1], [], [], [0]], "Ev Idx": 8871 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 1336756, "tid": 1336756, + "ts": 1655274354404.252, "dur": 0.330, + "args": { + "External id": 4050961,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 8872 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 1336756, "tid": 1336756, + "ts": 1655274354405.541, "dur": 37.685, + "args": { + "External id": 4050962,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 8873 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 1336756, "tid": 1336756, + "ts": 1655274354445.760, "dur": 3.934, + "args": { + "External id": 4050963,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[8192, 1], []], "Ev Idx": 8874 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274354448.108, "dur": 1.346, + "args": { + "External id": 4050964,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[8192, 1], [], [], []], "Ev Idx": 8875 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336756, "tid": 1336756, + "ts": 1655274354450.806, "dur": 25.014, + "args": { + "External id": 4050965,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 8876 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274354453.536, "dur": 2.259, + "args": { + "External id": 4050966,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8877 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336756, "tid": 1336756, + "ts": 1655274354456.897, "dur": 18.623, + "args": { + "External id": 4050967,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[8192], [0]], "Ev Idx": 8878 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336756, "tid": 1336756, + "ts": 1655274354461.551, "dur": 2.452, + "args": { + "External id": 4050968,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 8879 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 1336756, "tid": 1336756, + "ts": 1655274354477.173, "dur": 20.199, + "args": { + "External id": 4050969,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 8880 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 1336756, "tid": 1336756, + "ts": 1655274354498.640, "dur": 12.570, + "args": { + "External id": 4050970,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 8881 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 1336756, "tid": 1336756, + "ts": 1655274354513.688, "dur": 12.740, + "args": { + "External id": 4050971,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[8192, 1], [8192, 1], []], "Ev Idx": 8882 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 1336756, "tid": 1336756, + "ts": 1655274354527.684, "dur": 11.441, + "args": { + "External id": 4050972,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 8883 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 1336756, "tid": 1336756, + "ts": 1655274354540.770, "dur": 20.036, + "args": { + "External id": 4050973,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[8192, 1], [], [], [], [0]], "Ev Idx": 8884 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336756, "tid": 1336756, + "ts": 1655274354542.210, "dur": 1.245, + "args": { + "External id": 4050974,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 8885 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274354547.254, "dur": 0.892, + "args": { + "External id": 4050975,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[8192], [], [], []], "Ev Idx": 8886 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 1336756, "tid": 1336756, + "ts": 1655274354562.030, "dur": 11.185, + "args": { + "External id": 4050976,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 8887 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336756, "tid": 1336756, + "ts": 1655274354574.138, "dur": 11.656, + "args": { + "External id": 4050977,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 8888 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274354594.174, "dur": 2.176, + "args": { + "External id": 4050978,"Record function id": 0, "Concrete Inputs": ["", "[8192]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 8889 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1336756, + "ts": 1655274354605.340, "dur": 3.643, + "args": { + "External id": 4050979,"Record function id": 0, "Concrete Inputs": ["", "0", "24576", "32768", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 8890 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274354607.583, "dur": 0.660, + "args": { + "External id": 4050980,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "24576"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 8891 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274354672.794, "dur": 51.225, + "args": { + "External id": 4050981,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [2048, 1]], "Input Dims": [[8192, 32000], [32000, 2048]], "Ev Idx": 8892 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1336756, + "ts": 1655274354728.580, "dur": 5.818, + "args": { + "External id": 4050982,"Record function id": 0, "Concrete Inputs": ["", "0", "24576", "32768", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], [], [], []], "Input Dims": [[65536, 2048], [], [], [], []], "Ev Idx": 8893 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274354732.363, "dur": 1.137, + "args": { + "External id": 4050983,"Record function id": 0, "Concrete Inputs": ["", "[8192, 2048]", "[2048, 1]", "50331648"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[65536, 2048], [], [], []], "Ev Idx": 8894 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1336756, + "ts": 1655274354735.624, "dur": 22.987, + "args": { + "External id": 4050984,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[8192, 2048], [8192, 2048], []], "Ev Idx": 8895 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1336756, + "ts": 1655274354763.199, "dur": 4.474, + "args": { + "External id": 4050985,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[8192, 32000]], "Ev Idx": 8896 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1336756, + "ts": 1655274354764.277, "dur": 2.758, + "args": { + "External id": 4050986,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[8192, 32000], [], []], "Ev Idx": 8897 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274354765.989, "dur": 0.886, + "args": { + "External id": 4050987,"Record function id": 0, "Concrete Inputs": ["", "[32000, 8192]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[8192, 32000], [], [], []], "Ev Idx": 8898 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336756, "tid": 1336756, + "ts": 1655274354770.108, "dur": 40.229, + "args": { + "External id": 4050988,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [2048, 1]], "Input Dims": [[32000, 8192], [8192, 2048]], "Ev Idx": 8899 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274354773.051, "dur": 36.693, + "args": { + "External id": 4050989,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [2048, 1]], "Input Dims": [[32000, 8192], [8192, 2048]], "Ev Idx": 8900 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336756, "tid": 1336756, + "ts": 1655274354814.310, "dur": 13.204, + "args": { + "External id": 4050990,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[32000, 2048], [32000, 2048], []], "Ev Idx": 8901 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1336756, + "ts": 1655274354832.822, "dur": 3.106, + "args": { + "External id": 4050991,"Record function id": 0, "Concrete Inputs": ["", "0", "32768", "40960", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], [], [], []], "Input Dims": [[65536, 2048], [], [], [], []], "Ev Idx": 8902 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274354834.584, "dur": 0.640, + "args": { + "External id": 4050992,"Record function id": 0, "Concrete Inputs": ["", "[8192, 2048]", "[2048, 1]", "67108864"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[65536, 2048], [], [], []], "Ev Idx": 8903 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336756, "tid": 1336756, + "ts": 1655274354839.551, "dur": 49.459, + "args": { + "External id": 4050993,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[8192, 2048], [32000, 2048], []], "Ev Idx": 8904 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1336756, + "ts": 1655274354840.528, "dur": 7.282, + "args": { + "External id": 4050994,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[32000, 2048]], "Ev Idx": 8905 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1336756, + "ts": 1655274354841.250, "dur": 6.083, + "args": { + "External id": 4050995,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[32000, 2048], [], []], "Ev Idx": 8906 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274354844.623, "dur": 2.539, + "args": { + "External id": 4050996,"Record function id": 0, "Concrete Inputs": ["", "[2048, 32000]", "[1, 2048]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[32000, 2048], [], [], []], "Ev Idx": 8907 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336756, "tid": 1336756, + "ts": 1655274354848.317, "dur": 40.287, + "args": { + "External id": 4050997,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048]], "Input Dims": [[8192, 2048], [2048, 32000]], "Ev Idx": 8908 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274354848.722, "dur": 39.097, + "args": { + "External id": 4050998,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048]], "Input Dims": [[8192, 2048], [2048, 32000]], "Ev Idx": 8909 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1336756, + "ts": 1655274354893.019, "dur": 3.400, + "args": { + "External id": 4050999,"Record function id": 0, "Concrete Inputs": ["", "0", "32768", "40960", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 8910 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274354894.648, "dur": 0.788, + "args": { + "External id": 4051000,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "32768"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 8911 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274354901.281, "dur": 1.501, + "args": { + "External id": 4051001,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[8192, 32000], []], "Ev Idx": 8912 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274354909.301, "dur": 7.032, + "args": { + "External id": 4051002,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[8192, 32000], [], [], [], [], []], "Ev Idx": 8913 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274354912.636, "dur": 3.450, + "args": { + "External id": 4051003,"Record function id": 0, "Concrete Inputs": ["[8192, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8914 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 1336756, "tid": 1336756, + "ts": 1655274355027.990, "dur": 169.509, + "args": { + "External id": 4051004,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 8915 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274355030.449, "dur": 3.252, + "args": { + "External id": 4051005,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8916 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 1336756, "tid": 1336756, + "ts": 1655274355035.202, "dur": 161.898, + "args": { + "External id": 4051006,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[8192, 1], [], [], [0]], "Ev Idx": 8917 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 1336756, "tid": 1336756, + "ts": 1655274355036.428, "dur": 0.295, + "args": { + "External id": 4051007,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 8918 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 1336756, "tid": 1336756, + "ts": 1655274355039.973, "dur": 21.393, + "args": { + "External id": 4051008,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 8919 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 1336756, "tid": 1336756, + "ts": 1655274355062.822, "dur": 3.280, + "args": { + "External id": 4051009,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[8192, 1], []], "Ev Idx": 8920 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274355064.762, "dur": 0.957, + "args": { + "External id": 4051010,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[8192, 1], [], [], []], "Ev Idx": 8921 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336756, "tid": 1336756, + "ts": 1655274355068.686, "dur": 21.359, + "args": { + "External id": 4051011,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 8922 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274355069.689, "dur": 2.997, + "args": { + "External id": 4051012,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8923 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336756, "tid": 1336756, + "ts": 1655274355073.870, "dur": 15.808, + "args": { + "External id": 4051013,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[8192], [0]], "Ev Idx": 8924 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336756, "tid": 1336756, + "ts": 1655274355076.305, "dur": 2.484, + "args": { + "External id": 4051014,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 8925 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 1336756, "tid": 1336756, + "ts": 1655274355091.558, "dur": 18.270, + "args": { + "External id": 4051015,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 8926 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 1336756, "tid": 1336756, + "ts": 1655274355111.332, "dur": 12.351, + "args": { + "External id": 4051016,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 8927 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 1336756, "tid": 1336756, + "ts": 1655274355126.591, "dur": 12.169, + "args": { + "External id": 4051017,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[8192, 1], [8192, 1], []], "Ev Idx": 8928 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 1336756, "tid": 1336756, + "ts": 1655274355140.082, "dur": 11.553, + "args": { + "External id": 4051018,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 8929 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 1336756, "tid": 1336756, + "ts": 1655274355153.162, "dur": 18.665, + "args": { + "External id": 4051019,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[8192, 1], [], [], [], [0]], "Ev Idx": 8930 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336756, "tid": 1336756, + "ts": 1655274355156.425, "dur": 1.116, + "args": { + "External id": 4051020,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 8931 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274355159.399, "dur": 0.691, + "args": { + "External id": 4051021,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[8192], [], [], []], "Ev Idx": 8932 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 1336756, "tid": 1336756, + "ts": 1655274355173.085, "dur": 11.078, + "args": { + "External id": 4051022,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 8933 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336756, "tid": 1336756, + "ts": 1655274355185.286, "dur": 10.764, + "args": { + "External id": 4051023,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 8934 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274355203.710, "dur": 1.922, + "args": { + "External id": 4051024,"Record function id": 0, "Concrete Inputs": ["", "[8192]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 8935 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1336756, + "ts": 1655274355214.336, "dur": 4.089, + "args": { + "External id": 4051025,"Record function id": 0, "Concrete Inputs": ["", "0", "32768", "40960", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 8936 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274355216.841, "dur": 0.794, + "args": { + "External id": 4051026,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "32768"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 8937 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274355282.680, "dur": 50.650, + "args": { + "External id": 4051027,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [2048, 1]], "Input Dims": [[8192, 32000], [32000, 2048]], "Ev Idx": 8938 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1336756, + "ts": 1655274355339.491, "dur": 4.547, + "args": { + "External id": 4051028,"Record function id": 0, "Concrete Inputs": ["", "0", "32768", "40960", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], [], [], []], "Input Dims": [[65536, 2048], [], [], [], []], "Ev Idx": 8939 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274355342.125, "dur": 1.084, + "args": { + "External id": 4051029,"Record function id": 0, "Concrete Inputs": ["", "[8192, 2048]", "[2048, 1]", "67108864"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[65536, 2048], [], [], []], "Ev Idx": 8940 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1336756, + "ts": 1655274355345.950, "dur": 20.948, + "args": { + "External id": 4051030,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[8192, 2048], [8192, 2048], []], "Ev Idx": 8941 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1336756, + "ts": 1655274355371.363, "dur": 6.397, + "args": { + "External id": 4051031,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[8192, 32000]], "Ev Idx": 8942 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1336756, + "ts": 1655274355372.696, "dur": 4.435, + "args": { + "External id": 4051032,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[8192, 32000], [], []], "Ev Idx": 8943 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274355374.341, "dur": 2.614, + "args": { + "External id": 4051033,"Record function id": 0, "Concrete Inputs": ["", "[32000, 8192]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[8192, 32000], [], [], []], "Ev Idx": 8944 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336756, "tid": 1336756, + "ts": 1655274355382.043, "dur": 60.991, + "args": { + "External id": 4051034,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [2048, 1]], "Input Dims": [[32000, 8192], [8192, 2048]], "Ev Idx": 8945 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274355383.504, "dur": 58.416, + "args": { + "External id": 4051035,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [2048, 1]], "Input Dims": [[32000, 8192], [8192, 2048]], "Ev Idx": 8946 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336756, "tid": 1336756, + "ts": 1655274355448.134, "dur": 14.811, + "args": { + "External id": 4051036,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[32000, 2048], [32000, 2048], []], "Ev Idx": 8947 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1336756, + "ts": 1655274355469.168, "dur": 4.275, + "args": { + "External id": 4051037,"Record function id": 0, "Concrete Inputs": ["", "0", "40960", "49152", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], [], [], []], "Input Dims": [[65536, 2048], [], [], [], []], "Ev Idx": 8948 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274355471.438, "dur": 0.840, + "args": { + "External id": 4051038,"Record function id": 0, "Concrete Inputs": ["", "[8192, 2048]", "[2048, 1]", "83886080"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[65536, 2048], [], [], []], "Ev Idx": 8949 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336756, "tid": 1336756, + "ts": 1655274355477.190, "dur": 52.621, + "args": { + "External id": 4051039,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[8192, 2048], [32000, 2048], []], "Ev Idx": 8950 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1336756, + "ts": 1655274355477.823, "dur": 5.619, + "args": { + "External id": 4051040,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[32000, 2048]], "Ev Idx": 8951 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1336756, + "ts": 1655274355480.489, "dur": 2.453, + "args": { + "External id": 4051041,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[32000, 2048], [], []], "Ev Idx": 8952 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274355482.031, "dur": 0.773, + "args": { + "External id": 4051042,"Record function id": 0, "Concrete Inputs": ["", "[2048, 32000]", "[1, 2048]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[32000, 2048], [], [], []], "Ev Idx": 8953 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336756, "tid": 1336756, + "ts": 1655274355483.940, "dur": 45.304, + "args": { + "External id": 4051043,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048]], "Input Dims": [[8192, 2048], [2048, 32000]], "Ev Idx": 8954 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274355485.234, "dur": 43.421, + "args": { + "External id": 4051044,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048]], "Input Dims": [[8192, 2048], [2048, 32000]], "Ev Idx": 8955 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1336756, + "ts": 1655274355533.411, "dur": 3.602, + "args": { + "External id": 4051045,"Record function id": 0, "Concrete Inputs": ["", "0", "40960", "49152", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 8956 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274355535.075, "dur": 0.911, + "args": { + "External id": 4051046,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "40960"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 8957 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274355544.316, "dur": 1.700, + "args": { + "External id": 4051047,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[8192, 32000], []], "Ev Idx": 8958 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274355553.053, "dur": 6.027, + "args": { + "External id": 4051048,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[8192, 32000], [], [], [], [], []], "Ev Idx": 8959 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274355554.765, "dur": 4.043, + "args": { + "External id": 4051049,"Record function id": 0, "Concrete Inputs": ["[8192, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8960 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 1336756, "tid": 1336756, + "ts": 1655274355641.856, "dur": 178.230, + "args": { + "External id": 4051050,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 8961 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274355644.430, "dur": 2.448, + "args": { + "External id": 4051051,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8962 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 1336756, "tid": 1336756, + "ts": 1655274355649.963, "dur": 169.635, + "args": { + "External id": 4051052,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[8192, 1], [], [], [0]], "Ev Idx": 8963 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 1336756, "tid": 1336756, + "ts": 1655274355653.124, "dur": 0.235, + "args": { + "External id": 4051053,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 8964 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 1336756, "tid": 1336756, + "ts": 1655274355654.676, "dur": 18.628, + "args": { + "External id": 4051054,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 8965 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 1336756, "tid": 1336756, + "ts": 1655274355674.687, "dur": 9.982, + "args": { + "External id": 4051055,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[8192, 1], []], "Ev Idx": 8966 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274355682.192, "dur": 2.238, + "args": { + "External id": 4051056,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[8192, 1], [], [], []], "Ev Idx": 8967 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336756, "tid": 1336756, + "ts": 1655274355685.656, "dur": 19.424, + "args": { + "External id": 4051057,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 8968 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274355686.546, "dur": 2.028, + "args": { + "External id": 4051058,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 8969 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336756, "tid": 1336756, + "ts": 1655274355689.653, "dur": 15.134, + "args": { + "External id": 4051059,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[8192], [0]], "Ev Idx": 8970 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336756, "tid": 1336756, + "ts": 1655274355691.935, "dur": 2.578, + "args": { + "External id": 4051060,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 8971 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 1336756, "tid": 1336756, + "ts": 1655274355706.398, "dur": 18.267, + "args": { + "External id": 4051061,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 8972 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 1336756, "tid": 1336756, + "ts": 1655274355726.060, "dur": 12.269, + "args": { + "External id": 4051062,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 8973 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 1336756, "tid": 1336756, + "ts": 1655274355740.688, "dur": 12.590, + "args": { + "External id": 4051063,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[8192, 1], [8192, 1], []], "Ev Idx": 8974 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 1336756, "tid": 1336756, + "ts": 1655274355756.881, "dur": 10.969, + "args": { + "External id": 4051064,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 8975 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 1336756, "tid": 1336756, + "ts": 1655274355771.286, "dur": 19.462, + "args": { + "External id": 4051065,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[8192, 1], [], [], [], [0]], "Ev Idx": 8976 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336756, "tid": 1336756, + "ts": 1655274355774.758, "dur": 1.675, + "args": { + "External id": 4051066,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 8977 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274355778.131, "dur": 0.639, + "args": { + "External id": 4051067,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[8192], [], [], []], "Ev Idx": 8978 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 1336756, "tid": 1336756, + "ts": 1655274355792.169, "dur": 12.594, + "args": { + "External id": 4051068,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 8979 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336756, "tid": 1336756, + "ts": 1655274355805.965, "dur": 10.996, + "args": { + "External id": 4051069,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 8980 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274355825.771, "dur": 1.416, + "args": { + "External id": 4051070,"Record function id": 0, "Concrete Inputs": ["", "[8192]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 8981 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1336756, + "ts": 1655274355835.369, "dur": 3.760, + "args": { + "External id": 4051071,"Record function id": 0, "Concrete Inputs": ["", "0", "40960", "49152", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 8982 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274355837.821, "dur": 0.483, + "args": { + "External id": 4051072,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "40960"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 8983 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274355900.835, "dur": 48.887, + "args": { + "External id": 4051073,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [2048, 1]], "Input Dims": [[8192, 32000], [32000, 2048]], "Ev Idx": 8984 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1336756, + "ts": 1655274355954.775, "dur": 4.051, + "args": { + "External id": 4051074,"Record function id": 0, "Concrete Inputs": ["", "0", "40960", "49152", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], [], [], []], "Input Dims": [[65536, 2048], [], [], [], []], "Ev Idx": 8985 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274355957.162, "dur": 0.740, + "args": { + "External id": 4051075,"Record function id": 0, "Concrete Inputs": ["", "[8192, 2048]", "[2048, 1]", "83886080"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[65536, 2048], [], [], []], "Ev Idx": 8986 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1336756, + "ts": 1655274355960.078, "dur": 22.062, + "args": { + "External id": 4051076,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[8192, 2048], [8192, 2048], []], "Ev Idx": 8987 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1336756, + "ts": 1655274356023.300, "dur": 8.891, + "args": { + "External id": 4051077,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[8192, 32000]], "Ev Idx": 8988 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1336756, + "ts": 1655274356026.911, "dur": 4.362, + "args": { + "External id": 4051078,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[8192, 32000], [], []], "Ev Idx": 8989 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274356028.915, "dur": 1.976, + "args": { + "External id": 4051079,"Record function id": 0, "Concrete Inputs": ["", "[32000, 8192]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[8192, 32000], [], [], []], "Ev Idx": 8990 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336756, "tid": 1336756, + "ts": 1655274356035.608, "dur": 47.488, + "args": { + "External id": 4051080,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [2048, 1]], "Input Dims": [[32000, 8192], [8192, 2048]], "Ev Idx": 8991 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274356036.831, "dur": 45.523, + "args": { + "External id": 4051081,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [2048, 1]], "Input Dims": [[32000, 8192], [8192, 2048]], "Ev Idx": 8992 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336756, "tid": 1336756, + "ts": 1655274356087.199, "dur": 15.736, + "args": { + "External id": 4051082,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[32000, 2048], [32000, 2048], []], "Ev Idx": 8993 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1336756, + "ts": 1655274356109.493, "dur": 5.965, + "args": { + "External id": 4051083,"Record function id": 0, "Concrete Inputs": ["", "0", "49152", "57344", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], [], [], []], "Input Dims": [[65536, 2048], [], [], [], []], "Ev Idx": 8994 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274356113.638, "dur": 0.804, + "args": { + "External id": 4051084,"Record function id": 0, "Concrete Inputs": ["", "[8192, 2048]", "[2048, 1]", "100663296"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[65536, 2048], [], [], []], "Ev Idx": 8995 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336756, "tid": 1336756, + "ts": 1655274356119.369, "dur": 47.886, + "args": { + "External id": 4051085,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[8192, 2048], [32000, 2048], []], "Ev Idx": 8996 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1336756, + "ts": 1655274356120.239, "dur": 3.649, + "args": { + "External id": 4051086,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[32000, 2048]], "Ev Idx": 8997 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1336756, + "ts": 1655274356121.213, "dur": 2.186, + "args": { + "External id": 4051087,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[32000, 2048], [], []], "Ev Idx": 8998 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274356122.433, "dur": 0.797, + "args": { + "External id": 4051088,"Record function id": 0, "Concrete Inputs": ["", "[2048, 32000]", "[1, 2048]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[32000, 2048], [], [], []], "Ev Idx": 8999 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336756, "tid": 1336756, + "ts": 1655274356124.366, "dur": 42.462, + "args": { + "External id": 4051089,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048]], "Input Dims": [[8192, 2048], [2048, 32000]], "Ev Idx": 9000 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274356125.126, "dur": 41.167, + "args": { + "External id": 4051090,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048]], "Input Dims": [[8192, 2048], [2048, 32000]], "Ev Idx": 9001 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1336756, + "ts": 1655274356171.047, "dur": 3.989, + "args": { + "External id": 4051091,"Record function id": 0, "Concrete Inputs": ["", "0", "49152", "57344", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 9002 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274356172.890, "dur": 0.811, + "args": { + "External id": 4051092,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "49152"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 9003 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274356182.206, "dur": 1.454, + "args": { + "External id": 4051093,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[8192, 32000], []], "Ev Idx": 9004 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274356191.375, "dur": 6.226, + "args": { + "External id": 4051094,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[8192, 32000], [], [], [], [], []], "Ev Idx": 9005 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274356193.250, "dur": 4.083, + "args": { + "External id": 4051095,"Record function id": 0, "Concrete Inputs": ["[8192, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9006 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 1336756, "tid": 1336756, + "ts": 1655274356283.224, "dur": 187.815, + "args": { + "External id": 4051096,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 9007 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274356287.222, "dur": 2.016, + "args": { + "External id": 4051097,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9008 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 1336756, "tid": 1336756, + "ts": 1655274356291.945, "dur": 178.607, + "args": { + "External id": 4051098,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[8192, 1], [], [], [0]], "Ev Idx": 9009 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 1336756, "tid": 1336756, + "ts": 1655274356293.422, "dur": 0.503, + "args": { + "External id": 4051099,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 9010 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 1336756, "tid": 1336756, + "ts": 1655274356294.730, "dur": 18.891, + "args": { + "External id": 4051100,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 9011 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 1336756, "tid": 1336756, + "ts": 1655274356314.864, "dur": 4.415, + "args": { + "External id": 4051101,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[8192, 1], []], "Ev Idx": 9012 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274356318.269, "dur": 0.778, + "args": { + "External id": 4051102,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[8192, 1], [], [], []], "Ev Idx": 9013 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336756, "tid": 1336756, + "ts": 1655274356319.989, "dur": 20.213, + "args": { + "External id": 4051103,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 9014 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274356321.236, "dur": 1.634, + "args": { + "External id": 4051104,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9015 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336756, "tid": 1336756, + "ts": 1655274356324.092, "dur": 15.773, + "args": { + "External id": 4051105,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[8192], [0]], "Ev Idx": 9016 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336756, "tid": 1336756, + "ts": 1655274356326.459, "dur": 2.359, + "args": { + "External id": 4051106,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 9017 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 1336756, "tid": 1336756, + "ts": 1655274356343.289, "dur": 18.902, + "args": { + "External id": 4051107,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 9018 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 1336756, "tid": 1336756, + "ts": 1655274356363.814, "dur": 15.023, + "args": { + "External id": 4051108,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 9019 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 1336756, "tid": 1336756, + "ts": 1655274356381.557, "dur": 11.536, + "args": { + "External id": 4051109,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[8192, 1], [8192, 1], []], "Ev Idx": 9020 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 1336756, "tid": 1336756, + "ts": 1655274356394.473, "dur": 11.382, + "args": { + "External id": 4051110,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 9021 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 1336756, "tid": 1336756, + "ts": 1655274356407.355, "dur": 35.840, + "args": { + "External id": 4051111,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[8192, 1], [], [], [], [0]], "Ev Idx": 9022 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336756, "tid": 1336756, + "ts": 1655274356409.202, "dur": 1.155, + "args": { + "External id": 4051112,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 9023 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274356412.441, "dur": 0.887, + "args": { + "External id": 4051113,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[8192], [], [], []], "Ev Idx": 9024 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 1336756, "tid": 1336756, + "ts": 1655274356445.580, "dur": 11.663, + "args": { + "External id": 4051114,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 9025 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336756, "tid": 1336756, + "ts": 1655274356460.001, "dur": 9.497, + "args": { + "External id": 4051115,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 9026 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274356478.137, "dur": 2.098, + "args": { + "External id": 4051116,"Record function id": 0, "Concrete Inputs": ["", "[8192]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 9027 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1336756, + "ts": 1655274356488.430, "dur": 3.842, + "args": { + "External id": 4051117,"Record function id": 0, "Concrete Inputs": ["", "0", "49152", "57344", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 9028 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274356490.900, "dur": 0.583, + "args": { + "External id": 4051118,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "49152"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 9029 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274356555.343, "dur": 52.384, + "args": { + "External id": 4051119,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [2048, 1]], "Input Dims": [[8192, 32000], [32000, 2048]], "Ev Idx": 9030 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1336756, + "ts": 1655274356612.500, "dur": 4.281, + "args": { + "External id": 4051120,"Record function id": 0, "Concrete Inputs": ["", "0", "49152", "57344", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], [], [], []], "Input Dims": [[65536, 2048], [], [], [], []], "Ev Idx": 9031 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274356614.941, "dur": 0.879, + "args": { + "External id": 4051121,"Record function id": 0, "Concrete Inputs": ["", "[8192, 2048]", "[2048, 1]", "100663296"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[65536, 2048], [], [], []], "Ev Idx": 9032 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1336756, + "ts": 1655274356618.011, "dur": 22.243, + "args": { + "External id": 4051122,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[8192, 2048], [8192, 2048], []], "Ev Idx": 9033 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1336756, + "ts": 1655274356646.232, "dur": 4.757, + "args": { + "External id": 4051123,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[8192, 32000]], "Ev Idx": 9034 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1336756, + "ts": 1655274356647.709, "dur": 2.741, + "args": { + "External id": 4051124,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[8192, 32000], [], []], "Ev Idx": 9035 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274356649.288, "dur": 1.001, + "args": { + "External id": 4051125,"Record function id": 0, "Concrete Inputs": ["", "[32000, 8192]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[8192, 32000], [], [], []], "Ev Idx": 9036 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336756, "tid": 1336756, + "ts": 1655274356653.631, "dur": 38.739, + "args": { + "External id": 4051126,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [2048, 1]], "Input Dims": [[32000, 8192], [8192, 2048]], "Ev Idx": 9037 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274356654.415, "dur": 37.469, + "args": { + "External id": 4051127,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [2048, 1]], "Input Dims": [[32000, 8192], [8192, 2048]], "Ev Idx": 9038 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336756, "tid": 1336756, + "ts": 1655274356695.970, "dur": 12.894, + "args": { + "External id": 4051128,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[32000, 2048], [32000, 2048], []], "Ev Idx": 9039 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1336756, + "ts": 1655274356714.020, "dur": 4.718, + "args": { + "External id": 4051129,"Record function id": 0, "Concrete Inputs": ["", "0", "57344", "65536", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], [], [], []], "Input Dims": [[65536, 2048], [], [], [], []], "Ev Idx": 9040 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274356717.101, "dur": 0.725, + "args": { + "External id": 4051130,"Record function id": 0, "Concrete Inputs": ["", "[8192, 2048]", "[2048, 1]", "117440512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[65536, 2048], [], [], []], "Ev Idx": 9041 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336756, "tid": 1336756, + "ts": 1655274356722.234, "dur": 47.195, + "args": { + "External id": 4051131,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[8192, 2048], [32000, 2048], []], "Ev Idx": 9042 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1336756, + "ts": 1655274356722.842, "dur": 3.231, + "args": { + "External id": 4051132,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[32000, 2048]], "Ev Idx": 9043 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1336756, + "ts": 1655274356723.407, "dur": 2.195, + "args": { + "External id": 4051133,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[32000, 2048], [], []], "Ev Idx": 9044 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274356724.735, "dur": 0.749, + "args": { + "External id": 4051134,"Record function id": 0, "Concrete Inputs": ["", "[2048, 32000]", "[1, 2048]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[32000, 2048], [], [], []], "Ev Idx": 9045 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336756, "tid": 1336756, + "ts": 1655274356726.489, "dur": 42.477, + "args": { + "External id": 4051135,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048]], "Input Dims": [[8192, 2048], [2048, 32000]], "Ev Idx": 9046 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274356728.665, "dur": 39.739, + "args": { + "External id": 4051136,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048]], "Input Dims": [[8192, 2048], [2048, 32000]], "Ev Idx": 9047 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1336756, + "ts": 1655274356773.679, "dur": 3.090, + "args": { + "External id": 4051137,"Record function id": 0, "Concrete Inputs": ["", "0", "57344", "65536", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 9048 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274356775.323, "dur": 0.520, + "args": { + "External id": 4051138,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "57344"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 9049 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274356781.860, "dur": 1.447, + "args": { + "External id": 4051139,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[8192, 32000], []], "Ev Idx": 9050 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274356789.979, "dur": 8.974, + "args": { + "External id": 4051140,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[8192, 32000], [], [], [], [], []], "Ev Idx": 9051 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274356793.602, "dur": 5.051, + "args": { + "External id": 4051141,"Record function id": 0, "Concrete Inputs": ["[8192, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9052 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 1336756, "tid": 1336756, + "ts": 1655274356875.549, "dur": 202.273, + "args": { + "External id": 4051142,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 9053 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274356877.548, "dur": 1.940, + "args": { + "External id": 4051143,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9054 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 1336756, "tid": 1336756, + "ts": 1655274356880.672, "dur": 196.760, + "args": { + "External id": 4051144,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[8192, 1], [], [], [0]], "Ev Idx": 9055 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 1336756, "tid": 1336756, + "ts": 1655274356881.887, "dur": 0.433, + "args": { + "External id": 4051145,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 9056 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 1336756, "tid": 1336756, + "ts": 1655274356883.153, "dur": 19.972, + "args": { + "External id": 4051146,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 9057 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 1336756, "tid": 1336756, + "ts": 1655274356904.718, "dur": 2.874, + "args": { + "External id": 4051147,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[8192, 1], []], "Ev Idx": 9058 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274356906.650, "dur": 0.725, + "args": { + "External id": 4051148,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[8192, 1], [], [], []], "Ev Idx": 9059 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336756, "tid": 1336756, + "ts": 1655274356908.616, "dur": 22.785, + "args": { + "External id": 4051149,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 9060 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274356911.002, "dur": 1.657, + "args": { + "External id": 4051150,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9061 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336756, "tid": 1336756, + "ts": 1655274356913.729, "dur": 17.391, + "args": { + "External id": 4051151,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[8192], [0]], "Ev Idx": 9062 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336756, "tid": 1336756, + "ts": 1655274356918.043, "dur": 2.435, + "args": { + "External id": 4051152,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 9063 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 1336756, "tid": 1336756, + "ts": 1655274356932.719, "dur": 17.960, + "args": { + "External id": 4051153,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 9064 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 1336756, "tid": 1336756, + "ts": 1655274356951.917, "dur": 12.012, + "args": { + "External id": 4051154,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 9065 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 1336756, "tid": 1336756, + "ts": 1655274356966.116, "dur": 12.168, + "args": { + "External id": 4051155,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[8192, 1], [8192, 1], []], "Ev Idx": 9066 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 1336756, "tid": 1336756, + "ts": 1655274356979.545, "dur": 46.507, + "args": { + "External id": 4051156,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 9067 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 1336756, "tid": 1336756, + "ts": 1655274357028.769, "dur": 22.078, + "args": { + "External id": 4051157,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[8192, 1], [], [], [], [0]], "Ev Idx": 9068 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336756, "tid": 1336756, + "ts": 1655274357030.799, "dur": 1.690, + "args": { + "External id": 4051158,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 9069 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274357036.005, "dur": 1.040, + "args": { + "External id": 4051159,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[8192], [], [], []], "Ev Idx": 9070 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 1336756, "tid": 1336756, + "ts": 1655274357052.029, "dur": 12.085, + "args": { + "External id": 4051160,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 9071 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336756, "tid": 1336756, + "ts": 1655274357065.115, "dur": 11.133, + "args": { + "External id": 4051161,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 9072 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274357085.120, "dur": 2.052, + "args": { + "External id": 4051162,"Record function id": 0, "Concrete Inputs": ["", "[8192]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 9073 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1336756, + "ts": 1655274357095.628, "dur": 3.931, + "args": { + "External id": 4051163,"Record function id": 0, "Concrete Inputs": ["", "0", "57344", "65536", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 9074 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274357098.112, "dur": 0.553, + "args": { + "External id": 4051164,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "57344"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 9075 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274357163.820, "dur": 52.363, + "args": { + "External id": 4051165,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [2048, 1]], "Input Dims": [[8192, 32000], [32000, 2048]], "Ev Idx": 9076 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1336756, + "ts": 1655274357221.095, "dur": 5.907, + "args": { + "External id": 4051166,"Record function id": 0, "Concrete Inputs": ["", "0", "57344", "65536", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], [], [], []], "Input Dims": [[65536, 2048], [], [], [], []], "Ev Idx": 9077 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274357224.999, "dur": 1.115, + "args": { + "External id": 4051167,"Record function id": 0, "Concrete Inputs": ["", "[8192, 2048]", "[2048, 1]", "117440512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[65536, 2048], [], [], []], "Ev Idx": 9078 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1336756, + "ts": 1655274357228.396, "dur": 20.842, + "args": { + "External id": 4051168,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[8192, 2048], [8192, 2048], []], "Ev Idx": 9079 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1336756, + "ts": 1655274357253.480, "dur": 4.803, + "args": { + "External id": 4051169,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[8192, 32000]], "Ev Idx": 9080 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1336756, + "ts": 1655274357254.849, "dur": 2.768, + "args": { + "External id": 4051170,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[8192, 32000], [], []], "Ev Idx": 9081 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274357256.501, "dur": 0.900, + "args": { + "External id": 4051171,"Record function id": 0, "Concrete Inputs": ["", "[32000, 8192]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[8192, 32000], [], [], []], "Ev Idx": 9082 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336756, "tid": 1336756, + "ts": 1655274357260.448, "dur": 39.958, + "args": { + "External id": 4051172,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [2048, 1]], "Input Dims": [[32000, 8192], [8192, 2048]], "Ev Idx": 9083 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274357262.824, "dur": 36.925, + "args": { + "External id": 4051173,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [2048, 1]], "Input Dims": [[32000, 8192], [8192, 2048]], "Ev Idx": 9084 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336756, "tid": 1336756, + "ts": 1655274357303.823, "dur": 13.412, + "args": { + "External id": 4051174,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[32000, 2048], [32000, 2048], []], "Ev Idx": 9085 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 1336756, "tid": 1336756, + "ts": 1655274357321.831, "dur": 24.071, + "args": { + "External id": 4051175,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", ""], "Input Strides": [[1], []], "Input Dims": [[65536], []], "Ev Idx": 9086 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 1336756, "tid": 1336756, + "ts": 1655274357324.129, "dur": 21.391, + "args": { + "External id": 4051176,"Record function id": 0, "Concrete Inputs": ["", "[]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 9087 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274357330.610, "dur": 0.717, + "args": { + "External id": 4051177,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 9088 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655274357351.186, "dur": 27.154, + "args": { + "External id": 4051178,"Record function id": 0, "Concrete Inputs": ["", "", "15", "False", "False", ""], "Input type": ["float", "", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[2048, 1], [], [], [], [], []], "Input Dims": [[32000, 2048], [], [], [], [], []], "Ev Idx": 9089 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336756, "tid": 1336756, + "ts": 1655274357353.018, "dur": 25.125, + "args": { + "External id": 4051179,"Record function id": 0, "Concrete Inputs": ["", "15", "", "", "", "False", ""], "Input type": ["float", "Scalar", "", "", "", "Scalar", ""], "Input Strides": [[2048, 1], [], [], [], [], [], []], "Input Dims": [[32000, 2048], [], [], [], [], [], []], "Ev Idx": 9090 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274357357.221, "dur": 4.235, + "args": { + "External id": 4051180,"Record function id": 0, "Concrete Inputs": ["[32000, 2048]", "[2048, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9091 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1336756, + "ts": 1655274357364.441, "dur": 13.263, + "args": { + "External id": 4051181,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "float", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[32000, 2048], [32000, 2048], []], "Ev Idx": 9092 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1336756, + "ts": 1655274357391.708, "dur": 5.656, + "args": { + "External id": 4051182,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[65536, 2048]], "Ev Idx": 9093 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1336756, + "ts": 1655274357394.296, "dur": 2.810, + "args": { + "External id": 4051183,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[65536, 2048]], "Ev Idx": 9094 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1336756, + "ts": 1655274357398.460, "dur": 1.690, + "args": { + "External id": 4051184,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[32000, 2048]], "Ev Idx": 9095 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1336756, + "ts": 1655274357399.371, "dur": 0.705, + "args": { + "External id": 4051185,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[32000, 2048]], "Ev Idx": 9096 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336756, "tid": 1336756, + "ts": 1655274357457.991, "dur": 25.953, + "args": { + "External id": 4051186,"Sequence number": 40618557, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[1], [], []], "Ev Idx": 9097 + } + }, + { + "ph": "s", "id": 23, "pid": 1336756, "tid": 1336756, "ts": 1655274357457.991, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1336756, + "ts": 1655274357490.433, "dur": 6.875, + "args": { + "External id": 4051187,"Sequence number": 40618558, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "0", "0", "9223372036854775807", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 1], [], [], [], []], "Input Dims": [[16, 4, 4096], [], [], [], []], "Ev Idx": 9098 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274357494.252, "dur": 1.230, + "args": { + "External id": 4051188,"Record function id": 0, "Concrete Inputs": ["", "[16, 4, 4096]", "[8192, 1, 1]", "1"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[8192, 1, 1], [], [], []], "Input Dims": [[16, 4, 4096], [], [], []], "Ev Idx": 9099 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select", "pid": 1336756, "tid": 1336756, + "ts": 1655274357501.557, "dur": 6.419, + "args": { + "External id": 4051189,"Sequence number": 40618558, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "1", "1"], "Input type": ["long int", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 1], [], []], "Input Dims": [[16, 4, 4096], [], []], "Ev Idx": 9100 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274357505.814, "dur": 0.944, + "args": { + "External id": 4051190,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096]", "[8192, 1]", "2"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[8192, 1, 1], [], [], []], "Input Dims": [[16, 4, 4096], [], [], []], "Ev Idx": 9101 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1336756, + "ts": 1655274357509.057, "dur": 2.816, + "args": { + "External id": 4051191,"Sequence number": 40618558, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "1", "0", "9223372036854775807", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8192, 1], [], [], [], []], "Input Dims": [[16, 4096], [], [], [], []], "Ev Idx": 9102 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274357510.930, "dur": 0.407, + "args": { + "External id": 4051192,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096]", "[8192, 1]", "2"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[8192, 1], [], [], []], "Input Dims": [[16, 4096], [], [], []], "Ev Idx": 9103 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1336756, + "ts": 1655274357515.906, "dur": 7.526, + "args": { + "External id": 4051193,"Sequence number": 40618558, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "0", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[33554432, 8192, 2048, 1], [], [], [], []], "Input Dims": [[16, 4096, 4, 2048], [], [], [], []], "Ev Idx": 9104 + } + }, + { + "ph": "s", "id": 22, "pid": 1336756, "tid": 1336756, "ts": 1655274357515.906, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274357520.650, "dur": 1.472, + "args": { + "External id": 4051194,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 4, 2048]", "[33554432, 8192, 2048, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[33554432, 8192, 2048, 1], [], [], []], "Input Dims": [[16, 4096, 4, 2048], [], [], []], "Ev Idx": 9105 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1336756, + "ts": 1655274357524.441, "dur": 4.186, + "args": { + "External id": 4051195,"Sequence number": 40618559, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "1", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[33554432, 8192, 2048, 1], [], [], [], []], "Input Dims": [[16, 4096, 4, 2048], [], [], [], []], "Ev Idx": 9106 + } + }, + { + "ph": "s", "id": 21, "pid": 1336756, "tid": 1336756, "ts": 1655274357524.441, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274357527.414, "dur": 0.449, + "args": { + "External id": 4051196,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 4, 2048]", "[33554432, 8192, 2048, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[33554432, 8192, 2048, 1], [], [], []], "Input Dims": [[16, 4096, 4, 2048], [], [], []], "Ev Idx": 9107 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select", "pid": 1336756, "tid": 1336756, + "ts": 1655274357529.587, "dur": 6.394, + "args": { + "External id": 4051197,"Sequence number": 40618560, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "2", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[33554432, 8192, 2048, 1], [], []], "Input Dims": [[16, 4096, 4, 2048], [], []], "Ev Idx": 9108 + } + }, + { + "ph": "s", "id": 20, "pid": 1336756, "tid": 1336756, "ts": 1655274357529.587, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274357534.401, "dur": 0.541, + "args": { + "External id": 4051198,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]", "[33554432, 8192, 1]", "2048"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[33554432, 8192, 2048, 1], [], [], []], "Input Dims": [[16, 4096, 4, 2048], [], [], []], "Ev Idx": 9109 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1336756, + "ts": 1655274357537.021, "dur": 4.541, + "args": { + "External id": 4051199,"Sequence number": 40618561, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "2", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[33554432, 8192, 1], [], [], [], []], "Input Dims": [[16, 4096, 2048], [], [], [], []], "Ev Idx": 9110 + } + }, + { + "ph": "s", "id": 19, "pid": 1336756, "tid": 1336756, "ts": 1655274357537.021, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274357539.750, "dur": 1.093, + "args": { + "External id": 4051200,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]", "[33554432, 8192, 1]", "2048"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[33554432, 8192, 1], [], [], []], "Input Dims": [[16, 4096, 2048], [], [], []], "Ev Idx": 9111 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::contiguous", "pid": 1336756, "tid": 1336756, + "ts": 1655274357545.281, "dur": 28.217, + "args": { + "External id": 4051201,"Sequence number": 40618562, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["long int", "Scalar"], "Input Strides": [[8192, 1], []], "Input Dims": [[16, 4096], []], "Ev Idx": 9112 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 1336756, "tid": 1336756, + "ts": 1655274357546.968, "dur": 26.323, + "args": { + "External id": 4051202,"Sequence number": 40618562, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["long int", "Scalar"], "Input Strides": [[8192, 1], []], "Input Dims": [[16, 4096], []], "Ev Idx": 9113 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336756, "tid": 1336756, + "ts": 1655274357549.063, "dur": 6.817, + "args": { + "External id": 4051203,"Record function id": 0, "Concrete Inputs": ["", "4", "0", "", "", "0"], "Input type": ["long int", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[8192, 1], [], [], [], [], []], "Input Dims": [[16, 4096], [], [], [], [], []], "Ev Idx": 9114 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274357551.572, "dur": 3.807, + "args": { + "External id": 4051204,"Record function id": 0, "Concrete Inputs": ["[16, 4096]", "4", "0", "", "", "0"], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9115 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1336756, + "ts": 1655274357556.603, "dur": 16.152, + "args": { + "External id": 4051205,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[4096, 1], [8192, 1], []], "Input Dims": [[16, 4096], [16, 4096], []], "Ev Idx": 9116 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274357599.833, "dur": 3.921, + "args": { + "External id": 4051206,"Sequence number": 40618562, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[-1, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[33554432, 8192, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 9117 + } + }, + { + "ph": "s", "id": 18, "pid": 1336756, "tid": 1336756, "ts": 1655274357599.833, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274357606.021, "dur": 1.572, + "args": { + "External id": 4051207,"Sequence number": 40618563, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["long int", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[16, 4096], []], "Ev Idx": 9118 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "FusedLinearCrossEntropyFunction", "pid": 1336756, "tid": 1336756, + "ts": 1655274357639.444, "dur": 41715.444, + "args": { + "External id": 4051208,"Sequence number": 40618563, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "-100", "0.", "1.", "8"], "Input type": ["c10::BFloat16", "long int", "c10::BFloat16", "", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8192, 1], [1], [2048, 1], [], [], [], [], []], "Input Dims": [[65536, 2048], [65536], [32000, 2048], [], [], [], [], []], "Ev Idx": 9119 + } + }, + { + "ph": "s", "id": 17, "pid": 1336756, "tid": 1336756, "ts": 1655274357639.444, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::contiguous", "pid": 1336756, "tid": 1336756, + "ts": 1655274357653.353, "dur": 25.329, + "args": { + "External id": 4051209,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[8192, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 9120 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 1336756, "tid": 1336756, + "ts": 1655274357654.156, "dur": 24.322, + "args": { + "External id": 4051210,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[8192, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 9121 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336756, "tid": 1336756, + "ts": 1655274357655.480, "dur": 6.384, + "args": { + "External id": 4051211,"Record function id": 0, "Concrete Inputs": ["", "15", "0", "", "", "0"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[8192, 1], [], [], [], [], []], "Input Dims": [[65536, 2048], [], [], [], [], []], "Ev Idx": 9122 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274357658.514, "dur": 2.950, + "args": { + "External id": 4051212,"Record function id": 0, "Concrete Inputs": ["[65536, 2048]", "15", "0", "", "", "0"], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9123 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1336756, + "ts": 1655274357662.611, "dur": 15.498, + "args": { + "External id": 4051213,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [8192, 1], []], "Input Dims": [[65536, 2048], [65536, 2048], []], "Ev Idx": 9124 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros_like", "pid": 1336756, "tid": 1336756, + "ts": 1655274357693.618, "dur": 23.181, + "args": { + "External id": 4051214,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[2048, 1], [], [], [], [], []], "Input Dims": [[65536, 2048], [], [], [], [], []], "Ev Idx": 9125 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336756, "tid": 1336756, + "ts": 1655274357694.570, "dur": 5.883, + "args": { + "External id": 4051215,"Record function id": 0, "Concrete Inputs": ["", "15", "0", "", "False", ""], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[2048, 1], [], [], [], [], []], "Input Dims": [[65536, 2048], [], [], [], [], []], "Ev Idx": 9126 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274357696.560, "dur": 3.638, + "args": { + "External id": 4051216,"Record function id": 0, "Concrete Inputs": ["[65536, 2048]", "[2048, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9127 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 1336756, "tid": 1336756, + "ts": 1655274357701.709, "dur": 14.879, + "args": { + "External id": 4051217,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[65536, 2048]], "Ev Idx": 9128 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 1336756, "tid": 1336756, + "ts": 1655274357703.540, "dur": 12.719, + "args": { + "External id": 4051218,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 9129 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros_like", "pid": 1336756, "tid": 1336756, + "ts": 1655274357719.943, "dur": 20.238, + "args": { + "External id": 4051219,"Record function id": 0, "Concrete Inputs": ["", "6", "", "", "False", ""], "Input type": ["c10::BFloat16", "Scalar", "", "", "Scalar", ""], "Input Strides": [[2048, 1], [], [], [], [], []], "Input Dims": [[32000, 2048], [], [], [], [], []], "Ev Idx": 9130 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336756, "tid": 1336756, + "ts": 1655274357720.740, "dur": 5.959, + "args": { + "External id": 4051220,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "False", ""], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[2048, 1], [], [], [], [], []], "Input Dims": [[32000, 2048], [], [], [], [], []], "Ev Idx": 9131 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274357723.526, "dur": 2.886, + "args": { + "External id": 4051221,"Record function id": 0, "Concrete Inputs": ["[32000, 2048]", "[2048, 1]", "6", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9132 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 1336756, "tid": 1336756, + "ts": 1655274357727.310, "dur": 12.676, + "args": { + "External id": 4051222,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[2048, 1]], "Input Dims": [[32000, 2048]], "Ev Idx": 9133 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 1336756, "tid": 1336756, + "ts": 1655274357727.746, "dur": 11.805, + "args": { + "External id": 4051223,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[2048, 1], []], "Input Dims": [[32000, 2048], []], "Ev Idx": 9134 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros", "pid": 1336756, "tid": 1336756, + "ts": 1655274357745.895, "dur": 15.705, + "args": { + "External id": 4051224,"Record function id": 0, "Concrete Inputs": ["[65536]", "6", "", "", "False"], "Input type": ["ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 9135 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274357747.325, "dur": 2.906, + "args": { + "External id": 4051225,"Record function id": 0, "Concrete Inputs": ["[65536]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9136 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 1336756, "tid": 1336756, + "ts": 1655274357750.738, "dur": 10.604, + "args": { + "External id": 4051226,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[65536]], "Ev Idx": 9137 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 1336756, "tid": 1336756, + "ts": 1655274357751.548, "dur": 9.505, + "args": { + "External id": 4051227,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[65536], []], "Ev Idx": 9138 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::ne", "pid": 1336756, "tid": 1336756, + "ts": 1655274357768.011, "dur": 20.819, + "args": { + "External id": 4051228,"Record function id": 0, "Concrete Inputs": ["", "-100"], "Input type": ["long int", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[65536], []], "Ev Idx": 9139 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 1336756, "tid": 1336756, + "ts": 1655274357791.368, "dur": 44.598, + "args": { + "External id": 4051229,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["bool", ""], "Input Strides": [[1], []], "Input Dims": [[65536], []], "Ev Idx": 9140 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 1336756, "tid": 1336756, + "ts": 1655274357793.303, "dur": 42.249, + "args": { + "External id": 4051230,"Record function id": 0, "Concrete Inputs": ["", "[]", "False", ""], "Input type": ["bool", "ScalarList", "Scalar", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 9141 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274357799.070, "dur": 1.025, + "args": { + "External id": 4051231,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[0]", ""], "Input type": ["long int", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 9142 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655274357801.437, "dur": 20.212, + "args": { + "External id": 4051232,"Record function id": 0, "Concrete Inputs": ["", "4", "False", "False", ""], "Input type": ["bool", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 9143 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336756, "tid": 1336756, + "ts": 1655274357802.963, "dur": 18.339, + "args": { + "External id": 4051233,"Record function id": 0, "Concrete Inputs": ["", "4", "", "", "", "False", ""], "Input type": ["bool", "Scalar", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[65536], [], [], [], [], [], []], "Ev Idx": 9144 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274357805.357, "dur": 2.498, + "args": { + "External id": 4051234,"Record function id": 0, "Concrete Inputs": ["[65536]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9145 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1336756, + "ts": 1655274357808.566, "dur": 12.351, + "args": { + "External id": 4051235,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["long int", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[65536], [65536], []], "Ev Idx": 9146 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::item", "pid": 1336756, "tid": 1336756, + "ts": 1655274357839.737, "dur": 36082.959, + "args": { + "External id": 4051236,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["long int"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 9147 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_local_scalar_dense", "pid": 1336756, "tid": 1336756, + "ts": 1655274357841.348, "dur": 36080.377, + "args": { + "External id": 4051237,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["long int"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 9148 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1336756, + "ts": 1655274393946.349, "dur": 8.759, + "args": { + "External id": 4051238,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "8192", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], [], [], []], "Input Dims": [[65536, 2048], [], [], [], []], "Ev Idx": 9149 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274393952.594, "dur": 0.927, + "args": { + "External id": 4051239,"Record function id": 0, "Concrete Inputs": ["", "[8192, 2048]", "[2048, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[65536, 2048], [], [], []], "Ev Idx": 9150 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336756, "tid": 1336756, + "ts": 1655274393959.735, "dur": 129.239, + "args": { + "External id": 4051240,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[8192, 2048], [32000, 2048], []], "Ev Idx": 9151 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1336756, + "ts": 1655274393961.188, "dur": 5.757, + "args": { + "External id": 4051241,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[32000, 2048]], "Ev Idx": 9152 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1336756, + "ts": 1655274393963.527, "dur": 2.565, + "args": { + "External id": 4051242,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[32000, 2048], [], []], "Ev Idx": 9153 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274393965.220, "dur": 0.571, + "args": { + "External id": 4051243,"Record function id": 0, "Concrete Inputs": ["", "[2048, 32000]", "[1, 2048]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[32000, 2048], [], [], []], "Ev Idx": 9154 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336756, "tid": 1336756, + "ts": 1655274393968.120, "dur": 120.000, + "args": { + "External id": 4051244,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048]], "Input Dims": [[8192, 2048], [2048, 32000]], "Ev Idx": 9155 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274393971.703, "dur": 115.067, + "args": { + "External id": 4051245,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048]], "Input Dims": [[8192, 2048], [2048, 32000]], "Ev Idx": 9156 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1336756, + "ts": 1655274394094.557, "dur": 4.376, + "args": { + "External id": 4051246,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "8192", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 9157 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274394096.926, "dur": 0.627, + "args": { + "External id": 4051247,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "0"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 9158 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274394105.776, "dur": 2.152, + "args": { + "External id": 4051248,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[8192, 32000], []], "Ev Idx": 9159 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274394116.232, "dur": 6.781, + "args": { + "External id": 4051249,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[8192, 32000], [], [], [], [], []], "Ev Idx": 9160 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274394118.389, "dur": 4.316, + "args": { + "External id": 4051250,"Record function id": 0, "Concrete Inputs": ["[8192, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9161 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 1336756, "tid": 1336756, + "ts": 1655274394252.436, "dur": 206.165, + "args": { + "External id": 4051251,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 9162 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274394256.458, "dur": 2.212, + "args": { + "External id": 4051252,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9163 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 1336756, "tid": 1336756, + "ts": 1655274394259.978, "dur": 198.130, + "args": { + "External id": 4051253,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[8192, 1], [], [], [0]], "Ev Idx": 9164 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 1336756, "tid": 1336756, + "ts": 1655274394261.552, "dur": 0.493, + "args": { + "External id": 4051254,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 9165 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 1336756, "tid": 1336756, + "ts": 1655274394263.472, "dur": 24.186, + "args": { + "External id": 4051255,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 9166 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 1336756, "tid": 1336756, + "ts": 1655274394289.119, "dur": 5.173, + "args": { + "External id": 4051256,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[8192, 1], []], "Ev Idx": 9167 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274394293.153, "dur": 0.827, + "args": { + "External id": 4051257,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[8192, 1], [], [], []], "Ev Idx": 9168 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336756, "tid": 1336756, + "ts": 1655274394295.250, "dur": 25.266, + "args": { + "External id": 4051258,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 9169 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274394296.348, "dur": 1.415, + "args": { + "External id": 4051259,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9170 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336756, "tid": 1336756, + "ts": 1655274394300.799, "dur": 19.376, + "args": { + "External id": 4051260,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[8192], [0]], "Ev Idx": 9171 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336756, "tid": 1336756, + "ts": 1655274394304.712, "dur": 2.899, + "args": { + "External id": 4051261,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 9172 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 1336756, "tid": 1336756, + "ts": 1655274394322.161, "dur": 22.752, + "args": { + "External id": 4051262,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 9173 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 1336756, "tid": 1336756, + "ts": 1655274394346.751, "dur": 14.770, + "args": { + "External id": 4051263,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 9174 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 1336756, "tid": 1336756, + "ts": 1655274394364.851, "dur": 13.484, + "args": { + "External id": 4051264,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[8192, 1], [8192, 1], []], "Ev Idx": 9175 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 1336756, "tid": 1336756, + "ts": 1655274394379.822, "dur": 13.187, + "args": { + "External id": 4051265,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 9176 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 1336756, "tid": 1336756, + "ts": 1655274394394.597, "dur": 33.322, + "args": { + "External id": 4051266,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[8192, 1], [], [], [], [0]], "Ev Idx": 9177 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336756, "tid": 1336756, + "ts": 1655274394396.298, "dur": 1.651, + "args": { + "External id": 4051267,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 9178 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274394401.693, "dur": 0.597, + "args": { + "External id": 4051268,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[8192], [], [], []], "Ev Idx": 9179 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 1336756, "tid": 1336756, + "ts": 1655274394431.053, "dur": 13.623, + "args": { + "External id": 4051269,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 9180 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336756, "tid": 1336756, + "ts": 1655274394445.872, "dur": 10.920, + "args": { + "External id": 4051270,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 9181 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274394466.347, "dur": 2.696, + "args": { + "External id": 4051271,"Record function id": 0, "Concrete Inputs": ["", "[8192]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 9182 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1336756, + "ts": 1655274394476.291, "dur": 4.113, + "args": { + "External id": 4051272,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "8192", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 9183 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274394478.660, "dur": 0.877, + "args": { + "External id": 4051273,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 9184 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274394557.376, "dur": 66.790, + "args": { + "External id": 4051274,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [2048, 1]], "Input Dims": [[8192, 32000], [32000, 2048]], "Ev Idx": 9185 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1336756, + "ts": 1655274394629.582, "dur": 7.373, + "args": { + "External id": 4051275,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "8192", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], [], [], []], "Input Dims": [[65536, 2048], [], [], [], []], "Ev Idx": 9186 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274394633.742, "dur": 0.899, + "args": { + "External id": 4051276,"Record function id": 0, "Concrete Inputs": ["", "[8192, 2048]", "[2048, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[65536, 2048], [], [], []], "Ev Idx": 9187 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1336756, + "ts": 1655274394638.765, "dur": 28.155, + "args": { + "External id": 4051277,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[8192, 2048], [8192, 2048], []], "Ev Idx": 9188 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1336756, + "ts": 1655274394672.834, "dur": 6.648, + "args": { + "External id": 4051278,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[8192, 32000]], "Ev Idx": 9189 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1336756, + "ts": 1655274394675.049, "dur": 3.467, + "args": { + "External id": 4051279,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[8192, 32000], [], []], "Ev Idx": 9190 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274394676.929, "dur": 1.335, + "args": { + "External id": 4051280,"Record function id": 0, "Concrete Inputs": ["", "[32000, 8192]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[8192, 32000], [], [], []], "Ev Idx": 9191 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336756, "tid": 1336756, + "ts": 1655274394682.569, "dur": 45.891, + "args": { + "External id": 4051281,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [2048, 1]], "Input Dims": [[32000, 8192], [8192, 2048]], "Ev Idx": 9192 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274394685.415, "dur": 42.410, + "args": { + "External id": 4051282,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [2048, 1]], "Input Dims": [[32000, 8192], [8192, 2048]], "Ev Idx": 9193 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336756, "tid": 1336756, + "ts": 1655274394732.652, "dur": 14.347, + "args": { + "External id": 4051283,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[32000, 2048], [32000, 2048], []], "Ev Idx": 9194 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1336756, + "ts": 1655274394753.071, "dur": 3.581, + "args": { + "External id": 4051284,"Record function id": 0, "Concrete Inputs": ["", "0", "8192", "16384", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], [], [], []], "Input Dims": [[65536, 2048], [], [], [], []], "Ev Idx": 9195 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274394754.872, "dur": 0.863, + "args": { + "External id": 4051285,"Record function id": 0, "Concrete Inputs": ["", "[8192, 2048]", "[2048, 1]", "16777216"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[65536, 2048], [], [], []], "Ev Idx": 9196 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336756, "tid": 1336756, + "ts": 1655274394761.129, "dur": 47.898, + "args": { + "External id": 4051286,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[8192, 2048], [32000, 2048], []], "Ev Idx": 9197 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1336756, + "ts": 1655274394762.145, "dur": 4.897, + "args": { + "External id": 4051287,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[32000, 2048]], "Ev Idx": 9198 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1336756, + "ts": 1655274394762.877, "dur": 3.607, + "args": { + "External id": 4051288,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[32000, 2048], [], []], "Ev Idx": 9199 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274394765.634, "dur": 0.663, + "args": { + "External id": 4051289,"Record function id": 0, "Concrete Inputs": ["", "[2048, 32000]", "[1, 2048]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[32000, 2048], [], [], []], "Ev Idx": 9200 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336756, "tid": 1336756, + "ts": 1655274394767.845, "dur": 40.749, + "args": { + "External id": 4051290,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048]], "Input Dims": [[8192, 2048], [2048, 32000]], "Ev Idx": 9201 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274394768.385, "dur": 39.657, + "args": { + "External id": 4051291,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048]], "Input Dims": [[8192, 2048], [2048, 32000]], "Ev Idx": 9202 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1336756, + "ts": 1655274394813.212, "dur": 5.058, + "args": { + "External id": 4051292,"Record function id": 0, "Concrete Inputs": ["", "0", "8192", "16384", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 9203 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274394814.751, "dur": 2.394, + "args": { + "External id": 4051293,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "8192"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 9204 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274394823.778, "dur": 1.470, + "args": { + "External id": 4051294,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[8192, 32000], []], "Ev Idx": 9205 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274394834.376, "dur": 6.211, + "args": { + "External id": 4051295,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[8192, 32000], [], [], [], [], []], "Ev Idx": 9206 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274394836.146, "dur": 4.170, + "args": { + "External id": 4051296,"Record function id": 0, "Concrete Inputs": ["[8192, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9207 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 1336756, "tid": 1336756, + "ts": 1655274394928.966, "dur": 221.390, + "args": { + "External id": 4051297,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 9208 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274394935.682, "dur": 2.869, + "args": { + "External id": 4051298,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9209 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 1336756, "tid": 1336756, + "ts": 1655274394941.302, "dur": 208.590, + "args": { + "External id": 4051299,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[8192, 1], [], [], [0]], "Ev Idx": 9210 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 1336756, "tid": 1336756, + "ts": 1655274394942.383, "dur": 0.216, + "args": { + "External id": 4051300,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 9211 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 1336756, "tid": 1336756, + "ts": 1655274394945.840, "dur": 20.178, + "args": { + "External id": 4051301,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 9212 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 1336756, "tid": 1336756, + "ts": 1655274394967.479, "dur": 6.836, + "args": { + "External id": 4051302,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[8192, 1], []], "Ev Idx": 9213 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274394971.080, "dur": 2.928, + "args": { + "External id": 4051303,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[8192, 1], [], [], []], "Ev Idx": 9214 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336756, "tid": 1336756, + "ts": 1655274394975.257, "dur": 58.908, + "args": { + "External id": 4051304,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 9215 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274394976.239, "dur": 1.596, + "args": { + "External id": 4051305,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9216 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336756, "tid": 1336756, + "ts": 1655274394978.969, "dur": 54.868, + "args": { + "External id": 4051306,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[8192], [0]], "Ev Idx": 9217 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336756, "tid": 1336756, + "ts": 1655274395016.486, "dur": 3.619, + "args": { + "External id": 4051307,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 9218 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 1336756, "tid": 1336756, + "ts": 1655274395035.655, "dur": 21.842, + "args": { + "External id": 4051308,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 9219 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 1336756, "tid": 1336756, + "ts": 1655274395059.065, "dur": 12.296, + "args": { + "External id": 4051309,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 9220 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 1336756, "tid": 1336756, + "ts": 1655274395075.506, "dur": 13.613, + "args": { + "External id": 4051310,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[8192, 1], [8192, 1], []], "Ev Idx": 9221 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 1336756, "tid": 1336756, + "ts": 1655274395090.473, "dur": 11.456, + "args": { + "External id": 4051311,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 9222 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 1336756, "tid": 1336756, + "ts": 1655274395103.750, "dur": 20.104, + "args": { + "External id": 4051312,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[8192, 1], [], [], [], [0]], "Ev Idx": 9223 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336756, "tid": 1336756, + "ts": 1655274395105.389, "dur": 1.503, + "args": { + "External id": 4051313,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 9224 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274395108.944, "dur": 2.017, + "args": { + "External id": 4051314,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[8192], [], [], []], "Ev Idx": 9225 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 1336756, "tid": 1336756, + "ts": 1655274395125.341, "dur": 11.096, + "args": { + "External id": 4051315,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 9226 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336756, "tid": 1336756, + "ts": 1655274395137.524, "dur": 11.312, + "args": { + "External id": 4051316,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 9227 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274395159.853, "dur": 2.232, + "args": { + "External id": 4051317,"Record function id": 0, "Concrete Inputs": ["", "[8192]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 9228 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1336756, + "ts": 1655274395171.903, "dur": 3.509, + "args": { + "External id": 4051318,"Record function id": 0, "Concrete Inputs": ["", "0", "8192", "16384", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 9229 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274395174.008, "dur": 0.568, + "args": { + "External id": 4051319,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "8192"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 9230 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274395244.531, "dur": 56.430, + "args": { + "External id": 4051320,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [2048, 1]], "Input Dims": [[8192, 32000], [32000, 2048]], "Ev Idx": 9231 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1336756, + "ts": 1655274395306.017, "dur": 4.413, + "args": { + "External id": 4051321,"Record function id": 0, "Concrete Inputs": ["", "0", "8192", "16384", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], [], [], []], "Input Dims": [[65536, 2048], [], [], [], []], "Ev Idx": 9232 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274395308.483, "dur": 0.951, + "args": { + "External id": 4051322,"Record function id": 0, "Concrete Inputs": ["", "[8192, 2048]", "[2048, 1]", "16777216"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[65536, 2048], [], [], []], "Ev Idx": 9233 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1336756, + "ts": 1655274395311.930, "dur": 23.238, + "args": { + "External id": 4051323,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[8192, 2048], [8192, 2048], []], "Ev Idx": 9234 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1336756, + "ts": 1655274395339.664, "dur": 7.545, + "args": { + "External id": 4051324,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[8192, 32000]], "Ev Idx": 9235 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1336756, + "ts": 1655274395342.988, "dur": 3.616, + "args": { + "External id": 4051325,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[8192, 32000], [], []], "Ev Idx": 9236 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274395344.677, "dur": 1.688, + "args": { + "External id": 4051326,"Record function id": 0, "Concrete Inputs": ["", "[32000, 8192]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[8192, 32000], [], [], []], "Ev Idx": 9237 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336756, "tid": 1336756, + "ts": 1655274395350.164, "dur": 40.969, + "args": { + "External id": 4051327,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [2048, 1]], "Input Dims": [[32000, 8192], [8192, 2048]], "Ev Idx": 9238 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274395351.191, "dur": 39.295, + "args": { + "External id": 4051328,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [2048, 1]], "Input Dims": [[32000, 8192], [8192, 2048]], "Ev Idx": 9239 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336756, "tid": 1336756, + "ts": 1655274395395.046, "dur": 13.850, + "args": { + "External id": 4051329,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[32000, 2048], [32000, 2048], []], "Ev Idx": 9240 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1336756, + "ts": 1655274395414.404, "dur": 20.969, + "args": { + "External id": 4051330,"Record function id": 0, "Concrete Inputs": ["", "0", "16384", "24576", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], [], [], []], "Input Dims": [[65536, 2048], [], [], [], []], "Ev Idx": 9241 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274395432.806, "dur": 1.158, + "args": { + "External id": 4051331,"Record function id": 0, "Concrete Inputs": ["", "[8192, 2048]", "[2048, 1]", "33554432"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[65536, 2048], [], [], []], "Ev Idx": 9242 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336756, "tid": 1336756, + "ts": 1655274395440.895, "dur": 51.238, + "args": { + "External id": 4051332,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[8192, 2048], [32000, 2048], []], "Ev Idx": 9243 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1336756, + "ts": 1655274395441.635, "dur": 3.727, + "args": { + "External id": 4051333,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[32000, 2048]], "Ev Idx": 9244 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1336756, + "ts": 1655274395442.701, "dur": 2.131, + "args": { + "External id": 4051334,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[32000, 2048], [], []], "Ev Idx": 9245 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274395444.106, "dur": 0.594, + "args": { + "External id": 4051335,"Record function id": 0, "Concrete Inputs": ["", "[2048, 32000]", "[1, 2048]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[32000, 2048], [], [], []], "Ev Idx": 9246 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336756, "tid": 1336756, + "ts": 1655274395445.945, "dur": 45.835, + "args": { + "External id": 4051336,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048]], "Input Dims": [[8192, 2048], [2048, 32000]], "Ev Idx": 9247 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274395446.760, "dur": 44.388, + "args": { + "External id": 4051337,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048]], "Input Dims": [[8192, 2048], [2048, 32000]], "Ev Idx": 9248 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1336756, + "ts": 1655274395496.919, "dur": 3.867, + "args": { + "External id": 4051338,"Record function id": 0, "Concrete Inputs": ["", "0", "16384", "24576", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 9249 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274395499.240, "dur": 0.576, + "args": { + "External id": 4051339,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "16384"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 9250 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274395508.039, "dur": 1.250, + "args": { + "External id": 4051340,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[8192, 32000], []], "Ev Idx": 9251 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274395516.310, "dur": 6.522, + "args": { + "External id": 4051341,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[8192, 32000], [], [], [], [], []], "Ev Idx": 9252 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274395518.387, "dur": 4.194, + "args": { + "External id": 4051342,"Record function id": 0, "Concrete Inputs": ["[8192, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9253 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 1336756, "tid": 1336756, + "ts": 1655274395606.919, "dur": 171.942, + "args": { + "External id": 4051343,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 9254 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274395611.167, "dur": 1.960, + "args": { + "External id": 4051344,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9255 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 1336756, "tid": 1336756, + "ts": 1655274395615.935, "dur": 162.343, + "args": { + "External id": 4051345,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[8192, 1], [], [], [0]], "Ev Idx": 9256 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 1336756, "tid": 1336756, + "ts": 1655274395617.147, "dur": 0.344, + "args": { + "External id": 4051346,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 9257 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 1336756, "tid": 1336756, + "ts": 1655274395618.437, "dur": 19.694, + "args": { + "External id": 4051347,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 9258 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 1336756, "tid": 1336756, + "ts": 1655274395639.651, "dur": 4.822, + "args": { + "External id": 4051348,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[8192, 1], []], "Ev Idx": 9259 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274395643.336, "dur": 0.904, + "args": { + "External id": 4051349,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[8192, 1], [], [], []], "Ev Idx": 9260 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336756, "tid": 1336756, + "ts": 1655274395645.316, "dur": 19.916, + "args": { + "External id": 4051350,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 9261 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274395646.299, "dur": 1.731, + "args": { + "External id": 4051351,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9262 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336756, "tid": 1336756, + "ts": 1655274395649.136, "dur": 15.808, + "args": { + "External id": 4051352,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[8192], [0]], "Ev Idx": 9263 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336756, "tid": 1336756, + "ts": 1655274395651.703, "dur": 2.418, + "args": { + "External id": 4051353,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 9264 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 1336756, "tid": 1336756, + "ts": 1655274395666.414, "dur": 21.369, + "args": { + "External id": 4051354,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 9265 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 1336756, "tid": 1336756, + "ts": 1655274395689.057, "dur": 12.720, + "args": { + "External id": 4051355,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 9266 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 1336756, "tid": 1336756, + "ts": 1655274395706.209, "dur": 12.369, + "args": { + "External id": 4051356,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[8192, 1], [8192, 1], []], "Ev Idx": 9267 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 1336756, "tid": 1336756, + "ts": 1655274395719.769, "dur": 11.955, + "args": { + "External id": 4051357,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 9268 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 1336756, "tid": 1336756, + "ts": 1655274395733.247, "dur": 19.506, + "args": { + "External id": 4051358,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[8192, 1], [], [], [], [0]], "Ev Idx": 9269 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336756, "tid": 1336756, + "ts": 1655274395736.962, "dur": 1.372, + "args": { + "External id": 4051359,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 9270 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274395740.161, "dur": 0.669, + "args": { + "External id": 4051360,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[8192], [], [], []], "Ev Idx": 9271 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 1336756, "tid": 1336756, + "ts": 1655274395754.120, "dur": 11.096, + "args": { + "External id": 4051361,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 9272 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336756, "tid": 1336756, + "ts": 1655274395767.742, "dur": 9.536, + "args": { + "External id": 4051362,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 9273 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274395785.019, "dur": 1.609, + "args": { + "External id": 4051363,"Record function id": 0, "Concrete Inputs": ["", "[8192]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 9274 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1336756, + "ts": 1655274395794.925, "dur": 2.739, + "args": { + "External id": 4051364,"Record function id": 0, "Concrete Inputs": ["", "0", "16384", "24576", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 9275 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274395796.694, "dur": 0.286, + "args": { + "External id": 4051365,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "16384"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 9276 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274395857.675, "dur": 47.237, + "args": { + "External id": 4051366,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [2048, 1]], "Input Dims": [[8192, 32000], [32000, 2048]], "Ev Idx": 9277 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1336756, + "ts": 1655274395909.733, "dur": 4.966, + "args": { + "External id": 4051367,"Record function id": 0, "Concrete Inputs": ["", "0", "16384", "24576", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], [], [], []], "Input Dims": [[65536, 2048], [], [], [], []], "Ev Idx": 9278 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274395912.665, "dur": 1.162, + "args": { + "External id": 4051368,"Record function id": 0, "Concrete Inputs": ["", "[8192, 2048]", "[2048, 1]", "33554432"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[65536, 2048], [], [], []], "Ev Idx": 9279 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1336756, + "ts": 1655274395915.996, "dur": 27.812, + "args": { + "External id": 4051369,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[8192, 2048], [8192, 2048], []], "Ev Idx": 9280 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1336756, + "ts": 1655274395949.816, "dur": 5.180, + "args": { + "External id": 4051370,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[8192, 32000]], "Ev Idx": 9281 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1336756, + "ts": 1655274395951.402, "dur": 2.935, + "args": { + "External id": 4051371,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[8192, 32000], [], []], "Ev Idx": 9282 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274395952.924, "dur": 1.253, + "args": { + "External id": 4051372,"Record function id": 0, "Concrete Inputs": ["", "[32000, 8192]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[8192, 32000], [], [], []], "Ev Idx": 9283 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336756, "tid": 1336756, + "ts": 1655274395957.488, "dur": 104.364, + "args": { + "External id": 4051373,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [2048, 1]], "Input Dims": [[32000, 8192], [8192, 2048]], "Ev Idx": 9284 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274395958.542, "dur": 102.298, + "args": { + "External id": 4051374,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [2048, 1]], "Input Dims": [[32000, 8192], [8192, 2048]], "Ev Idx": 9285 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336756, "tid": 1336756, + "ts": 1655274396067.585, "dur": 35.113, + "args": { + "External id": 4051375,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[32000, 2048], [32000, 2048], []], "Ev Idx": 9286 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1336756, + "ts": 1655274396109.421, "dur": 6.056, + "args": { + "External id": 4051376,"Record function id": 0, "Concrete Inputs": ["", "0", "24576", "32768", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], [], [], []], "Input Dims": [[65536, 2048], [], [], [], []], "Ev Idx": 9287 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274396113.293, "dur": 1.181, + "args": { + "External id": 4051377,"Record function id": 0, "Concrete Inputs": ["", "[8192, 2048]", "[2048, 1]", "50331648"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[65536, 2048], [], [], []], "Ev Idx": 9288 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336756, "tid": 1336756, + "ts": 1655274396119.428, "dur": 70.329, + "args": { + "External id": 4051378,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[8192, 2048], [32000, 2048], []], "Ev Idx": 9289 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1336756, + "ts": 1655274396120.500, "dur": 3.640, + "args": { + "External id": 4051379,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[32000, 2048]], "Ev Idx": 9290 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1336756, + "ts": 1655274396121.481, "dur": 2.128, + "args": { + "External id": 4051380,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[32000, 2048], [], []], "Ev Idx": 9291 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274396122.795, "dur": 0.682, + "args": { + "External id": 4051381,"Record function id": 0, "Concrete Inputs": ["", "[2048, 32000]", "[1, 2048]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[32000, 2048], [], [], []], "Ev Idx": 9292 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336756, "tid": 1336756, + "ts": 1655274396124.984, "dur": 64.331, + "args": { + "External id": 4051382,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048]], "Input Dims": [[8192, 2048], [2048, 32000]], "Ev Idx": 9293 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274396127.260, "dur": 61.489, + "args": { + "External id": 4051383,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048]], "Input Dims": [[8192, 2048], [2048, 32000]], "Ev Idx": 9294 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1336756, + "ts": 1655274396193.247, "dur": 3.629, + "args": { + "External id": 4051384,"Record function id": 0, "Concrete Inputs": ["", "0", "24576", "32768", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 9295 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274396195.263, "dur": 0.696, + "args": { + "External id": 4051385,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "24576"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 9296 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274396202.310, "dur": 1.528, + "args": { + "External id": 4051386,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[8192, 32000], []], "Ev Idx": 9297 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274396210.862, "dur": 7.209, + "args": { + "External id": 4051387,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[8192, 32000], [], [], [], [], []], "Ev Idx": 9298 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274396214.161, "dur": 3.637, + "args": { + "External id": 4051388,"Record function id": 0, "Concrete Inputs": ["[8192, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9299 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 1336756, "tid": 1336756, + "ts": 1655274396302.712, "dur": 186.000, + "args": { + "External id": 4051389,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 9300 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274396306.203, "dur": 2.104, + "args": { + "External id": 4051390,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9301 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 1336756, "tid": 1336756, + "ts": 1655274396309.713, "dur": 178.328, + "args": { + "External id": 4051391,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[8192, 1], [], [], [0]], "Ev Idx": 9302 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 1336756, "tid": 1336756, + "ts": 1655274396310.942, "dur": 0.517, + "args": { + "External id": 4051392,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 9303 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 1336756, "tid": 1336756, + "ts": 1655274396312.651, "dur": 19.499, + "args": { + "External id": 4051393,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 9304 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 1336756, "tid": 1336756, + "ts": 1655274396333.635, "dur": 4.383, + "args": { + "External id": 4051394,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[8192, 1], []], "Ev Idx": 9305 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274396337.122, "dur": 0.658, + "args": { + "External id": 4051395,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[8192, 1], [], [], []], "Ev Idx": 9306 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336756, "tid": 1336756, + "ts": 1655274396338.850, "dur": 21.231, + "args": { + "External id": 4051396,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 9307 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274396341.426, "dur": 1.293, + "args": { + "External id": 4051397,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9308 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336756, "tid": 1336756, + "ts": 1655274396343.852, "dur": 15.957, + "args": { + "External id": 4051398,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[8192], [0]], "Ev Idx": 9309 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336756, "tid": 1336756, + "ts": 1655274396346.393, "dur": 2.193, + "args": { + "External id": 4051399,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 9310 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 1336756, "tid": 1336756, + "ts": 1655274396361.301, "dur": 20.286, + "args": { + "External id": 4051400,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 9311 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 1336756, "tid": 1336756, + "ts": 1655274396383.074, "dur": 12.452, + "args": { + "External id": 4051401,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 9312 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 1336756, "tid": 1336756, + "ts": 1655274396397.915, "dur": 12.855, + "args": { + "External id": 4051402,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[8192, 1], [8192, 1], []], "Ev Idx": 9313 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 1336756, "tid": 1336756, + "ts": 1655274396412.019, "dur": 25.773, + "args": { + "External id": 4051403,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 9314 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 1336756, "tid": 1336756, + "ts": 1655274396440.412, "dur": 21.002, + "args": { + "External id": 4051404,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[8192, 1], [], [], [], [0]], "Ev Idx": 9315 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336756, "tid": 1336756, + "ts": 1655274396442.158, "dur": 1.714, + "args": { + "External id": 4051405,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 9316 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274396447.156, "dur": 0.954, + "args": { + "External id": 4051406,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[8192], [], [], []], "Ev Idx": 9317 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 1336756, "tid": 1336756, + "ts": 1655274396462.905, "dur": 11.890, + "args": { + "External id": 4051407,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 9318 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336756, "tid": 1336756, + "ts": 1655274396475.912, "dur": 11.173, + "args": { + "External id": 4051408,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 9319 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274396495.798, "dur": 2.201, + "args": { + "External id": 4051409,"Record function id": 0, "Concrete Inputs": ["", "[8192]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 9320 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1336756, + "ts": 1655274396506.378, "dur": 3.432, + "args": { + "External id": 4051410,"Record function id": 0, "Concrete Inputs": ["", "0", "24576", "32768", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 9321 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274396508.529, "dur": 0.513, + "args": { + "External id": 4051411,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "24576"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 9322 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274396575.791, "dur": 54.799, + "args": { + "External id": 4051412,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [2048, 1]], "Input Dims": [[8192, 32000], [32000, 2048]], "Ev Idx": 9323 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1336756, + "ts": 1655274396635.213, "dur": 6.734, + "args": { + "External id": 4051413,"Record function id": 0, "Concrete Inputs": ["", "0", "24576", "32768", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], [], [], []], "Input Dims": [[65536, 2048], [], [], [], []], "Ev Idx": 9324 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274396639.933, "dur": 0.955, + "args": { + "External id": 4051414,"Record function id": 0, "Concrete Inputs": ["", "[8192, 2048]", "[2048, 1]", "50331648"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[65536, 2048], [], [], []], "Ev Idx": 9325 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1336756, + "ts": 1655274396643.407, "dur": 23.381, + "args": { + "External id": 4051415,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[8192, 2048], [8192, 2048], []], "Ev Idx": 9326 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1336756, + "ts": 1655274396671.294, "dur": 5.884, + "args": { + "External id": 4051416,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[8192, 32000]], "Ev Idx": 9327 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1336756, + "ts": 1655274396672.923, "dur": 3.708, + "args": { + "External id": 4051417,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[8192, 32000], [], []], "Ev Idx": 9328 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274396674.816, "dur": 1.628, + "args": { + "External id": 4051418,"Record function id": 0, "Concrete Inputs": ["", "[32000, 8192]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[8192, 32000], [], [], []], "Ev Idx": 9329 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336756, "tid": 1336756, + "ts": 1655274396679.975, "dur": 42.104, + "args": { + "External id": 4051419,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [2048, 1]], "Input Dims": [[32000, 8192], [8192, 2048]], "Ev Idx": 9330 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274396682.738, "dur": 38.697, + "args": { + "External id": 4051420,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [2048, 1]], "Input Dims": [[32000, 8192], [8192, 2048]], "Ev Idx": 9331 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336756, "tid": 1336756, + "ts": 1655274396725.897, "dur": 13.423, + "args": { + "External id": 4051421,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[32000, 2048], [32000, 2048], []], "Ev Idx": 9332 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1336756, + "ts": 1655274396744.938, "dur": 3.478, + "args": { + "External id": 4051422,"Record function id": 0, "Concrete Inputs": ["", "0", "32768", "40960", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], [], [], []], "Input Dims": [[65536, 2048], [], [], [], []], "Ev Idx": 9333 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274396747.048, "dur": 0.694, + "args": { + "External id": 4051423,"Record function id": 0, "Concrete Inputs": ["", "[8192, 2048]", "[2048, 1]", "67108864"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[65536, 2048], [], [], []], "Ev Idx": 9334 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336756, "tid": 1336756, + "ts": 1655274396752.114, "dur": 47.135, + "args": { + "External id": 4051424,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[8192, 2048], [32000, 2048], []], "Ev Idx": 9335 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1336756, + "ts": 1655274396752.783, "dur": 5.157, + "args": { + "External id": 4051425,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[32000, 2048]], "Ev Idx": 9336 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1336756, + "ts": 1655274396753.680, "dur": 3.533, + "args": { + "External id": 4051426,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[32000, 2048], [], []], "Ev Idx": 9337 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274396756.503, "dur": 0.583, + "args": { + "External id": 4051427,"Record function id": 0, "Concrete Inputs": ["", "[2048, 32000]", "[1, 2048]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[32000, 2048], [], [], []], "Ev Idx": 9338 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336756, "tid": 1336756, + "ts": 1655274396758.443, "dur": 40.393, + "args": { + "External id": 4051428,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048]], "Input Dims": [[8192, 2048], [2048, 32000]], "Ev Idx": 9339 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274396758.885, "dur": 39.478, + "args": { + "External id": 4051429,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048]], "Input Dims": [[8192, 2048], [2048, 32000]], "Ev Idx": 9340 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1336756, + "ts": 1655274396803.282, "dur": 5.208, + "args": { + "External id": 4051430,"Record function id": 0, "Concrete Inputs": ["", "0", "32768", "40960", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 9341 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274396805.082, "dur": 2.362, + "args": { + "External id": 4051431,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "32768"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 9342 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274396813.670, "dur": 1.719, + "args": { + "External id": 4051432,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[8192, 32000], []], "Ev Idx": 9343 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274396822.189, "dur": 7.481, + "args": { + "External id": 4051433,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[8192, 32000], [], [], [], [], []], "Ev Idx": 9344 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274396825.877, "dur": 3.533, + "args": { + "External id": 4051434,"Record function id": 0, "Concrete Inputs": ["[8192, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9345 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 1336756, "tid": 1336756, + "ts": 1655274396910.044, "dur": 208.752, + "args": { + "External id": 4051435,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 9346 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274396911.796, "dur": 2.122, + "args": { + "External id": 4051436,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9347 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 1336756, "tid": 1336756, + "ts": 1655274396915.441, "dur": 202.912, + "args": { + "External id": 4051437,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[8192, 1], [], [], [0]], "Ev Idx": 9348 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 1336756, "tid": 1336756, + "ts": 1655274396916.660, "dur": 0.335, + "args": { + "External id": 4051438,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 9349 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 1336756, "tid": 1336756, + "ts": 1655274396918.056, "dur": 19.850, + "args": { + "External id": 4051439,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 9350 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 1336756, "tid": 1336756, + "ts": 1655274396939.476, "dur": 3.097, + "args": { + "External id": 4051440,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[8192, 1], []], "Ev Idx": 9351 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274396941.228, "dur": 0.973, + "args": { + "External id": 4051441,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[8192, 1], [], [], []], "Ev Idx": 9352 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336756, "tid": 1336756, + "ts": 1655274396945.207, "dur": 21.298, + "args": { + "External id": 4051442,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 9353 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274396946.374, "dur": 1.717, + "args": { + "External id": 4051443,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9354 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336756, "tid": 1336756, + "ts": 1655274396949.111, "dur": 17.100, + "args": { + "External id": 4051444,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[8192], [0]], "Ev Idx": 9355 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336756, "tid": 1336756, + "ts": 1655274396953.513, "dur": 2.057, + "args": { + "External id": 4051445,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 9356 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 1336756, "tid": 1336756, + "ts": 1655274396967.791, "dur": 56.357, + "args": { + "External id": 4051446,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 9357 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 1336756, "tid": 1336756, + "ts": 1655274397026.655, "dur": 13.770, + "args": { + "External id": 4051447,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 9358 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 1336756, "tid": 1336756, + "ts": 1655274397043.709, "dur": 13.335, + "args": { + "External id": 4051448,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[8192, 1], [8192, 1], []], "Ev Idx": 9359 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 1336756, "tid": 1336756, + "ts": 1655274397058.565, "dur": 11.715, + "args": { + "External id": 4051449,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 9360 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 1336756, "tid": 1336756, + "ts": 1655274397072.154, "dur": 20.878, + "args": { + "External id": 4051450,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[8192, 1], [], [], [], [0]], "Ev Idx": 9361 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336756, "tid": 1336756, + "ts": 1655274397075.725, "dur": 1.715, + "args": { + "External id": 4051451,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 9362 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274397079.218, "dur": 1.013, + "args": { + "External id": 4051452,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[8192], [], [], []], "Ev Idx": 9363 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 1336756, "tid": 1336756, + "ts": 1655274397094.218, "dur": 11.314, + "args": { + "External id": 4051453,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 9364 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336756, "tid": 1336756, + "ts": 1655274397106.711, "dur": 10.728, + "args": { + "External id": 4051454,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 9365 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274397126.361, "dur": 2.269, + "args": { + "External id": 4051455,"Record function id": 0, "Concrete Inputs": ["", "[8192]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 9366 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1336756, + "ts": 1655274397137.761, "dur": 38.091, + "args": { + "External id": 4051456,"Record function id": 0, "Concrete Inputs": ["", "0", "32768", "40960", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 9367 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274397174.602, "dur": 0.403, + "args": { + "External id": 4051457,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "32768"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 9368 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274397249.813, "dur": 56.611, + "args": { + "External id": 4051458,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [2048, 1]], "Input Dims": [[8192, 32000], [32000, 2048]], "Ev Idx": 9369 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1336756, + "ts": 1655274397311.448, "dur": 6.249, + "args": { + "External id": 4051459,"Record function id": 0, "Concrete Inputs": ["", "0", "32768", "40960", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], [], [], []], "Input Dims": [[65536, 2048], [], [], [], []], "Ev Idx": 9370 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274397314.266, "dur": 2.265, + "args": { + "External id": 4051460,"Record function id": 0, "Concrete Inputs": ["", "[8192, 2048]", "[2048, 1]", "67108864"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[65536, 2048], [], [], []], "Ev Idx": 9371 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1336756, + "ts": 1655274397319.219, "dur": 21.818, + "args": { + "External id": 4051461,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[8192, 2048], [8192, 2048], []], "Ev Idx": 9372 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1336756, + "ts": 1655274397345.622, "dur": 6.515, + "args": { + "External id": 4051462,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[8192, 32000]], "Ev Idx": 9373 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1336756, + "ts": 1655274397347.070, "dur": 4.506, + "args": { + "External id": 4051463,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[8192, 32000], [], []], "Ev Idx": 9374 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274397350.488, "dur": 0.869, + "args": { + "External id": 4051464,"Record function id": 0, "Concrete Inputs": ["", "[32000, 8192]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[8192, 32000], [], [], []], "Ev Idx": 9375 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336756, "tid": 1336756, + "ts": 1655274397354.806, "dur": 39.814, + "args": { + "External id": 4051465,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [2048, 1]], "Input Dims": [[32000, 8192], [8192, 2048]], "Ev Idx": 9376 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274397355.804, "dur": 38.403, + "args": { + "External id": 4051466,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [2048, 1]], "Input Dims": [[32000, 8192], [8192, 2048]], "Ev Idx": 9377 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336756, "tid": 1336756, + "ts": 1655274397398.467, "dur": 13.382, + "args": { + "External id": 4051467,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[32000, 2048], [32000, 2048], []], "Ev Idx": 9378 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1336756, + "ts": 1655274397433.925, "dur": 4.573, + "args": { + "External id": 4051468,"Record function id": 0, "Concrete Inputs": ["", "0", "40960", "49152", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], [], [], []], "Input Dims": [[65536, 2048], [], [], [], []], "Ev Idx": 9379 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274397436.484, "dur": 0.836, + "args": { + "External id": 4051469,"Record function id": 0, "Concrete Inputs": ["", "[8192, 2048]", "[2048, 1]", "83886080"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[65536, 2048], [], [], []], "Ev Idx": 9380 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336756, "tid": 1336756, + "ts": 1655274397443.213, "dur": 51.605, + "args": { + "External id": 4051470,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[8192, 2048], [32000, 2048], []], "Ev Idx": 9381 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1336756, + "ts": 1655274397445.810, "dur": 3.188, + "args": { + "External id": 4051471,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[32000, 2048]], "Ev Idx": 9382 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1336756, + "ts": 1655274397446.550, "dur": 1.909, + "args": { + "External id": 4051472,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[32000, 2048], [], []], "Ev Idx": 9383 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274397447.660, "dur": 0.673, + "args": { + "External id": 4051473,"Record function id": 0, "Concrete Inputs": ["", "[2048, 32000]", "[1, 2048]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[32000, 2048], [], [], []], "Ev Idx": 9384 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336756, "tid": 1336756, + "ts": 1655274397449.615, "dur": 44.739, + "args": { + "External id": 4051474,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048]], "Input Dims": [[8192, 2048], [2048, 32000]], "Ev Idx": 9385 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274397450.256, "dur": 43.570, + "args": { + "External id": 4051475,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048]], "Input Dims": [[8192, 2048], [2048, 32000]], "Ev Idx": 9386 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1336756, + "ts": 1655274397498.973, "dur": 3.584, + "args": { + "External id": 4051476,"Record function id": 0, "Concrete Inputs": ["", "0", "40960", "49152", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 9387 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274397500.858, "dur": 0.818, + "args": { + "External id": 4051477,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "40960"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 9388 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274397509.572, "dur": 1.495, + "args": { + "External id": 4051478,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[8192, 32000], []], "Ev Idx": 9389 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274397518.691, "dur": 6.160, + "args": { + "External id": 4051479,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[8192, 32000], [], [], [], [], []], "Ev Idx": 9390 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274397520.317, "dur": 4.273, + "args": { + "External id": 4051480,"Record function id": 0, "Concrete Inputs": ["[8192, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9391 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 1336756, "tid": 1336756, + "ts": 1655274397608.330, "dur": 174.755, + "args": { + "External id": 4051481,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 9392 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274397610.674, "dur": 3.660, + "args": { + "External id": 4051482,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9393 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 1336756, "tid": 1336756, + "ts": 1655274397617.541, "dur": 165.155, + "args": { + "External id": 4051483,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[8192, 1], [], [], [0]], "Ev Idx": 9394 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 1336756, "tid": 1336756, + "ts": 1655274397618.983, "dur": 0.258, + "args": { + "External id": 4051484,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 9395 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 1336756, "tid": 1336756, + "ts": 1655274397620.154, "dur": 20.139, + "args": { + "External id": 4051485,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 9396 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 1336756, "tid": 1336756, + "ts": 1655274397642.397, "dur": 4.683, + "args": { + "External id": 4051486,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[8192, 1], []], "Ev Idx": 9397 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274397645.859, "dur": 0.991, + "args": { + "External id": 4051487,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[8192, 1], [], [], []], "Ev Idx": 9398 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336756, "tid": 1336756, + "ts": 1655274397647.988, "dur": 22.635, + "args": { + "External id": 4051488,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 9399 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274397649.102, "dur": 1.402, + "args": { + "External id": 4051489,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9400 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336756, "tid": 1336756, + "ts": 1655274397651.555, "dur": 18.650, + "args": { + "External id": 4051490,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[8192], [0]], "Ev Idx": 9401 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336756, "tid": 1336756, + "ts": 1655274397654.093, "dur": 3.003, + "args": { + "External id": 4051491,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 9402 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 1336756, "tid": 1336756, + "ts": 1655274397671.957, "dur": 20.701, + "args": { + "External id": 4051492,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 9403 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 1336756, "tid": 1336756, + "ts": 1655274397693.815, "dur": 12.295, + "args": { + "External id": 4051493,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 9404 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 1336756, "tid": 1336756, + "ts": 1655274397710.570, "dur": 12.290, + "args": { + "External id": 4051494,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[8192, 1], [8192, 1], []], "Ev Idx": 9405 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 1336756, "tid": 1336756, + "ts": 1655274397724.059, "dur": 11.274, + "args": { + "External id": 4051495,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 9406 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 1336756, "tid": 1336756, + "ts": 1655274397737.023, "dur": 19.911, + "args": { + "External id": 4051496,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[8192, 1], [], [], [], [0]], "Ev Idx": 9407 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336756, "tid": 1336756, + "ts": 1655274397738.394, "dur": 1.722, + "args": { + "External id": 4051497,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 9408 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274397741.857, "dur": 2.121, + "args": { + "External id": 4051498,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[8192], [], [], []], "Ev Idx": 9409 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 1336756, "tid": 1336756, + "ts": 1655274397758.241, "dur": 10.736, + "args": { + "External id": 4051499,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 9410 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336756, "tid": 1336756, + "ts": 1655274397771.796, "dur": 9.734, + "args": { + "External id": 4051500,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 9411 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274397788.779, "dur": 1.580, + "args": { + "External id": 4051501,"Record function id": 0, "Concrete Inputs": ["", "[8192]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 9412 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1336756, + "ts": 1655274397798.729, "dur": 3.317, + "args": { + "External id": 4051502,"Record function id": 0, "Concrete Inputs": ["", "0", "40960", "49152", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 9413 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274397800.835, "dur": 0.417, + "args": { + "External id": 4051503,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "40960"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 9414 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274397859.555, "dur": 47.058, + "args": { + "External id": 4051504,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [2048, 1]], "Input Dims": [[8192, 32000], [32000, 2048]], "Ev Idx": 9415 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1336756, + "ts": 1655274397911.184, "dur": 4.358, + "args": { + "External id": 4051505,"Record function id": 0, "Concrete Inputs": ["", "0", "40960", "49152", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], [], [], []], "Input Dims": [[65536, 2048], [], [], [], []], "Ev Idx": 9416 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274397913.568, "dur": 0.934, + "args": { + "External id": 4051506,"Record function id": 0, "Concrete Inputs": ["", "[8192, 2048]", "[2048, 1]", "83886080"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[65536, 2048], [], [], []], "Ev Idx": 9417 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1336756, + "ts": 1655274397916.787, "dur": 21.583, + "args": { + "External id": 4051507,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[8192, 2048], [8192, 2048], []], "Ev Idx": 9418 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1336756, + "ts": 1655274397944.184, "dur": 5.093, + "args": { + "External id": 4051508,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[8192, 32000]], "Ev Idx": 9419 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1336756, + "ts": 1655274397945.394, "dur": 3.261, + "args": { + "External id": 4051509,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[8192, 32000], [], []], "Ev Idx": 9420 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274397947.252, "dur": 1.229, + "args": { + "External id": 4051510,"Record function id": 0, "Concrete Inputs": ["", "[32000, 8192]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[8192, 32000], [], [], []], "Ev Idx": 9421 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336756, "tid": 1336756, + "ts": 1655274397951.777, "dur": 74.590, + "args": { + "External id": 4051511,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [2048, 1]], "Input Dims": [[32000, 8192], [8192, 2048]], "Ev Idx": 9422 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274397952.766, "dur": 72.390, + "args": { + "External id": 4051512,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [2048, 1]], "Input Dims": [[32000, 8192], [8192, 2048]], "Ev Idx": 9423 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336756, "tid": 1336756, + "ts": 1655274398032.003, "dur": 16.103, + "args": { + "External id": 4051513,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[32000, 2048], [32000, 2048], []], "Ev Idx": 9424 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1336756, + "ts": 1655274398054.653, "dur": 6.138, + "args": { + "External id": 4051514,"Record function id": 0, "Concrete Inputs": ["", "0", "49152", "57344", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], [], [], []], "Input Dims": [[65536, 2048], [], [], [], []], "Ev Idx": 9425 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274398058.932, "dur": 0.840, + "args": { + "External id": 4051515,"Record function id": 0, "Concrete Inputs": ["", "[8192, 2048]", "[2048, 1]", "100663296"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[65536, 2048], [], [], []], "Ev Idx": 9426 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336756, "tid": 1336756, + "ts": 1655274398064.725, "dur": 53.041, + "args": { + "External id": 4051516,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[8192, 2048], [32000, 2048], []], "Ev Idx": 9427 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1336756, + "ts": 1655274398065.547, "dur": 4.167, + "args": { + "External id": 4051517,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[32000, 2048]], "Ev Idx": 9428 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1336756, + "ts": 1655274398066.665, "dur": 2.489, + "args": { + "External id": 4051518,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[32000, 2048], [], []], "Ev Idx": 9429 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274398068.107, "dur": 0.878, + "args": { + "External id": 4051519,"Record function id": 0, "Concrete Inputs": ["", "[2048, 32000]", "[1, 2048]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[32000, 2048], [], [], []], "Ev Idx": 9430 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336756, "tid": 1336756, + "ts": 1655274398070.327, "dur": 47.044, + "args": { + "External id": 4051520,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048]], "Input Dims": [[8192, 2048], [2048, 32000]], "Ev Idx": 9431 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274398073.041, "dur": 43.784, + "args": { + "External id": 4051521,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048]], "Input Dims": [[8192, 2048], [2048, 32000]], "Ev Idx": 9432 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1336756, + "ts": 1655274398121.682, "dur": 3.533, + "args": { + "External id": 4051522,"Record function id": 0, "Concrete Inputs": ["", "0", "49152", "57344", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 9433 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274398123.616, "dur": 0.655, + "args": { + "External id": 4051523,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "49152"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 9434 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274398130.421, "dur": 1.453, + "args": { + "External id": 4051524,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[8192, 32000], []], "Ev Idx": 9435 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274398138.558, "dur": 5.989, + "args": { + "External id": 4051525,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[8192, 32000], [], [], [], [], []], "Ev Idx": 9436 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274398140.427, "dur": 3.867, + "args": { + "External id": 4051526,"Record function id": 0, "Concrete Inputs": ["[8192, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9437 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 1336756, "tid": 1336756, + "ts": 1655274398225.530, "dur": 172.387, + "args": { + "External id": 4051527,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 9438 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274398229.769, "dur": 2.011, + "args": { + "External id": 4051528,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9439 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 1336756, "tid": 1336756, + "ts": 1655274398232.791, "dur": 164.545, + "args": { + "External id": 4051529,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[8192, 1], [], [], [0]], "Ev Idx": 9440 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 1336756, "tid": 1336756, + "ts": 1655274398234.019, "dur": 0.309, + "args": { + "External id": 4051530,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 9441 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 1336756, "tid": 1336756, + "ts": 1655274398235.266, "dur": 19.614, + "args": { + "External id": 4051531,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 9442 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 1336756, "tid": 1336756, + "ts": 1655274398256.353, "dur": 4.393, + "args": { + "External id": 4051532,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[8192, 1], []], "Ev Idx": 9443 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274398259.914, "dur": 0.609, + "args": { + "External id": 4051533,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[8192, 1], [], [], []], "Ev Idx": 9444 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336756, "tid": 1336756, + "ts": 1655274398261.612, "dur": 21.443, + "args": { + "External id": 4051534,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 9445 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274398262.530, "dur": 1.331, + "args": { + "External id": 4051535,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9446 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336756, "tid": 1336756, + "ts": 1655274398264.850, "dur": 17.956, + "args": { + "External id": 4051536,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[8192], [0]], "Ev Idx": 9447 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336756, "tid": 1336756, + "ts": 1655274398268.983, "dur": 2.670, + "args": { + "External id": 4051537,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 9448 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 1336756, "tid": 1336756, + "ts": 1655274398284.490, "dur": 17.889, + "args": { + "External id": 4051538,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 9449 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 1336756, "tid": 1336756, + "ts": 1655274398303.502, "dur": 12.419, + "args": { + "External id": 4051539,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 9450 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 1336756, "tid": 1336756, + "ts": 1655274398318.053, "dur": 12.466, + "args": { + "External id": 4051540,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[8192, 1], [8192, 1], []], "Ev Idx": 9451 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 1336756, "tid": 1336756, + "ts": 1655274398331.634, "dur": 10.720, + "args": { + "External id": 4051541,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 9452 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 1336756, "tid": 1336756, + "ts": 1655274398343.861, "dur": 25.876, + "args": { + "External id": 4051542,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[8192, 1], [], [], [], [0]], "Ev Idx": 9453 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336756, "tid": 1336756, + "ts": 1655274398347.543, "dur": 1.173, + "args": { + "External id": 4051543,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 9454 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274398356.333, "dur": 1.077, + "args": { + "External id": 4051544,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[8192], [], [], []], "Ev Idx": 9455 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 1336756, "tid": 1336756, + "ts": 1655274398372.788, "dur": 10.895, + "args": { + "External id": 4051545,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 9456 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336756, "tid": 1336756, + "ts": 1655274398384.752, "dur": 11.361, + "args": { + "External id": 4051546,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 9457 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274398403.869, "dur": 1.604, + "args": { + "External id": 4051547,"Record function id": 0, "Concrete Inputs": ["", "[8192]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 9458 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1336756, + "ts": 1655274398412.679, "dur": 19.960, + "args": { + "External id": 4051548,"Record function id": 0, "Concrete Inputs": ["", "0", "49152", "57344", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 9459 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274398430.297, "dur": 0.848, + "args": { + "External id": 4051549,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "49152"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 9460 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274398497.562, "dur": 51.773, + "args": { + "External id": 4051550,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [2048, 1]], "Input Dims": [[8192, 32000], [32000, 2048]], "Ev Idx": 9461 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1336756, + "ts": 1655274398553.832, "dur": 6.723, + "args": { + "External id": 4051551,"Record function id": 0, "Concrete Inputs": ["", "0", "49152", "57344", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], [], [], []], "Input Dims": [[65536, 2048], [], [], [], []], "Ev Idx": 9462 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274398558.575, "dur": 0.956, + "args": { + "External id": 4051552,"Record function id": 0, "Concrete Inputs": ["", "[8192, 2048]", "[2048, 1]", "100663296"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[65536, 2048], [], [], []], "Ev Idx": 9463 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1336756, + "ts": 1655274398561.916, "dur": 21.615, + "args": { + "External id": 4051553,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[8192, 2048], [8192, 2048], []], "Ev Idx": 9464 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1336756, + "ts": 1655274398590.248, "dur": 6.531, + "args": { + "External id": 4051554,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[8192, 32000]], "Ev Idx": 9465 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1336756, + "ts": 1655274398591.603, "dur": 4.596, + "args": { + "External id": 4051555,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[8192, 32000], [], []], "Ev Idx": 9466 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274398593.659, "dur": 2.278, + "args": { + "External id": 4051556,"Record function id": 0, "Concrete Inputs": ["", "[32000, 8192]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[8192, 32000], [], [], []], "Ev Idx": 9467 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336756, "tid": 1336756, + "ts": 1655274398599.013, "dur": 39.268, + "args": { + "External id": 4051557,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [2048, 1]], "Input Dims": [[32000, 8192], [8192, 2048]], "Ev Idx": 9468 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274398599.901, "dur": 37.652, + "args": { + "External id": 4051558,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [2048, 1]], "Input Dims": [[32000, 8192], [8192, 2048]], "Ev Idx": 9469 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336756, "tid": 1336756, + "ts": 1655274398643.567, "dur": 14.151, + "args": { + "External id": 4051559,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[32000, 2048], [32000, 2048], []], "Ev Idx": 9470 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1336756, + "ts": 1655274398663.052, "dur": 3.427, + "args": { + "External id": 4051560,"Record function id": 0, "Concrete Inputs": ["", "0", "57344", "65536", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], [], [], []], "Input Dims": [[65536, 2048], [], [], [], []], "Ev Idx": 9471 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274398665.061, "dur": 0.686, + "args": { + "External id": 4051561,"Record function id": 0, "Concrete Inputs": ["", "[8192, 2048]", "[2048, 1]", "117440512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[65536, 2048], [], [], []], "Ev Idx": 9472 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336756, "tid": 1336756, + "ts": 1655274398669.960, "dur": 46.096, + "args": { + "External id": 4051562,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[8192, 2048], [32000, 2048], []], "Ev Idx": 9473 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1336756, + "ts": 1655274398670.786, "dur": 4.657, + "args": { + "External id": 4051563,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[32000, 2048]], "Ev Idx": 9474 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1336756, + "ts": 1655274398671.529, "dur": 3.234, + "args": { + "External id": 4051564,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[32000, 2048], [], []], "Ev Idx": 9475 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274398674.059, "dur": 0.555, + "args": { + "External id": 4051565,"Record function id": 0, "Concrete Inputs": ["", "[2048, 32000]", "[1, 2048]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[32000, 2048], [], [], []], "Ev Idx": 9476 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336756, "tid": 1336756, + "ts": 1655274398675.939, "dur": 39.631, + "args": { + "External id": 4051566,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048]], "Input Dims": [[8192, 2048], [2048, 32000]], "Ev Idx": 9477 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274398676.407, "dur": 38.576, + "args": { + "External id": 4051567,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048]], "Input Dims": [[8192, 2048], [2048, 32000]], "Ev Idx": 9478 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1336756, + "ts": 1655274398719.217, "dur": 3.618, + "args": { + "External id": 4051568,"Record function id": 0, "Concrete Inputs": ["", "0", "57344", "65536", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 9479 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274398721.193, "dur": 0.768, + "args": { + "External id": 4051569,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "57344"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 9480 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274398727.664, "dur": 1.406, + "args": { + "External id": 4051570,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[8192, 32000], []], "Ev Idx": 9481 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274398737.427, "dur": 5.544, + "args": { + "External id": 4051571,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[8192, 32000], [], [], [], [], []], "Ev Idx": 9482 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274398738.949, "dur": 3.770, + "args": { + "External id": 4051572,"Record function id": 0, "Concrete Inputs": ["[8192, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9483 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 1336756, "tid": 1336756, + "ts": 1655274398815.172, "dur": 160.948, + "args": { + "External id": 4051573,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 9484 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274398817.111, "dur": 2.402, + "args": { + "External id": 4051574,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9485 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 1336756, "tid": 1336756, + "ts": 1655274398822.422, "dur": 153.289, + "args": { + "External id": 4051575,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[8192, 1], [], [], [0]], "Ev Idx": 9486 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 1336756, "tid": 1336756, + "ts": 1655274398823.596, "dur": 0.402, + "args": { + "External id": 4051576,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 9487 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 1336756, "tid": 1336756, + "ts": 1655274398824.742, "dur": 18.151, + "args": { + "External id": 4051577,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 9488 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 1336756, "tid": 1336756, + "ts": 1655274398845.929, "dur": 3.741, + "args": { + "External id": 4051578,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[8192, 1], []], "Ev Idx": 9489 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274398847.464, "dur": 1.986, + "args": { + "External id": 4051579,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[8192, 1], [], [], []], "Ev Idx": 9490 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336756, "tid": 1336756, + "ts": 1655274398850.493, "dur": 18.009, + "args": { + "External id": 4051580,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 9491 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274398851.352, "dur": 1.241, + "args": { + "External id": 4051581,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9492 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336756, "tid": 1336756, + "ts": 1655274398853.913, "dur": 14.349, + "args": { + "External id": 4051582,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[8192], [0]], "Ev Idx": 9493 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336756, "tid": 1336756, + "ts": 1655274398855.954, "dur": 2.132, + "args": { + "External id": 4051583,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 9494 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 1336756, "tid": 1336756, + "ts": 1655274398869.733, "dur": 18.308, + "args": { + "External id": 4051584,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 9495 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 1336756, "tid": 1336756, + "ts": 1655274398889.397, "dur": 11.495, + "args": { + "External id": 4051585,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 9496 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 1336756, "tid": 1336756, + "ts": 1655274398903.310, "dur": 12.530, + "args": { + "External id": 4051586,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[8192, 1], [8192, 1], []], "Ev Idx": 9497 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 1336756, "tid": 1336756, + "ts": 1655274398916.841, "dur": 11.508, + "args": { + "External id": 4051587,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 9498 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 1336756, "tid": 1336756, + "ts": 1655274398931.272, "dur": 18.831, + "args": { + "External id": 4051588,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[8192, 1], [], [], [], [0]], "Ev Idx": 9499 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336756, "tid": 1336756, + "ts": 1655274398932.812, "dur": 1.212, + "args": { + "External id": 4051589,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 9500 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274398935.572, "dur": 2.275, + "args": { + "External id": 4051590,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[8192], [], [], []], "Ev Idx": 9501 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 1336756, "tid": 1336756, + "ts": 1655274398951.318, "dur": 10.915, + "args": { + "External id": 4051591,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 9502 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336756, "tid": 1336756, + "ts": 1655274398963.187, "dur": 11.783, + "args": { + "External id": 4051592,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 9503 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274398981.803, "dur": 1.494, + "args": { + "External id": 4051593,"Record function id": 0, "Concrete Inputs": ["", "[8192]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 9504 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1336756, + "ts": 1655274399027.687, "dur": 4.418, + "args": { + "External id": 4051594,"Record function id": 0, "Concrete Inputs": ["", "0", "57344", "65536", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 9505 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274399030.134, "dur": 0.713, + "args": { + "External id": 4051595,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "57344"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 9506 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274399097.400, "dur": 52.867, + "args": { + "External id": 4051596,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [2048, 1]], "Input Dims": [[8192, 32000], [32000, 2048]], "Ev Idx": 9507 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1336756, + "ts": 1655274399154.875, "dur": 4.398, + "args": { + "External id": 4051597,"Record function id": 0, "Concrete Inputs": ["", "0", "57344", "65536", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], [], [], []], "Input Dims": [[65536, 2048], [], [], [], []], "Ev Idx": 9508 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274399157.402, "dur": 0.898, + "args": { + "External id": 4051598,"Record function id": 0, "Concrete Inputs": ["", "[8192, 2048]", "[2048, 1]", "117440512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[65536, 2048], [], [], []], "Ev Idx": 9509 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1336756, + "ts": 1655274399160.544, "dur": 23.463, + "args": { + "External id": 4051599,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[8192, 2048], [8192, 2048], []], "Ev Idx": 9510 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1336756, + "ts": 1655274399188.553, "dur": 6.816, + "args": { + "External id": 4051600,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[8192, 32000]], "Ev Idx": 9511 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1336756, + "ts": 1655274399189.817, "dur": 4.914, + "args": { + "External id": 4051601,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[8192, 32000], [], []], "Ev Idx": 9512 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274399193.303, "dur": 1.241, + "args": { + "External id": 4051602,"Record function id": 0, "Concrete Inputs": ["", "[32000, 8192]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[8192, 32000], [], [], []], "Ev Idx": 9513 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336756, "tid": 1336756, + "ts": 1655274399197.871, "dur": 38.767, + "args": { + "External id": 4051603,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [2048, 1]], "Input Dims": [[32000, 8192], [8192, 2048]], "Ev Idx": 9514 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274399198.897, "dur": 37.078, + "args": { + "External id": 4051604,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [2048, 1]], "Input Dims": [[32000, 8192], [8192, 2048]], "Ev Idx": 9515 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336756, "tid": 1336756, + "ts": 1655274399240.169, "dur": 14.233, + "args": { + "External id": 4051605,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[32000, 2048], [32000, 2048], []], "Ev Idx": 9516 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 1336756, "tid": 1336756, + "ts": 1655274399259.249, "dur": 25.709, + "args": { + "External id": 4051606,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", ""], "Input Strides": [[1], []], "Input Dims": [[65536], []], "Ev Idx": 9517 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 1336756, "tid": 1336756, + "ts": 1655274399261.545, "dur": 23.068, + "args": { + "External id": 4051607,"Record function id": 0, "Concrete Inputs": ["", "[]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 9518 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274399266.393, "dur": 0.922, + "args": { + "External id": 4051608,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 9519 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655274399289.649, "dur": 24.963, + "args": { + "External id": 4051609,"Record function id": 0, "Concrete Inputs": ["", "", "15", "False", "False", ""], "Input type": ["float", "", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[2048, 1], [], [], [], [], []], "Input Dims": [[32000, 2048], [], [], [], [], []], "Ev Idx": 9520 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336756, "tid": 1336756, + "ts": 1655274399291.581, "dur": 22.798, + "args": { + "External id": 4051610,"Record function id": 0, "Concrete Inputs": ["", "15", "", "", "", "False", ""], "Input type": ["float", "Scalar", "", "", "", "Scalar", ""], "Input Strides": [[2048, 1], [], [], [], [], [], []], "Input Dims": [[32000, 2048], [], [], [], [], [], []], "Ev Idx": 9521 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274399297.090, "dur": 3.799, + "args": { + "External id": 4051611,"Record function id": 0, "Concrete Inputs": ["[32000, 2048]", "[2048, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9522 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1336756, + "ts": 1655274399301.980, "dur": 11.932, + "args": { + "External id": 4051612,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "float", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[32000, 2048], [32000, 2048], []], "Ev Idx": 9523 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1336756, + "ts": 1655274399326.145, "dur": 4.540, + "args": { + "External id": 4051613,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[65536, 2048]], "Ev Idx": 9524 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1336756, + "ts": 1655274399327.691, "dur": 2.627, + "args": { + "External id": 4051614,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[65536, 2048]], "Ev Idx": 9525 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1336756, + "ts": 1655274399331.618, "dur": 0.922, + "args": { + "External id": 4051615,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[32000, 2048]], "Ev Idx": 9526 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1336756, + "ts": 1655274399331.978, "dur": 0.473, + "args": { + "External id": 4051616,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[32000, 2048]], "Ev Idx": 9527 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336756, "tid": 1336756, + "ts": 1655274399369.227, "dur": 20.350, + "args": { + "External id": 4051617,"Sequence number": 40618564, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[1], [], []], "Ev Idx": 9528 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336756, "tid": 1336756, + "ts": 1655274399391.221, "dur": 13.437, + "args": { + "External id": 4051618,"Sequence number": 40618565, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[1], [], []], "Ev Idx": 9529 + } + }, + { + "ph": "s", "id": 16, "pid": 1336756, "tid": 1336756, "ts": 1655274399391.221, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1336756, + "ts": 1655274399410.086, "dur": 20.769, + "args": { + "External id": 4051619,"Sequence number": 40618566, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "0", "0", "9223372036854775807", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 1], [], [], [], []], "Input Dims": [[16, 4, 4096], [], [], [], []], "Ev Idx": 9530 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274399412.940, "dur": 0.901, + "args": { + "External id": 4051620,"Record function id": 0, "Concrete Inputs": ["", "[16, 4, 4096]", "[8192, 1, 1]", "1"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[8192, 1, 1], [], [], []], "Input Dims": [[16, 4, 4096], [], [], []], "Ev Idx": 9531 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select", "pid": 1336756, "tid": 1336756, + "ts": 1655274399434.151, "dur": 6.985, + "args": { + "External id": 4051621,"Sequence number": 40618566, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "1", "2"], "Input type": ["long int", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 1], [], []], "Input Dims": [[16, 4, 4096], [], []], "Ev Idx": 9532 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274399438.833, "dur": 0.899, + "args": { + "External id": 4051622,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096]", "[8192, 1]", "3"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[8192, 1, 1], [], [], []], "Input Dims": [[16, 4, 4096], [], [], []], "Ev Idx": 9533 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1336756, + "ts": 1655274399442.674, "dur": 2.893, + "args": { + "External id": 4051623,"Sequence number": 40618566, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "1", "0", "9223372036854775807", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8192, 1], [], [], [], []], "Input Dims": [[16, 4096], [], [], [], []], "Ev Idx": 9534 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274399444.379, "dur": 0.565, + "args": { + "External id": 4051624,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096]", "[8192, 1]", "3"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[8192, 1], [], [], []], "Input Dims": [[16, 4096], [], [], []], "Ev Idx": 9535 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1336756, + "ts": 1655274399452.045, "dur": 5.976, + "args": { + "External id": 4051625,"Sequence number": 40618566, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "0", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[33554432, 8192, 2048, 1], [], [], [], []], "Input Dims": [[16, 4096, 4, 2048], [], [], [], []], "Ev Idx": 9536 + } + }, + { + "ph": "s", "id": 15, "pid": 1336756, "tid": 1336756, "ts": 1655274399452.045, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274399455.634, "dur": 0.886, + "args": { + "External id": 4051626,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 4, 2048]", "[33554432, 8192, 2048, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[33554432, 8192, 2048, 1], [], [], []], "Input Dims": [[16, 4096, 4, 2048], [], [], []], "Ev Idx": 9537 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1336756, + "ts": 1655274399459.095, "dur": 4.124, + "args": { + "External id": 4051627,"Sequence number": 40618567, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "1", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[33554432, 8192, 2048, 1], [], [], [], []], "Input Dims": [[16, 4096, 4, 2048], [], [], [], []], "Ev Idx": 9538 + } + }, + { + "ph": "s", "id": 14, "pid": 1336756, "tid": 1336756, "ts": 1655274399459.095, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274399461.858, "dur": 0.662, + "args": { + "External id": 4051628,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 4, 2048]", "[33554432, 8192, 2048, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[33554432, 8192, 2048, 1], [], [], []], "Input Dims": [[16, 4096, 4, 2048], [], [], []], "Ev Idx": 9539 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select", "pid": 1336756, "tid": 1336756, + "ts": 1655274399464.402, "dur": 6.269, + "args": { + "External id": 4051629,"Sequence number": 40618568, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "2", "2"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[33554432, 8192, 2048, 1], [], []], "Input Dims": [[16, 4096, 4, 2048], [], []], "Ev Idx": 9540 + } + }, + { + "ph": "s", "id": 13, "pid": 1336756, "tid": 1336756, "ts": 1655274399464.402, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274399469.013, "dur": 0.876, + "args": { + "External id": 4051630,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]", "[33554432, 8192, 1]", "4096"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[33554432, 8192, 2048, 1], [], [], []], "Input Dims": [[16, 4096, 4, 2048], [], [], []], "Ev Idx": 9541 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1336756, + "ts": 1655274399471.597, "dur": 4.054, + "args": { + "External id": 4051631,"Sequence number": 40618569, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "2", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[33554432, 8192, 1], [], [], [], []], "Input Dims": [[16, 4096, 2048], [], [], [], []], "Ev Idx": 9542 + } + }, + { + "ph": "s", "id": 12, "pid": 1336756, "tid": 1336756, "ts": 1655274399471.597, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274399474.237, "dur": 0.742, + "args": { + "External id": 4051632,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]", "[33554432, 8192, 1]", "4096"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[33554432, 8192, 1], [], [], []], "Input Dims": [[16, 4096, 2048], [], [], []], "Ev Idx": 9543 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::contiguous", "pid": 1336756, "tid": 1336756, + "ts": 1655274399479.876, "dur": 29.704, + "args": { + "External id": 4051633,"Sequence number": 40618570, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["long int", "Scalar"], "Input Strides": [[8192, 1], []], "Input Dims": [[16, 4096], []], "Ev Idx": 9544 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 1336756, "tid": 1336756, + "ts": 1655274399481.235, "dur": 28.107, + "args": { + "External id": 4051634,"Sequence number": 40618570, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["long int", "Scalar"], "Input Strides": [[8192, 1], []], "Input Dims": [[16, 4096], []], "Ev Idx": 9545 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336756, "tid": 1336756, + "ts": 1655274399483.380, "dur": 6.450, + "args": { + "External id": 4051635,"Record function id": 0, "Concrete Inputs": ["", "4", "0", "", "", "0"], "Input type": ["long int", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[8192, 1], [], [], [], [], []], "Input Dims": [[16, 4096], [], [], [], [], []], "Ev Idx": 9546 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274399485.531, "dur": 3.762, + "args": { + "External id": 4051636,"Record function id": 0, "Concrete Inputs": ["[16, 4096]", "4", "0", "", "", "0"], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9547 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1336756, + "ts": 1655274399490.575, "dur": 18.338, + "args": { + "External id": 4051637,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[4096, 1], [8192, 1], []], "Input Dims": [[16, 4096], [16, 4096], []], "Ev Idx": 9548 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274399536.921, "dur": 6.788, + "args": { + "External id": 4051638,"Sequence number": 40618570, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[-1, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[33554432, 8192, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 9549 + } + }, + { + "ph": "s", "id": 11, "pid": 1336756, "tid": 1336756, "ts": 1655274399536.921, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274399545.929, "dur": 1.088, + "args": { + "External id": 4051639,"Sequence number": 40618571, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["long int", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[16, 4096], []], "Ev Idx": 9550 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "FusedLinearCrossEntropyFunction", "pid": 1336756, "tid": 1336756, + "ts": 1655274399578.159, "dur": 44138.044, + "args": { + "External id": 4051640,"Sequence number": 40618571, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "-100", "0.", "1.", "8"], "Input type": ["c10::BFloat16", "long int", "c10::BFloat16", "", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8192, 1], [1], [2048, 1], [], [], [], [], []], "Input Dims": [[65536, 2048], [65536], [32000, 2048], [], [], [], [], []], "Ev Idx": 9551 + } + }, + { + "ph": "s", "id": 10, "pid": 1336756, "tid": 1336756, "ts": 1655274399578.159, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::contiguous", "pid": 1336756, "tid": 1336756, + "ts": 1655274399592.004, "dur": 26.068, + "args": { + "External id": 4051641,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[8192, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 9552 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 1336756, "tid": 1336756, + "ts": 1655274399592.647, "dur": 25.248, + "args": { + "External id": 4051642,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[8192, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 9553 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336756, "tid": 1336756, + "ts": 1655274399594.019, "dur": 5.505, + "args": { + "External id": 4051643,"Record function id": 0, "Concrete Inputs": ["", "15", "0", "", "", "0"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[8192, 1], [], [], [], [], []], "Input Dims": [[65536, 2048], [], [], [], [], []], "Ev Idx": 9554 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274399595.338, "dur": 3.675, + "args": { + "External id": 4051644,"Record function id": 0, "Concrete Inputs": ["[65536, 2048]", "15", "0", "", "", "0"], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9555 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1336756, + "ts": 1655274399600.286, "dur": 17.247, + "args": { + "External id": 4051645,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [8192, 1], []], "Input Dims": [[65536, 2048], [65536, 2048], []], "Ev Idx": 9556 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros_like", "pid": 1336756, "tid": 1336756, + "ts": 1655274399632.899, "dur": 25.626, + "args": { + "External id": 4051646,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[2048, 1], [], [], [], [], []], "Input Dims": [[65536, 2048], [], [], [], [], []], "Ev Idx": 9557 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336756, "tid": 1336756, + "ts": 1655274399633.987, "dur": 7.688, + "args": { + "External id": 4051647,"Record function id": 0, "Concrete Inputs": ["", "15", "0", "", "False", ""], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[2048, 1], [], [], [], [], []], "Input Dims": [[65536, 2048], [], [], [], [], []], "Ev Idx": 9558 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274399637.428, "dur": 3.929, + "args": { + "External id": 4051648,"Record function id": 0, "Concrete Inputs": ["[65536, 2048]", "[2048, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9559 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 1336756, "tid": 1336756, + "ts": 1655274399643.101, "dur": 15.156, + "args": { + "External id": 4051649,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[65536, 2048]], "Ev Idx": 9560 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 1336756, "tid": 1336756, + "ts": 1655274399645.035, "dur": 12.875, + "args": { + "External id": 4051650,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 9561 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros_like", "pid": 1336756, "tid": 1336756, + "ts": 1655274399661.762, "dur": 16.691, + "args": { + "External id": 4051651,"Record function id": 0, "Concrete Inputs": ["", "6", "", "", "False", ""], "Input type": ["c10::BFloat16", "Scalar", "", "", "Scalar", ""], "Input Strides": [[2048, 1], [], [], [], [], []], "Input Dims": [[32000, 2048], [], [], [], [], []], "Ev Idx": 9562 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336756, "tid": 1336756, + "ts": 1655274399662.611, "dur": 4.212, + "args": { + "External id": 4051652,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "False", ""], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[2048, 1], [], [], [], [], []], "Input Dims": [[32000, 2048], [], [], [], [], []], "Ev Idx": 9563 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274399663.915, "dur": 2.625, + "args": { + "External id": 4051653,"Record function id": 0, "Concrete Inputs": ["[32000, 2048]", "[2048, 1]", "6", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9564 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 1336756, "tid": 1336756, + "ts": 1655274399667.325, "dur": 10.941, + "args": { + "External id": 4051654,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[2048, 1]], "Input Dims": [[32000, 2048]], "Ev Idx": 9565 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 1336756, "tid": 1336756, + "ts": 1655274399667.757, "dur": 10.212, + "args": { + "External id": 4051655,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[2048, 1], []], "Input Dims": [[32000, 2048], []], "Ev Idx": 9566 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros", "pid": 1336756, "tid": 1336756, + "ts": 1655274399684.343, "dur": 18.547, + "args": { + "External id": 4051656,"Record function id": 0, "Concrete Inputs": ["[65536]", "6", "", "", "False"], "Input type": ["ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 9567 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274399687.799, "dur": 2.931, + "args": { + "External id": 4051657,"Record function id": 0, "Concrete Inputs": ["[65536]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9568 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 1336756, "tid": 1336756, + "ts": 1655274399692.845, "dur": 9.738, + "args": { + "External id": 4051658,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[65536]], "Ev Idx": 9569 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 1336756, "tid": 1336756, + "ts": 1655274399693.531, "dur": 8.758, + "args": { + "External id": 4051659,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[65536], []], "Ev Idx": 9570 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::ne", "pid": 1336756, "tid": 1336756, + "ts": 1655274399707.282, "dur": 21.684, + "args": { + "External id": 4051660,"Record function id": 0, "Concrete Inputs": ["", "-100"], "Input type": ["long int", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[65536], []], "Ev Idx": 9571 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 1336756, "tid": 1336756, + "ts": 1655274399731.145, "dur": 43.288, + "args": { + "External id": 4051661,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["bool", ""], "Input Strides": [[1], []], "Input Dims": [[65536], []], "Ev Idx": 9572 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 1336756, "tid": 1336756, + "ts": 1655274399733.104, "dur": 40.828, + "args": { + "External id": 4051662,"Record function id": 0, "Concrete Inputs": ["", "[]", "False", ""], "Input type": ["bool", "ScalarList", "Scalar", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 9573 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274399737.636, "dur": 0.685, + "args": { + "External id": 4051663,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[0]", ""], "Input type": ["long int", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 9574 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655274399739.391, "dur": 20.144, + "args": { + "External id": 4051664,"Record function id": 0, "Concrete Inputs": ["", "4", "False", "False", ""], "Input type": ["bool", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 9575 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336756, "tid": 1336756, + "ts": 1655274399741.113, "dur": 18.219, + "args": { + "External id": 4051665,"Record function id": 0, "Concrete Inputs": ["", "4", "", "", "", "False", ""], "Input type": ["bool", "Scalar", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[65536], [], [], [], [], [], []], "Ev Idx": 9576 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274399744.788, "dur": 2.452, + "args": { + "External id": 4051666,"Record function id": 0, "Concrete Inputs": ["[65536]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9577 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1336756, + "ts": 1655274399748.131, "dur": 10.822, + "args": { + "External id": 4051667,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["long int", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[65536], [65536], []], "Ev Idx": 9578 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::item", "pid": 1336756, "tid": 1336756, + "ts": 1655274399779.589, "dur": 38415.561, + "args": { + "External id": 4051668,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["long int"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 9579 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_local_scalar_dense", "pid": 1336756, "tid": 1336756, + "ts": 1655274399781.471, "dur": 38412.867, + "args": { + "External id": 4051669,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["long int"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 9580 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1336756, + "ts": 1655274438204.694, "dur": 6.066, + "args": { + "External id": 4051670,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "8192", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], [], [], []], "Input Dims": [[65536, 2048], [], [], [], []], "Ev Idx": 9581 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274438208.220, "dur": 0.886, + "args": { + "External id": 4051671,"Record function id": 0, "Concrete Inputs": ["", "[8192, 2048]", "[2048, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[65536, 2048], [], [], []], "Ev Idx": 9582 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336756, "tid": 1336756, + "ts": 1655274438215.553, "dur": 95.057, + "args": { + "External id": 4051672,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[8192, 2048], [32000, 2048], []], "Ev Idx": 9583 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1336756, + "ts": 1655274438217.054, "dur": 6.965, + "args": { + "External id": 4051673,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[32000, 2048]], "Ev Idx": 9584 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1336756, + "ts": 1655274438218.746, "dur": 4.477, + "args": { + "External id": 4051674,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[32000, 2048], [], []], "Ev Idx": 9585 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274438222.130, "dur": 0.839, + "args": { + "External id": 4051675,"Record function id": 0, "Concrete Inputs": ["", "[2048, 32000]", "[1, 2048]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[32000, 2048], [], [], []], "Ev Idx": 9586 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336756, "tid": 1336756, + "ts": 1655274438225.206, "dur": 84.723, + "args": { + "External id": 4051676,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048]], "Input Dims": [[8192, 2048], [2048, 32000]], "Ev Idx": 9587 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274438226.640, "dur": 82.326, + "args": { + "External id": 4051677,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048]], "Input Dims": [[8192, 2048], [2048, 32000]], "Ev Idx": 9588 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1336756, + "ts": 1655274438314.068, "dur": 3.633, + "args": { + "External id": 4051678,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "8192", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 9589 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274438315.755, "dur": 0.800, + "args": { + "External id": 4051679,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "0"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 9590 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274438324.413, "dur": 2.137, + "args": { + "External id": 4051680,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[8192, 32000], []], "Ev Idx": 9591 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274438334.680, "dur": 8.153, + "args": { + "External id": 4051681,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[8192, 32000], [], [], [], [], []], "Ev Idx": 9592 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274438338.696, "dur": 3.857, + "args": { + "External id": 4051682,"Record function id": 0, "Concrete Inputs": ["[8192, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9593 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 1336756, "tid": 1336756, + "ts": 1655274438475.239, "dur": 188.114, + "args": { + "External id": 4051683,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 9594 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274438478.624, "dur": 3.368, + "args": { + "External id": 4051684,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9595 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 1336756, "tid": 1336756, + "ts": 1655274438483.588, "dur": 179.257, + "args": { + "External id": 4051685,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[8192, 1], [], [], [0]], "Ev Idx": 9596 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 1336756, "tid": 1336756, + "ts": 1655274438486.908, "dur": 0.411, + "args": { + "External id": 4051686,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 9597 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 1336756, "tid": 1336756, + "ts": 1655274438488.551, "dur": 23.914, + "args": { + "External id": 4051687,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 9598 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 1336756, "tid": 1336756, + "ts": 1655274438514.510, "dur": 3.647, + "args": { + "External id": 4051688,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[8192, 1], []], "Ev Idx": 9599 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274438516.843, "dur": 0.986, + "args": { + "External id": 4051689,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[8192, 1], [], [], []], "Ev Idx": 9600 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336756, "tid": 1336756, + "ts": 1655274438520.771, "dur": 23.558, + "args": { + "External id": 4051690,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 9601 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274438523.414, "dur": 1.428, + "args": { + "External id": 4051691,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9602 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336756, "tid": 1336756, + "ts": 1655274438526.131, "dur": 17.932, + "args": { + "External id": 4051692,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[8192], [0]], "Ev Idx": 9603 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336756, "tid": 1336756, + "ts": 1655274438529.728, "dur": 3.170, + "args": { + "External id": 4051693,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 9604 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 1336756, "tid": 1336756, + "ts": 1655274438545.950, "dur": 20.887, + "args": { + "External id": 4051694,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 9605 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 1336756, "tid": 1336756, + "ts": 1655274438568.448, "dur": 13.804, + "args": { + "External id": 4051695,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 9606 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 1336756, "tid": 1336756, + "ts": 1655274438585.374, "dur": 14.525, + "args": { + "External id": 4051696,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[8192, 1], [8192, 1], []], "Ev Idx": 9607 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 1336756, "tid": 1336756, + "ts": 1655274438601.356, "dur": 13.076, + "args": { + "External id": 4051697,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 9608 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 1336756, "tid": 1336756, + "ts": 1655274438616.303, "dur": 20.286, + "args": { + "External id": 4051698,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[8192, 1], [], [], [], [0]], "Ev Idx": 9609 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336756, "tid": 1336756, + "ts": 1655274438620.510, "dur": 1.428, + "args": { + "External id": 4051699,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 9610 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274438623.640, "dur": 0.712, + "args": { + "External id": 4051700,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[8192], [], [], []], "Ev Idx": 9611 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 1336756, "tid": 1336756, + "ts": 1655274438638.014, "dur": 11.421, + "args": { + "External id": 4051701,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 9612 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336756, "tid": 1336756, + "ts": 1655274438650.952, "dur": 10.594, + "args": { + "External id": 4051702,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 9613 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274438670.508, "dur": 2.355, + "args": { + "External id": 4051703,"Record function id": 0, "Concrete Inputs": ["", "[8192]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 9614 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1336756, + "ts": 1655274438679.505, "dur": 3.650, + "args": { + "External id": 4051704,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "8192", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 9615 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274438681.620, "dur": 0.752, + "args": { + "External id": 4051705,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 9616 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274438750.657, "dur": 62.211, + "args": { + "External id": 4051706,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [2048, 1]], "Input Dims": [[8192, 32000], [32000, 2048]], "Ev Idx": 9617 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1336756, + "ts": 1655274438817.829, "dur": 5.605, + "args": { + "External id": 4051707,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "8192", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], [], [], []], "Input Dims": [[65536, 2048], [], [], [], []], "Ev Idx": 9618 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274438820.361, "dur": 0.949, + "args": { + "External id": 4051708,"Record function id": 0, "Concrete Inputs": ["", "[8192, 2048]", "[2048, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[65536, 2048], [], [], []], "Ev Idx": 9619 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1336756, + "ts": 1655274438826.241, "dur": 23.472, + "args": { + "External id": 4051709,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[8192, 2048], [8192, 2048], []], "Ev Idx": 9620 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1336756, + "ts": 1655274438854.686, "dur": 8.324, + "args": { + "External id": 4051710,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[8192, 32000]], "Ev Idx": 9621 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1336756, + "ts": 1655274438856.252, "dur": 6.091, + "args": { + "External id": 4051711,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[8192, 32000], [], []], "Ev Idx": 9622 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274438859.681, "dur": 2.394, + "args": { + "External id": 4051712,"Record function id": 0, "Concrete Inputs": ["", "[32000, 8192]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[8192, 32000], [], [], []], "Ev Idx": 9623 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336756, "tid": 1336756, + "ts": 1655274438865.886, "dur": 41.733, + "args": { + "External id": 4051713,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [2048, 1]], "Input Dims": [[32000, 8192], [8192, 2048]], "Ev Idx": 9624 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274438867.352, "dur": 39.540, + "args": { + "External id": 4051714,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [2048, 1]], "Input Dims": [[32000, 8192], [8192, 2048]], "Ev Idx": 9625 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336756, "tid": 1336756, + "ts": 1655274438911.521, "dur": 13.699, + "args": { + "External id": 4051715,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[32000, 2048], [32000, 2048], []], "Ev Idx": 9626 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1336756, + "ts": 1655274438931.012, "dur": 3.321, + "args": { + "External id": 4051716,"Record function id": 0, "Concrete Inputs": ["", "0", "8192", "16384", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], [], [], []], "Input Dims": [[65536, 2048], [], [], [], []], "Ev Idx": 9627 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274438932.877, "dur": 0.524, + "args": { + "External id": 4051717,"Record function id": 0, "Concrete Inputs": ["", "[8192, 2048]", "[2048, 1]", "16777216"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[65536, 2048], [], [], []], "Ev Idx": 9628 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336756, "tid": 1336756, + "ts": 1655274438938.314, "dur": 99.568, + "args": { + "External id": 4051718,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[8192, 2048], [32000, 2048], []], "Ev Idx": 9629 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1336756, + "ts": 1655274438940.856, "dur": 3.497, + "args": { + "External id": 4051719,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[32000, 2048]], "Ev Idx": 9630 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1336756, + "ts": 1655274438941.647, "dur": 2.171, + "args": { + "External id": 4051720,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[32000, 2048], [], []], "Ev Idx": 9631 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274438942.994, "dur": 0.635, + "args": { + "External id": 4051721,"Record function id": 0, "Concrete Inputs": ["", "[2048, 32000]", "[1, 2048]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[32000, 2048], [], [], []], "Ev Idx": 9632 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336756, "tid": 1336756, + "ts": 1655274438945.178, "dur": 91.940, + "args": { + "External id": 4051722,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048]], "Input Dims": [[8192, 2048], [2048, 32000]], "Ev Idx": 9633 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274438945.874, "dur": 89.784, + "args": { + "External id": 4051723,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048]], "Input Dims": [[8192, 2048], [2048, 32000]], "Ev Idx": 9634 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1336756, + "ts": 1655274439045.426, "dur": 5.842, + "args": { + "External id": 4051724,"Record function id": 0, "Concrete Inputs": ["", "0", "8192", "16384", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 9635 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274439048.543, "dur": 1.177, + "args": { + "External id": 4051725,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "8192"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 9636 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274439059.544, "dur": 1.754, + "args": { + "External id": 4051726,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[8192, 32000], []], "Ev Idx": 9637 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274439069.659, "dur": 7.885, + "args": { + "External id": 4051727,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[8192, 32000], [], [], [], [], []], "Ev Idx": 9638 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274439072.549, "dur": 4.682, + "args": { + "External id": 4051728,"Record function id": 0, "Concrete Inputs": ["[8192, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9639 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 1336756, "tid": 1336756, + "ts": 1655274439173.003, "dur": 174.600, + "args": { + "External id": 4051729,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 9640 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274439175.156, "dur": 2.095, + "args": { + "External id": 4051730,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9641 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 1336756, "tid": 1336756, + "ts": 1655274439182.307, "dur": 164.855, + "args": { + "External id": 4051731,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[8192, 1], [], [], [0]], "Ev Idx": 9642 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 1336756, "tid": 1336756, + "ts": 1655274439183.744, "dur": 0.665, + "args": { + "External id": 4051732,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 9643 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 1336756, "tid": 1336756, + "ts": 1655274439185.686, "dur": 21.268, + "args": { + "External id": 4051733,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 9644 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 1336756, "tid": 1336756, + "ts": 1655274439208.287, "dur": 4.895, + "args": { + "External id": 4051734,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[8192, 1], []], "Ev Idx": 9645 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274439210.582, "dur": 2.304, + "args": { + "External id": 4051735,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[8192, 1], [], [], []], "Ev Idx": 9646 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336756, "tid": 1336756, + "ts": 1655274439214.169, "dur": 20.832, + "args": { + "External id": 4051736,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 9647 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274439215.306, "dur": 1.569, + "args": { + "External id": 4051737,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9648 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336756, "tid": 1336756, + "ts": 1655274439217.932, "dur": 16.745, + "args": { + "External id": 4051738,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[8192], [0]], "Ev Idx": 9649 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336756, "tid": 1336756, + "ts": 1655274439220.926, "dur": 2.443, + "args": { + "External id": 4051739,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 9650 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 1336756, "tid": 1336756, + "ts": 1655274439237.920, "dur": 19.399, + "args": { + "External id": 4051740,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 9651 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 1336756, "tid": 1336756, + "ts": 1655274439258.616, "dur": 12.936, + "args": { + "External id": 4051741,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 9652 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 1336756, "tid": 1336756, + "ts": 1655274439274.304, "dur": 13.139, + "args": { + "External id": 4051742,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[8192, 1], [8192, 1], []], "Ev Idx": 9653 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 1336756, "tid": 1336756, + "ts": 1655274439288.918, "dur": 11.191, + "args": { + "External id": 4051743,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 9654 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 1336756, "tid": 1336756, + "ts": 1655274439301.956, "dur": 18.252, + "args": { + "External id": 4051744,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[8192, 1], [], [], [], [0]], "Ev Idx": 9655 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336756, "tid": 1336756, + "ts": 1655274439304.000, "dur": 1.149, + "args": { + "External id": 4051745,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 9656 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274439306.871, "dur": 0.886, + "args": { + "External id": 4051746,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[8192], [], [], []], "Ev Idx": 9657 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 1336756, "tid": 1336756, + "ts": 1655274439321.562, "dur": 11.681, + "args": { + "External id": 4051747,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 9658 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336756, "tid": 1336756, + "ts": 1655274439336.361, "dur": 9.857, + "args": { + "External id": 4051748,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 9659 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274439353.718, "dur": 1.647, + "args": { + "External id": 4051749,"Record function id": 0, "Concrete Inputs": ["", "[8192]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 9660 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1336756, + "ts": 1655274439363.138, "dur": 3.221, + "args": { + "External id": 4051750,"Record function id": 0, "Concrete Inputs": ["", "0", "8192", "16384", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 9661 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274439365.291, "dur": 0.354, + "args": { + "External id": 4051751,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "8192"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 9662 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274439558.131, "dur": 63.270, + "args": { + "External id": 4051752,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [2048, 1]], "Input Dims": [[8192, 32000], [32000, 2048]], "Ev Idx": 9663 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1336756, + "ts": 1655274439627.693, "dur": 7.432, + "args": { + "External id": 4051753,"Record function id": 0, "Concrete Inputs": ["", "0", "8192", "16384", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], [], [], []], "Input Dims": [[65536, 2048], [], [], [], []], "Ev Idx": 9664 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274439631.188, "dur": 2.328, + "args": { + "External id": 4051754,"Record function id": 0, "Concrete Inputs": ["", "[8192, 2048]", "[2048, 1]", "16777216"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[65536, 2048], [], [], []], "Ev Idx": 9665 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1336756, + "ts": 1655274439636.932, "dur": 24.722, + "args": { + "External id": 4051755,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[8192, 2048], [8192, 2048], []], "Ev Idx": 9666 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1336756, + "ts": 1655274439668.497, "dur": 5.181, + "args": { + "External id": 4051756,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[8192, 32000]], "Ev Idx": 9667 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1336756, + "ts": 1655274439670.077, "dur": 2.876, + "args": { + "External id": 4051757,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[8192, 32000], [], []], "Ev Idx": 9668 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274439671.791, "dur": 0.979, + "args": { + "External id": 4051758,"Record function id": 0, "Concrete Inputs": ["", "[32000, 8192]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[8192, 32000], [], [], []], "Ev Idx": 9669 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336756, "tid": 1336756, + "ts": 1655274439676.379, "dur": 40.600, + "args": { + "External id": 4051759,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [2048, 1]], "Input Dims": [[32000, 8192], [8192, 2048]], "Ev Idx": 9670 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274439677.426, "dur": 39.005, + "args": { + "External id": 4051760,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [2048, 1]], "Input Dims": [[32000, 8192], [8192, 2048]], "Ev Idx": 9671 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336756, "tid": 1336756, + "ts": 1655274439721.203, "dur": 14.332, + "args": { + "External id": 4051761,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[32000, 2048], [32000, 2048], []], "Ev Idx": 9672 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1336756, + "ts": 1655274439741.490, "dur": 4.923, + "args": { + "External id": 4051762,"Record function id": 0, "Concrete Inputs": ["", "0", "16384", "24576", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], [], [], []], "Input Dims": [[65536, 2048], [], [], [], []], "Ev Idx": 9673 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274439744.910, "dur": 0.734, + "args": { + "External id": 4051763,"Record function id": 0, "Concrete Inputs": ["", "[8192, 2048]", "[2048, 1]", "33554432"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[65536, 2048], [], [], []], "Ev Idx": 9674 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336756, "tid": 1336756, + "ts": 1655274439750.438, "dur": 48.034, + "args": { + "External id": 4051764,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[8192, 2048], [32000, 2048], []], "Ev Idx": 9675 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1336756, + "ts": 1655274439751.370, "dur": 3.294, + "args": { + "External id": 4051765,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[32000, 2048]], "Ev Idx": 9676 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1336756, + "ts": 1655274439752.105, "dur": 2.018, + "args": { + "External id": 4051766,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[32000, 2048], [], []], "Ev Idx": 9677 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274439753.324, "dur": 0.668, + "args": { + "External id": 4051767,"Record function id": 0, "Concrete Inputs": ["", "[2048, 32000]", "[1, 2048]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[32000, 2048], [], [], []], "Ev Idx": 9678 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336756, "tid": 1336756, + "ts": 1655274439755.479, "dur": 42.582, + "args": { + "External id": 4051768,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048]], "Input Dims": [[8192, 2048], [2048, 32000]], "Ev Idx": 9679 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274439757.929, "dur": 39.561, + "args": { + "External id": 4051769,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048]], "Input Dims": [[8192, 2048], [2048, 32000]], "Ev Idx": 9680 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1336756, + "ts": 1655274439802.563, "dur": 3.676, + "args": { + "External id": 4051770,"Record function id": 0, "Concrete Inputs": ["", "0", "16384", "24576", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 9681 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274439804.683, "dur": 0.673, + "args": { + "External id": 4051771,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "16384"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 9682 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274439812.429, "dur": 1.357, + "args": { + "External id": 4051772,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[8192, 32000], []], "Ev Idx": 9683 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274439821.036, "dur": 6.746, + "args": { + "External id": 4051773,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[8192, 32000], [], [], [], [], []], "Ev Idx": 9684 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274439823.185, "dur": 4.301, + "args": { + "External id": 4051774,"Record function id": 0, "Concrete Inputs": ["[8192, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9685 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 1336756, "tid": 1336756, + "ts": 1655274439919.986, "dur": 235.053, + "args": { + "External id": 4051775,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 9686 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274439922.779, "dur": 3.604, + "args": { + "External id": 4051776,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9687 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 1336756, "tid": 1336756, + "ts": 1655274439944.540, "dur": 209.964, + "args": { + "External id": 4051777,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[8192, 1], [], [], [0]], "Ev Idx": 9688 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 1336756, "tid": 1336756, + "ts": 1655274439945.901, "dur": 0.521, + "args": { + "External id": 4051778,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 9689 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 1336756, "tid": 1336756, + "ts": 1655274439947.364, "dur": 20.031, + "args": { + "External id": 4051779,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 9690 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 1336756, "tid": 1336756, + "ts": 1655274439968.908, "dur": 4.179, + "args": { + "External id": 4051780,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[8192, 1], []], "Ev Idx": 9691 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274439972.209, "dur": 0.642, + "args": { + "External id": 4051781,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[8192, 1], [], [], []], "Ev Idx": 9692 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336756, "tid": 1336756, + "ts": 1655274439974.087, "dur": 63.470, + "args": { + "External id": 4051782,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 9693 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274439975.051, "dur": 1.574, + "args": { + "External id": 4051783,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9694 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336756, "tid": 1336756, + "ts": 1655274439979.801, "dur": 57.324, + "args": { + "External id": 4051784,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[8192], [0]], "Ev Idx": 9695 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336756, "tid": 1336756, + "ts": 1655274440020.038, "dur": 3.749, + "args": { + "External id": 4051785,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 9696 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 1336756, "tid": 1336756, + "ts": 1655274440039.170, "dur": 21.673, + "args": { + "External id": 4051786,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 9697 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 1336756, "tid": 1336756, + "ts": 1655274440062.111, "dur": 12.593, + "args": { + "External id": 4051787,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 9698 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 1336756, "tid": 1336756, + "ts": 1655274440077.666, "dur": 13.494, + "args": { + "External id": 4051788,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[8192, 1], [8192, 1], []], "Ev Idx": 9699 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 1336756, "tid": 1336756, + "ts": 1655274440092.537, "dur": 11.463, + "args": { + "External id": 4051789,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 9700 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 1336756, "tid": 1336756, + "ts": 1655274440105.667, "dur": 22.055, + "args": { + "External id": 4051790,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[8192, 1], [], [], [], [0]], "Ev Idx": 9701 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336756, "tid": 1336756, + "ts": 1655274440109.110, "dur": 1.353, + "args": { + "External id": 4051791,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 9702 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274440113.902, "dur": 0.740, + "args": { + "External id": 4051792,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[8192], [], [], []], "Ev Idx": 9703 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 1336756, "tid": 1336756, + "ts": 1655274440129.189, "dur": 11.266, + "args": { + "External id": 4051793,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 9704 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336756, "tid": 1336756, + "ts": 1655274440141.761, "dur": 11.509, + "args": { + "External id": 4051794,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 9705 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274440162.883, "dur": 1.989, + "args": { + "External id": 4051795,"Record function id": 0, "Concrete Inputs": ["", "[8192]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 9706 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1336756, + "ts": 1655274440174.154, "dur": 3.251, + "args": { + "External id": 4051796,"Record function id": 0, "Concrete Inputs": ["", "0", "16384", "24576", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 9707 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274440176.279, "dur": 0.327, + "args": { + "External id": 4051797,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "16384"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 9708 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274440246.362, "dur": 89.091, + "args": { + "External id": 4051798,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [2048, 1]], "Input Dims": [[8192, 32000], [32000, 2048]], "Ev Idx": 9709 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1336756, + "ts": 1655274440340.280, "dur": 6.312, + "args": { + "External id": 4051799,"Record function id": 0, "Concrete Inputs": ["", "0", "16384", "24576", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], [], [], []], "Input Dims": [[65536, 2048], [], [], [], []], "Ev Idx": 9710 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274440344.640, "dur": 0.969, + "args": { + "External id": 4051800,"Record function id": 0, "Concrete Inputs": ["", "[8192, 2048]", "[2048, 1]", "33554432"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[65536, 2048], [], [], []], "Ev Idx": 9711 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1336756, + "ts": 1655274440348.135, "dur": 24.585, + "args": { + "External id": 4051801,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[8192, 2048], [8192, 2048], []], "Ev Idx": 9712 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1336756, + "ts": 1655274440377.346, "dur": 5.110, + "args": { + "External id": 4051802,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[8192, 32000]], "Ev Idx": 9713 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1336756, + "ts": 1655274440378.708, "dur": 3.198, + "args": { + "External id": 4051803,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[8192, 32000], [], []], "Ev Idx": 9714 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274440380.298, "dur": 1.476, + "args": { + "External id": 4051804,"Record function id": 0, "Concrete Inputs": ["", "[32000, 8192]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[8192, 32000], [], [], []], "Ev Idx": 9715 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336756, "tid": 1336756, + "ts": 1655274440384.780, "dur": 64.223, + "args": { + "External id": 4051805,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [2048, 1]], "Input Dims": [[32000, 8192], [8192, 2048]], "Ev Idx": 9716 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274440390.585, "dur": 57.453, + "args": { + "External id": 4051806,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [2048, 1]], "Input Dims": [[32000, 8192], [8192, 2048]], "Ev Idx": 9717 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336756, "tid": 1336756, + "ts": 1655274440454.570, "dur": 16.418, + "args": { + "External id": 4051807,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[32000, 2048], [32000, 2048], []], "Ev Idx": 9718 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1336756, + "ts": 1655274440477.527, "dur": 4.711, + "args": { + "External id": 4051808,"Record function id": 0, "Concrete Inputs": ["", "0", "24576", "32768", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], [], [], []], "Input Dims": [[65536, 2048], [], [], [], []], "Ev Idx": 9719 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274440480.001, "dur": 1.141, + "args": { + "External id": 4051809,"Record function id": 0, "Concrete Inputs": ["", "[8192, 2048]", "[2048, 1]", "50331648"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[65536, 2048], [], [], []], "Ev Idx": 9720 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336756, "tid": 1336756, + "ts": 1655274440485.914, "dur": 52.560, + "args": { + "External id": 4051810,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[8192, 2048], [32000, 2048], []], "Ev Idx": 9721 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1336756, + "ts": 1655274440486.843, "dur": 5.336, + "args": { + "External id": 4051811,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[32000, 2048]], "Ev Idx": 9722 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1336756, + "ts": 1655274440487.867, "dur": 3.769, + "args": { + "External id": 4051812,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[32000, 2048], [], []], "Ev Idx": 9723 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274440490.867, "dur": 0.621, + "args": { + "External id": 4051813,"Record function id": 0, "Concrete Inputs": ["", "[2048, 32000]", "[1, 2048]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[32000, 2048], [], [], []], "Ev Idx": 9724 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336756, "tid": 1336756, + "ts": 1655274440493.085, "dur": 45.022, + "args": { + "External id": 4051814,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048]], "Input Dims": [[8192, 2048], [2048, 32000]], "Ev Idx": 9725 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274440493.854, "dur": 43.724, + "args": { + "External id": 4051815,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048]], "Input Dims": [[8192, 2048], [2048, 32000]], "Ev Idx": 9726 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1336756, + "ts": 1655274440542.278, "dur": 3.364, + "args": { + "External id": 4051816,"Record function id": 0, "Concrete Inputs": ["", "0", "24576", "32768", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 9727 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274440544.165, "dur": 0.467, + "args": { + "External id": 4051817,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "24576"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 9728 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274440551.460, "dur": 1.315, + "args": { + "External id": 4051818,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[8192, 32000], []], "Ev Idx": 9729 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274440561.025, "dur": 7.588, + "args": { + "External id": 4051819,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[8192, 32000], [], [], [], [], []], "Ev Idx": 9730 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274440562.638, "dur": 5.679, + "args": { + "External id": 4051820,"Record function id": 0, "Concrete Inputs": ["[8192, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9731 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 1336756, "tid": 1336756, + "ts": 1655274440653.493, "dur": 169.436, + "args": { + "External id": 4051821,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 9732 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274440655.435, "dur": 2.384, + "args": { + "External id": 4051822,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9733 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 1336756, "tid": 1336756, + "ts": 1655274440659.146, "dur": 163.219, + "args": { + "External id": 4051823,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[8192, 1], [], [], [0]], "Ev Idx": 9734 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 1336756, "tid": 1336756, + "ts": 1655274440660.429, "dur": 0.282, + "args": { + "External id": 4051824,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 9735 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 1336756, "tid": 1336756, + "ts": 1655274440663.802, "dur": 22.023, + "args": { + "External id": 4051825,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 9736 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 1336756, "tid": 1336756, + "ts": 1655274440687.401, "dur": 3.018, + "args": { + "External id": 4051826,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[8192, 1], []], "Ev Idx": 9737 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274440689.295, "dur": 0.914, + "args": { + "External id": 4051827,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[8192, 1], [], [], []], "Ev Idx": 9738 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336756, "tid": 1336756, + "ts": 1655274440691.056, "dur": 22.012, + "args": { + "External id": 4051828,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 9739 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274440692.147, "dur": 1.485, + "args": { + "External id": 4051829,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9740 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336756, "tid": 1336756, + "ts": 1655274440695.211, "dur": 17.448, + "args": { + "External id": 4051830,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[8192], [0]], "Ev Idx": 9741 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336756, "tid": 1336756, + "ts": 1655274440699.457, "dur": 2.619, + "args": { + "External id": 4051831,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 9742 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 1336756, "tid": 1336756, + "ts": 1655274440714.522, "dur": 19.212, + "args": { + "External id": 4051832,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 9743 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 1336756, "tid": 1336756, + "ts": 1655274440735.103, "dur": 13.095, + "args": { + "External id": 4051833,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 9744 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 1336756, "tid": 1336756, + "ts": 1655274440750.900, "dur": 11.990, + "args": { + "External id": 4051834,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[8192, 1], [8192, 1], []], "Ev Idx": 9745 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 1336756, "tid": 1336756, + "ts": 1655274440765.991, "dur": 11.656, + "args": { + "External id": 4051835,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 9746 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 1336756, "tid": 1336756, + "ts": 1655274440779.170, "dur": 17.349, + "args": { + "External id": 4051836,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[8192, 1], [], [], [], [0]], "Ev Idx": 9747 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336756, "tid": 1336756, + "ts": 1655274440780.738, "dur": 1.054, + "args": { + "External id": 4051837,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 9748 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274440783.587, "dur": 0.854, + "args": { + "External id": 4051838,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[8192], [], [], []], "Ev Idx": 9749 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 1336756, "tid": 1336756, + "ts": 1655274440797.898, "dur": 11.536, + "args": { + "External id": 4051839,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 9750 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336756, "tid": 1336756, + "ts": 1655274440810.605, "dur": 10.844, + "args": { + "External id": 4051840,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 9751 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274440829.051, "dur": 1.717, + "args": { + "External id": 4051841,"Record function id": 0, "Concrete Inputs": ["", "[8192]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 9752 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1336756, + "ts": 1655274440840.132, "dur": 3.129, + "args": { + "External id": 4051842,"Record function id": 0, "Concrete Inputs": ["", "0", "24576", "32768", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 9753 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274440842.156, "dur": 0.369, + "args": { + "External id": 4051843,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "24576"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 9754 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274440902.988, "dur": 51.643, + "args": { + "External id": 4051844,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [2048, 1]], "Input Dims": [[8192, 32000], [32000, 2048]], "Ev Idx": 9755 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1336756, + "ts": 1655274440959.229, "dur": 4.670, + "args": { + "External id": 4051845,"Record function id": 0, "Concrete Inputs": ["", "0", "24576", "32768", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], [], [], []], "Input Dims": [[65536, 2048], [], [], [], []], "Ev Idx": 9756 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274440961.667, "dur": 1.279, + "args": { + "External id": 4051846,"Record function id": 0, "Concrete Inputs": ["", "[8192, 2048]", "[2048, 1]", "50331648"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[65536, 2048], [], [], []], "Ev Idx": 9757 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1336756, + "ts": 1655274440965.253, "dur": 60.891, + "args": { + "External id": 4051847,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[8192, 2048], [8192, 2048], []], "Ev Idx": 9758 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1336756, + "ts": 1655274441032.868, "dur": 7.347, + "args": { + "External id": 4051848,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[8192, 32000]], "Ev Idx": 9759 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1336756, + "ts": 1655274441034.108, "dur": 5.329, + "args": { + "External id": 4051849,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[8192, 32000], [], []], "Ev Idx": 9760 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274441037.984, "dur": 1.226, + "args": { + "External id": 4051850,"Record function id": 0, "Concrete Inputs": ["", "[32000, 8192]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[8192, 32000], [], [], []], "Ev Idx": 9761 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336756, "tid": 1336756, + "ts": 1655274441043.766, "dur": 47.769, + "args": { + "External id": 4051851,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [2048, 1]], "Input Dims": [[32000, 8192], [8192, 2048]], "Ev Idx": 9762 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274441044.919, "dur": 45.860, + "args": { + "External id": 4051852,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [2048, 1]], "Input Dims": [[32000, 8192], [8192, 2048]], "Ev Idx": 9763 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336756, "tid": 1336756, + "ts": 1655274441095.401, "dur": 14.495, + "args": { + "External id": 4051853,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[32000, 2048], [32000, 2048], []], "Ev Idx": 9764 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1336756, + "ts": 1655274441116.211, "dur": 3.711, + "args": { + "External id": 4051854,"Record function id": 0, "Concrete Inputs": ["", "0", "32768", "40960", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], [], [], []], "Input Dims": [[65536, 2048], [], [], [], []], "Ev Idx": 9765 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274441118.306, "dur": 0.768, + "args": { + "External id": 4051855,"Record function id": 0, "Concrete Inputs": ["", "[8192, 2048]", "[2048, 1]", "67108864"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[65536, 2048], [], [], []], "Ev Idx": 9766 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336756, "tid": 1336756, + "ts": 1655274441125.759, "dur": 49.279, + "args": { + "External id": 4051856,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[8192, 2048], [32000, 2048], []], "Ev Idx": 9767 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1336756, + "ts": 1655274441126.766, "dur": 5.366, + "args": { + "External id": 4051857,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[32000, 2048]], "Ev Idx": 9768 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1336756, + "ts": 1655274441127.747, "dur": 3.787, + "args": { + "External id": 4051858,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[32000, 2048], [], []], "Ev Idx": 9769 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274441128.965, "dur": 2.388, + "args": { + "External id": 4051859,"Record function id": 0, "Concrete Inputs": ["", "[2048, 32000]", "[1, 2048]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[32000, 2048], [], [], []], "Ev Idx": 9770 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336756, "tid": 1336756, + "ts": 1655274441132.700, "dur": 41.910, + "args": { + "External id": 4051860,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048]], "Input Dims": [[8192, 2048], [2048, 32000]], "Ev Idx": 9771 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274441133.499, "dur": 40.515, + "args": { + "External id": 4051861,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048]], "Input Dims": [[8192, 2048], [2048, 32000]], "Ev Idx": 9772 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1336756, + "ts": 1655274441179.097, "dur": 3.948, + "args": { + "External id": 4051862,"Record function id": 0, "Concrete Inputs": ["", "0", "32768", "40960", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 9773 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274441181.047, "dur": 0.919, + "args": { + "External id": 4051863,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "32768"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 9774 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274441191.423, "dur": 1.448, + "args": { + "External id": 4051864,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[8192, 32000], []], "Ev Idx": 9775 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274441200.561, "dur": 6.145, + "args": { + "External id": 4051865,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[8192, 32000], [], [], [], [], []], "Ev Idx": 9776 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274441202.523, "dur": 3.900, + "args": { + "External id": 4051866,"Record function id": 0, "Concrete Inputs": ["[8192, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9777 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 1336756, "tid": 1336756, + "ts": 1655274441289.672, "dur": 194.539, + "args": { + "External id": 4051867,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 9778 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274441291.725, "dur": 2.331, + "args": { + "External id": 4051868,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9779 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 1336756, "tid": 1336756, + "ts": 1655274441301.975, "dur": 181.828, + "args": { + "External id": 4051869,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[8192, 1], [], [], [0]], "Ev Idx": 9780 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 1336756, "tid": 1336756, + "ts": 1655274441304.791, "dur": 0.359, + "args": { + "External id": 4051870,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 9781 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 1336756, "tid": 1336756, + "ts": 1655274441307.886, "dur": 20.354, + "args": { + "External id": 4051871,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 9782 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 1336756, "tid": 1336756, + "ts": 1655274441329.888, "dur": 2.653, + "args": { + "External id": 4051872,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[8192, 1], []], "Ev Idx": 9783 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274441331.586, "dur": 0.652, + "args": { + "External id": 4051873,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[8192, 1], [], [], []], "Ev Idx": 9784 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336756, "tid": 1336756, + "ts": 1655274441333.210, "dur": 21.369, + "args": { + "External id": 4051874,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 9785 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274441334.515, "dur": 2.773, + "args": { + "External id": 4051875,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9786 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336756, "tid": 1336756, + "ts": 1655274441338.548, "dur": 15.604, + "args": { + "External id": 4051876,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[8192], [0]], "Ev Idx": 9787 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336756, "tid": 1336756, + "ts": 1655274441341.033, "dur": 2.484, + "args": { + "External id": 4051877,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 9788 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 1336756, "tid": 1336756, + "ts": 1655274441356.082, "dur": 18.231, + "args": { + "External id": 4051878,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 9789 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 1336756, "tid": 1336756, + "ts": 1655274441375.767, "dur": 11.576, + "args": { + "External id": 4051879,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 9790 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 1336756, "tid": 1336756, + "ts": 1655274441391.088, "dur": 13.337, + "args": { + "External id": 4051880,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[8192, 1], [8192, 1], []], "Ev Idx": 9791 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 1336756, "tid": 1336756, + "ts": 1655274441405.778, "dur": 29.700, + "args": { + "External id": 4051881,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 9792 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 1336756, "tid": 1336756, + "ts": 1655274441438.215, "dur": 20.314, + "args": { + "External id": 4051882,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[8192, 1], [], [], [], [0]], "Ev Idx": 9793 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336756, "tid": 1336756, + "ts": 1655274441440.251, "dur": 2.061, + "args": { + "External id": 4051883,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 9794 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274441443.931, "dur": 0.799, + "args": { + "External id": 4051884,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[8192], [], [], []], "Ev Idx": 9795 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 1336756, "tid": 1336756, + "ts": 1655274441459.829, "dur": 11.184, + "args": { + "External id": 4051885,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 9796 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336756, "tid": 1336756, + "ts": 1655274441472.023, "dur": 10.885, + "args": { + "External id": 4051886,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 9797 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274441492.747, "dur": 2.001, + "args": { + "External id": 4051887,"Record function id": 0, "Concrete Inputs": ["", "[8192]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 9798 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1336756, + "ts": 1655274441503.389, "dur": 3.415, + "args": { + "External id": 4051888,"Record function id": 0, "Concrete Inputs": ["", "0", "32768", "40960", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 9799 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274441505.484, "dur": 0.572, + "args": { + "External id": 4051889,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "32768"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 9800 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274441571.211, "dur": 53.526, + "args": { + "External id": 4051890,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [2048, 1]], "Input Dims": [[8192, 32000], [32000, 2048]], "Ev Idx": 9801 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1336756, + "ts": 1655274441629.295, "dur": 4.792, + "args": { + "External id": 4051891,"Record function id": 0, "Concrete Inputs": ["", "0", "32768", "40960", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], [], [], []], "Input Dims": [[65536, 2048], [], [], [], []], "Ev Idx": 9802 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274441632.209, "dur": 0.963, + "args": { + "External id": 4051892,"Record function id": 0, "Concrete Inputs": ["", "[8192, 2048]", "[2048, 1]", "67108864"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[65536, 2048], [], [], []], "Ev Idx": 9803 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1336756, + "ts": 1655274441635.388, "dur": 22.729, + "args": { + "External id": 4051893,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[8192, 2048], [8192, 2048], []], "Ev Idx": 9804 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1336756, + "ts": 1655274441662.928, "dur": 8.007, + "args": { + "External id": 4051894,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[8192, 32000]], "Ev Idx": 9805 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1336756, + "ts": 1655274441665.835, "dur": 4.436, + "args": { + "External id": 4051895,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[8192, 32000], [], []], "Ev Idx": 9806 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274441667.662, "dur": 2.434, + "args": { + "External id": 4051896,"Record function id": 0, "Concrete Inputs": ["", "[32000, 8192]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[8192, 32000], [], [], []], "Ev Idx": 9807 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336756, "tid": 1336756, + "ts": 1655274441673.436, "dur": 40.412, + "args": { + "External id": 4051897,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [2048, 1]], "Input Dims": [[32000, 8192], [8192, 2048]], "Ev Idx": 9808 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274441674.792, "dur": 38.325, + "args": { + "External id": 4051898,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [2048, 1]], "Input Dims": [[32000, 8192], [8192, 2048]], "Ev Idx": 9809 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336756, "tid": 1336756, + "ts": 1655274441717.572, "dur": 13.323, + "args": { + "External id": 4051899,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[32000, 2048], [32000, 2048], []], "Ev Idx": 9810 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1336756, + "ts": 1655274441736.529, "dur": 4.734, + "args": { + "External id": 4051900,"Record function id": 0, "Concrete Inputs": ["", "0", "40960", "49152", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], [], [], []], "Input Dims": [[65536, 2048], [], [], [], []], "Ev Idx": 9811 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274441739.954, "dur": 0.540, + "args": { + "External id": 4051901,"Record function id": 0, "Concrete Inputs": ["", "[8192, 2048]", "[2048, 1]", "83886080"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[65536, 2048], [], [], []], "Ev Idx": 9812 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336756, "tid": 1336756, + "ts": 1655274441744.961, "dur": 52.963, + "args": { + "External id": 4051902,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[8192, 2048], [32000, 2048], []], "Ev Idx": 9813 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1336756, + "ts": 1655274441745.834, "dur": 3.168, + "args": { + "External id": 4051903,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[32000, 2048]], "Ev Idx": 9814 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1336756, + "ts": 1655274441746.550, "dur": 1.890, + "args": { + "External id": 4051904,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[32000, 2048], [], []], "Ev Idx": 9815 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274441747.530, "dur": 0.776, + "args": { + "External id": 4051905,"Record function id": 0, "Concrete Inputs": ["", "[2048, 32000]", "[1, 2048]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[32000, 2048], [], [], []], "Ev Idx": 9816 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336756, "tid": 1336756, + "ts": 1655274441756.953, "dur": 40.495, + "args": { + "External id": 4051906,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048]], "Input Dims": [[8192, 2048], [2048, 32000]], "Ev Idx": 9817 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274441757.481, "dur": 39.468, + "args": { + "External id": 4051907,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048]], "Input Dims": [[8192, 2048], [2048, 32000]], "Ev Idx": 9818 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1336756, + "ts": 1655274441803.645, "dur": 3.504, + "args": { + "External id": 4051908,"Record function id": 0, "Concrete Inputs": ["", "0", "40960", "49152", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 9819 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274441805.463, "dur": 0.735, + "args": { + "External id": 4051909,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "40960"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 9820 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274441811.796, "dur": 1.424, + "args": { + "External id": 4051910,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[8192, 32000], []], "Ev Idx": 9821 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274441820.322, "dur": 7.057, + "args": { + "External id": 4051911,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[8192, 32000], [], [], [], [], []], "Ev Idx": 9822 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274441822.050, "dur": 4.966, + "args": { + "External id": 4051912,"Record function id": 0, "Concrete Inputs": ["[8192, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9823 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 1336756, "tid": 1336756, + "ts": 1655274441911.669, "dur": 205.243, + "args": { + "External id": 4051913,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 9824 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274441913.815, "dur": 1.621, + "args": { + "External id": 4051914,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9825 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 1336756, "tid": 1336756, + "ts": 1655274441916.516, "dur": 199.970, + "args": { + "External id": 4051915,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[8192, 1], [], [], [0]], "Ev Idx": 9826 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 1336756, "tid": 1336756, + "ts": 1655274441917.600, "dur": 0.489, + "args": { + "External id": 4051916,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 9827 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 1336756, "tid": 1336756, + "ts": 1655274441918.913, "dur": 21.026, + "args": { + "External id": 4051917,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 9828 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 1336756, "tid": 1336756, + "ts": 1655274441941.485, "dur": 2.892, + "args": { + "External id": 4051918,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[8192, 1], []], "Ev Idx": 9829 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274441943.426, "dur": 0.711, + "args": { + "External id": 4051919,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[8192, 1], [], [], []], "Ev Idx": 9830 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336756, "tid": 1336756, + "ts": 1655274441945.118, "dur": 22.740, + "args": { + "External id": 4051920,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 9831 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274441946.306, "dur": 1.444, + "args": { + "External id": 4051921,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9832 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336756, "tid": 1336756, + "ts": 1655274441948.764, "dur": 18.782, + "args": { + "External id": 4051922,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[8192], [0]], "Ev Idx": 9833 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336756, "tid": 1336756, + "ts": 1655274441954.587, "dur": 2.308, + "args": { + "External id": 4051923,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 9834 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 1336756, "tid": 1336756, + "ts": 1655274441969.086, "dur": 54.125, + "args": { + "External id": 4051924,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 9835 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 1336756, "tid": 1336756, + "ts": 1655274442025.783, "dur": 14.389, + "args": { + "External id": 4051925,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 9836 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 1336756, "tid": 1336756, + "ts": 1655274442043.237, "dur": 13.102, + "args": { + "External id": 4051926,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[8192, 1], [8192, 1], []], "Ev Idx": 9837 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 1336756, "tid": 1336756, + "ts": 1655274442057.771, "dur": 11.270, + "args": { + "External id": 4051927,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 9838 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 1336756, "tid": 1336756, + "ts": 1655274442070.555, "dur": 18.067, + "args": { + "External id": 4051928,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[8192, 1], [], [], [], [0]], "Ev Idx": 9839 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336756, "tid": 1336756, + "ts": 1655274442072.581, "dur": 1.687, + "args": { + "External id": 4051929,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 9840 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274442075.865, "dur": 0.680, + "args": { + "External id": 4051930,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[8192], [], [], []], "Ev Idx": 9841 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 1336756, "tid": 1336756, + "ts": 1655274442091.640, "dur": 11.564, + "args": { + "External id": 4051931,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 9842 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336756, "tid": 1336756, + "ts": 1655274442104.158, "dur": 11.051, + "args": { + "External id": 4051932,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 9843 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274442124.136, "dur": 2.011, + "args": { + "External id": 4051933,"Record function id": 0, "Concrete Inputs": ["", "[8192]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 9844 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1336756, + "ts": 1655274442134.913, "dur": 3.550, + "args": { + "External id": 4051934,"Record function id": 0, "Concrete Inputs": ["", "0", "40960", "49152", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 9845 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274442137.014, "dur": 0.639, + "args": { + "External id": 4051935,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "40960"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 9846 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274442203.796, "dur": 51.883, + "args": { + "External id": 4051936,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [2048, 1]], "Input Dims": [[8192, 32000], [32000, 2048]], "Ev Idx": 9847 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1336756, + "ts": 1655274442260.551, "dur": 6.197, + "args": { + "External id": 4051937,"Record function id": 0, "Concrete Inputs": ["", "0", "40960", "49152", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], [], [], []], "Input Dims": [[65536, 2048], [], [], [], []], "Ev Idx": 9848 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274442264.513, "dur": 1.148, + "args": { + "External id": 4051938,"Record function id": 0, "Concrete Inputs": ["", "[8192, 2048]", "[2048, 1]", "83886080"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[65536, 2048], [], [], []], "Ev Idx": 9849 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1336756, + "ts": 1655274442267.875, "dur": 20.834, + "args": { + "External id": 4051939,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[8192, 2048], [8192, 2048], []], "Ev Idx": 9850 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1336756, + "ts": 1655274442292.699, "dur": 4.779, + "args": { + "External id": 4051940,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[8192, 32000]], "Ev Idx": 9851 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1336756, + "ts": 1655274442294.005, "dur": 2.806, + "args": { + "External id": 4051941,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[8192, 32000], [], []], "Ev Idx": 9852 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274442295.804, "dur": 0.858, + "args": { + "External id": 4051942,"Record function id": 0, "Concrete Inputs": ["", "[32000, 8192]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[8192, 32000], [], [], []], "Ev Idx": 9853 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336756, "tid": 1336756, + "ts": 1655274442299.755, "dur": 39.224, + "args": { + "External id": 4051943,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [2048, 1]], "Input Dims": [[32000, 8192], [8192, 2048]], "Ev Idx": 9854 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274442300.510, "dur": 37.807, + "args": { + "External id": 4051944,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [2048, 1]], "Input Dims": [[32000, 8192], [8192, 2048]], "Ev Idx": 9855 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336756, "tid": 1336756, + "ts": 1655274442344.471, "dur": 13.032, + "args": { + "External id": 4051945,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[32000, 2048], [32000, 2048], []], "Ev Idx": 9856 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1336756, + "ts": 1655274442363.021, "dur": 3.539, + "args": { + "External id": 4051946,"Record function id": 0, "Concrete Inputs": ["", "0", "49152", "57344", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], [], [], []], "Input Dims": [[65536, 2048], [], [], [], []], "Ev Idx": 9857 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274442365.106, "dur": 0.686, + "args": { + "External id": 4051947,"Record function id": 0, "Concrete Inputs": ["", "[8192, 2048]", "[2048, 1]", "100663296"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[65536, 2048], [], [], []], "Ev Idx": 9858 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336756, "tid": 1336756, + "ts": 1655274442369.914, "dur": 63.843, + "args": { + "External id": 4051948,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[8192, 2048], [32000, 2048], []], "Ev Idx": 9859 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1336756, + "ts": 1655274442370.863, "dur": 6.075, + "args": { + "External id": 4051949,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[32000, 2048]], "Ev Idx": 9860 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1336756, + "ts": 1655274442371.464, "dur": 4.904, + "args": { + "External id": 4051950,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[32000, 2048], [], []], "Ev Idx": 9861 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274442374.034, "dur": 2.156, + "args": { + "External id": 4051951,"Record function id": 0, "Concrete Inputs": ["", "[2048, 32000]", "[1, 2048]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[32000, 2048], [], [], []], "Ev Idx": 9862 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336756, "tid": 1336756, + "ts": 1655274442377.674, "dur": 55.505, + "args": { + "External id": 4051952,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048]], "Input Dims": [[8192, 2048], [2048, 32000]], "Ev Idx": 9863 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274442378.441, "dur": 53.644, + "args": { + "External id": 4051953,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048]], "Input Dims": [[8192, 2048], [2048, 32000]], "Ev Idx": 9864 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1336756, + "ts": 1655274442439.961, "dur": 4.347, + "args": { + "External id": 4051954,"Record function id": 0, "Concrete Inputs": ["", "0", "49152", "57344", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 9865 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274442442.419, "dur": 0.666, + "args": { + "External id": 4051955,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "49152"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 9866 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274442450.407, "dur": 1.480, + "args": { + "External id": 4051956,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[8192, 32000], []], "Ev Idx": 9867 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274442458.861, "dur": 7.175, + "args": { + "External id": 4051957,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[8192, 32000], [], [], [], [], []], "Ev Idx": 9868 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274442462.061, "dur": 3.716, + "args": { + "External id": 4051958,"Record function id": 0, "Concrete Inputs": ["[8192, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9869 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 1336756, "tid": 1336756, + "ts": 1655274442543.413, "dur": 190.994, + "args": { + "External id": 4051959,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 9870 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274442545.772, "dur": 1.830, + "args": { + "External id": 4051960,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9871 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 1336756, "tid": 1336756, + "ts": 1655274442548.958, "dur": 184.952, + "args": { + "External id": 4051961,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[8192, 1], [], [], [0]], "Ev Idx": 9872 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 1336756, "tid": 1336756, + "ts": 1655274442550.196, "dur": 0.297, + "args": { + "External id": 4051962,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 9873 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 1336756, "tid": 1336756, + "ts": 1655274442553.272, "dur": 19.519, + "args": { + "External id": 4051963,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 9874 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 1336756, "tid": 1336756, + "ts": 1655274442574.354, "dur": 2.496, + "args": { + "External id": 4051964,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[8192, 1], []], "Ev Idx": 9875 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274442575.956, "dur": 0.658, + "args": { + "External id": 4051965,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[8192, 1], [], [], []], "Ev Idx": 9876 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336756, "tid": 1336756, + "ts": 1655274442577.722, "dur": 48.292, + "args": { + "External id": 4051966,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 9877 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274442580.349, "dur": 3.110, + "args": { + "External id": 4051967,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9878 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336756, "tid": 1336756, + "ts": 1655274442584.593, "dur": 41.171, + "args": { + "External id": 4051968,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[8192], [0]], "Ev Idx": 9879 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336756, "tid": 1336756, + "ts": 1655274442612.200, "dur": 2.517, + "args": { + "External id": 4051969,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 9880 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 1336756, "tid": 1336756, + "ts": 1655274442627.467, "dur": 19.206, + "args": { + "External id": 4051970,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 9881 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 1336756, "tid": 1336756, + "ts": 1655274442648.007, "dur": 12.483, + "args": { + "External id": 4051971,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 9882 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 1336756, "tid": 1336756, + "ts": 1655274442663.103, "dur": 12.367, + "args": { + "External id": 4051972,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[8192, 1], [8192, 1], []], "Ev Idx": 9883 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 1336756, "tid": 1336756, + "ts": 1655274442676.745, "dur": 11.663, + "args": { + "External id": 4051973,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 9884 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 1336756, "tid": 1336756, + "ts": 1655274442689.745, "dur": 18.834, + "args": { + "External id": 4051974,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[8192, 1], [], [], [], [0]], "Ev Idx": 9885 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336756, "tid": 1336756, + "ts": 1655274442691.258, "dur": 1.185, + "args": { + "External id": 4051975,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 9886 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274442695.610, "dur": 0.759, + "args": { + "External id": 4051976,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[8192], [], [], []], "Ev Idx": 9887 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 1336756, "tid": 1336756, + "ts": 1655274442709.690, "dur": 10.826, + "args": { + "External id": 4051977,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 9888 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336756, "tid": 1336756, + "ts": 1655274442721.400, "dur": 11.622, + "args": { + "External id": 4051978,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 9889 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274442740.332, "dur": 1.578, + "args": { + "External id": 4051979,"Record function id": 0, "Concrete Inputs": ["", "[8192]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 9890 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1336756, + "ts": 1655274442749.244, "dur": 3.124, + "args": { + "External id": 4051980,"Record function id": 0, "Concrete Inputs": ["", "0", "49152", "57344", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 9891 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274442751.121, "dur": 0.398, + "args": { + "External id": 4051981,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "49152"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 9892 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274442809.137, "dur": 51.902, + "args": { + "External id": 4051982,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [2048, 1]], "Input Dims": [[8192, 32000], [32000, 2048]], "Ev Idx": 9893 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1336756, + "ts": 1655274442865.409, "dur": 7.503, + "args": { + "External id": 4051983,"Record function id": 0, "Concrete Inputs": ["", "0", "49152", "57344", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], [], [], []], "Input Dims": [[65536, 2048], [], [], [], []], "Ev Idx": 9894 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274442869.596, "dur": 2.369, + "args": { + "External id": 4051984,"Record function id": 0, "Concrete Inputs": ["", "[8192, 2048]", "[2048, 1]", "100663296"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[65536, 2048], [], [], []], "Ev Idx": 9895 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1336756, + "ts": 1655274442874.251, "dur": 22.029, + "args": { + "External id": 4051985,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[8192, 2048], [8192, 2048], []], "Ev Idx": 9896 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1336756, + "ts": 1655274442900.453, "dur": 4.673, + "args": { + "External id": 4051986,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[8192, 32000]], "Ev Idx": 9897 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1336756, + "ts": 1655274442901.879, "dur": 2.523, + "args": { + "External id": 4051987,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[8192, 32000], [], []], "Ev Idx": 9898 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274442903.348, "dur": 0.863, + "args": { + "External id": 4051988,"Record function id": 0, "Concrete Inputs": ["", "[32000, 8192]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[8192, 32000], [], [], []], "Ev Idx": 9899 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336756, "tid": 1336756, + "ts": 1655274442907.560, "dur": 40.732, + "args": { + "External id": 4051989,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [2048, 1]], "Input Dims": [[32000, 8192], [8192, 2048]], "Ev Idx": 9900 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274442910.175, "dur": 37.598, + "args": { + "External id": 4051990,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [2048, 1]], "Input Dims": [[32000, 8192], [8192, 2048]], "Ev Idx": 9901 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336756, "tid": 1336756, + "ts": 1655274442951.802, "dur": 12.728, + "args": { + "External id": 4051991,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[32000, 2048], [32000, 2048], []], "Ev Idx": 9902 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1336756, + "ts": 1655274442969.639, "dur": 3.579, + "args": { + "External id": 4051992,"Record function id": 0, "Concrete Inputs": ["", "0", "57344", "65536", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], [], [], []], "Input Dims": [[65536, 2048], [], [], [], []], "Ev Idx": 9903 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274442971.596, "dur": 0.679, + "args": { + "External id": 4051993,"Record function id": 0, "Concrete Inputs": ["", "[8192, 2048]", "[2048, 1]", "117440512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[65536, 2048], [], [], []], "Ev Idx": 9904 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336756, "tid": 1336756, + "ts": 1655274442976.741, "dur": 88.757, + "args": { + "External id": 4051994,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[8192, 2048], [32000, 2048], []], "Ev Idx": 9905 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1336756, + "ts": 1655274442977.492, "dur": 4.681, + "args": { + "External id": 4051995,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[32000, 2048]], "Ev Idx": 9906 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1336756, + "ts": 1655274442978.169, "dur": 3.416, + "args": { + "External id": 4051996,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[32000, 2048], [], []], "Ev Idx": 9907 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274442980.810, "dur": 0.586, + "args": { + "External id": 4051997,"Record function id": 0, "Concrete Inputs": ["", "[2048, 32000]", "[1, 2048]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[32000, 2048], [], [], []], "Ev Idx": 9908 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336756, "tid": 1336756, + "ts": 1655274442982.674, "dur": 82.277, + "args": { + "External id": 4051998,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048]], "Input Dims": [[8192, 2048], [2048, 32000]], "Ev Idx": 9909 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274442983.181, "dur": 80.729, + "args": { + "External id": 4051999,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048]], "Input Dims": [[8192, 2048], [2048, 32000]], "Ev Idx": 9910 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1336756, + "ts": 1655274443071.005, "dur": 4.504, + "args": { + "External id": 4052000,"Record function id": 0, "Concrete Inputs": ["", "0", "57344", "65536", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 9911 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274443073.527, "dur": 0.757, + "args": { + "External id": 4052001,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "57344"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 9912 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274443081.414, "dur": 1.365, + "args": { + "External id": 4052002,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[8192, 32000], []], "Ev Idx": 9913 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274443091.169, "dur": 5.910, + "args": { + "External id": 4052003,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[8192, 32000], [], [], [], [], []], "Ev Idx": 9914 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274443092.617, "dur": 4.230, + "args": { + "External id": 4052004,"Record function id": 0, "Concrete Inputs": ["[8192, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9915 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 1336756, "tid": 1336756, + "ts": 1655274443174.380, "dur": 172.239, + "args": { + "External id": 4052005,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 9916 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274443176.122, "dur": 3.727, + "args": { + "External id": 4052006,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9917 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 1336756, "tid": 1336756, + "ts": 1655274443181.165, "dur": 165.000, + "args": { + "External id": 4052007,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[8192, 1], [], [], [0]], "Ev Idx": 9918 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 1336756, "tid": 1336756, + "ts": 1655274443182.417, "dur": 0.262, + "args": { + "External id": 4052008,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 9919 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 1336756, "tid": 1336756, + "ts": 1655274443185.569, "dur": 20.270, + "args": { + "External id": 4052009,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 9920 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 1336756, "tid": 1336756, + "ts": 1655274443207.355, "dur": 4.410, + "args": { + "External id": 4052010,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[8192, 1], []], "Ev Idx": 9921 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274443210.776, "dur": 0.793, + "args": { + "External id": 4052011,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[8192, 1], [], [], []], "Ev Idx": 9922 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336756, "tid": 1336756, + "ts": 1655274443212.722, "dur": 19.348, + "args": { + "External id": 4052012,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 9923 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274443214.077, "dur": 1.274, + "args": { + "External id": 4052013,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9924 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336756, "tid": 1336756, + "ts": 1655274443216.578, "dur": 15.255, + "args": { + "External id": 4052014,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[8192], [0]], "Ev Idx": 9925 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336756, "tid": 1336756, + "ts": 1655274443218.839, "dur": 2.278, + "args": { + "External id": 4052015,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 9926 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 1336756, "tid": 1336756, + "ts": 1655274443233.325, "dur": 18.349, + "args": { + "External id": 4052016,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 9927 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 1336756, "tid": 1336756, + "ts": 1655274443253.086, "dur": 12.924, + "args": { + "External id": 4052017,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 9928 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 1336756, "tid": 1336756, + "ts": 1655274443268.770, "dur": 12.398, + "args": { + "External id": 4052018,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[8192, 1], [8192, 1], []], "Ev Idx": 9929 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 1336756, "tid": 1336756, + "ts": 1655274443284.201, "dur": 11.153, + "args": { + "External id": 4052019,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 9930 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 1336756, "tid": 1336756, + "ts": 1655274443297.057, "dur": 18.695, + "args": { + "External id": 4052020,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[8192, 1], [], [], [], [0]], "Ev Idx": 9931 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336756, "tid": 1336756, + "ts": 1655274443300.666, "dur": 1.141, + "args": { + "External id": 4052021,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 9932 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274443303.433, "dur": 0.506, + "args": { + "External id": 4052022,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[8192], [], [], []], "Ev Idx": 9933 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 1336756, "tid": 1336756, + "ts": 1655274443322.025, "dur": 11.028, + "args": { + "External id": 4052023,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 9934 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336756, "tid": 1336756, + "ts": 1655274443334.092, "dur": 10.855, + "args": { + "External id": 4052024,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 9935 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274443352.648, "dur": 1.452, + "args": { + "External id": 4052025,"Record function id": 0, "Concrete Inputs": ["", "[8192]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 9936 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1336756, + "ts": 1655274443363.358, "dur": 3.062, + "args": { + "External id": 4052026,"Record function id": 0, "Concrete Inputs": ["", "0", "57344", "65536", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 9937 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274443365.440, "dur": 0.309, + "args": { + "External id": 4052027,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "57344"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 9938 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274443446.067, "dur": 58.239, + "args": { + "External id": 4052028,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [2048, 1]], "Input Dims": [[8192, 32000], [32000, 2048]], "Ev Idx": 9939 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1336756, + "ts": 1655274443509.922, "dur": 5.627, + "args": { + "External id": 4052029,"Record function id": 0, "Concrete Inputs": ["", "0", "57344", "65536", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], [], [], []], "Input Dims": [[65536, 2048], [], [], [], []], "Ev Idx": 9940 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274443512.959, "dur": 1.385, + "args": { + "External id": 4052030,"Record function id": 0, "Concrete Inputs": ["", "[8192, 2048]", "[2048, 1]", "117440512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[65536, 2048], [], [], []], "Ev Idx": 9941 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1336756, + "ts": 1655274443516.881, "dur": 23.185, + "args": { + "External id": 4052031,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[8192, 2048], [8192, 2048], []], "Ev Idx": 9942 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1336756, + "ts": 1655274443544.687, "dur": 6.691, + "args": { + "External id": 4052032,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[8192, 32000]], "Ev Idx": 9943 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1336756, + "ts": 1655274443546.169, "dur": 4.583, + "args": { + "External id": 4052033,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[8192, 32000], [], []], "Ev Idx": 9944 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274443549.462, "dur": 1.113, + "args": { + "External id": 4052034,"Record function id": 0, "Concrete Inputs": ["", "[32000, 8192]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[8192, 32000], [], [], []], "Ev Idx": 9945 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336756, "tid": 1336756, + "ts": 1655274443553.927, "dur": 41.022, + "args": { + "External id": 4052035,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [2048, 1]], "Input Dims": [[32000, 8192], [8192, 2048]], "Ev Idx": 9946 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274443554.852, "dur": 39.447, + "args": { + "External id": 4052036,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [2048, 1]], "Input Dims": [[32000, 8192], [8192, 2048]], "Ev Idx": 9947 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336756, "tid": 1336756, + "ts": 1655274443598.802, "dur": 13.877, + "args": { + "External id": 4052037,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[32000, 2048], [32000, 2048], []], "Ev Idx": 9948 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 1336756, "tid": 1336756, + "ts": 1655274443617.647, "dur": 23.282, + "args": { + "External id": 4052038,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", ""], "Input Strides": [[1], []], "Input Dims": [[65536], []], "Ev Idx": 9949 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 1336756, "tid": 1336756, + "ts": 1655274443619.884, "dur": 20.674, + "args": { + "External id": 4052039,"Record function id": 0, "Concrete Inputs": ["", "[]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 9950 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274443626.562, "dur": 0.582, + "args": { + "External id": 4052040,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 9951 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655274443645.730, "dur": 26.142, + "args": { + "External id": 4052041,"Record function id": 0, "Concrete Inputs": ["", "", "15", "False", "False", ""], "Input type": ["float", "", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[2048, 1], [], [], [], [], []], "Input Dims": [[32000, 2048], [], [], [], [], []], "Ev Idx": 9952 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336756, "tid": 1336756, + "ts": 1655274443649.107, "dur": 22.566, + "args": { + "External id": 4052042,"Record function id": 0, "Concrete Inputs": ["", "15", "", "", "", "False", ""], "Input type": ["float", "Scalar", "", "", "", "Scalar", ""], "Input Strides": [[2048, 1], [], [], [], [], [], []], "Input Dims": [[32000, 2048], [], [], [], [], [], []], "Ev Idx": 9953 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274443653.431, "dur": 3.976, + "args": { + "External id": 4052043,"Record function id": 0, "Concrete Inputs": ["[32000, 2048]", "[2048, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9954 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1336756, + "ts": 1655274443658.422, "dur": 12.701, + "args": { + "External id": 4052044,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "float", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[32000, 2048], [32000, 2048], []], "Ev Idx": 9955 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1336756, + "ts": 1655274443683.523, "dur": 4.811, + "args": { + "External id": 4052045,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[65536, 2048]], "Ev Idx": 9956 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1336756, + "ts": 1655274443685.280, "dur": 2.813, + "args": { + "External id": 4052046,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[65536, 2048]], "Ev Idx": 9957 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1336756, + "ts": 1655274443689.559, "dur": 1.154, + "args": { + "External id": 4052047,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[32000, 2048]], "Ev Idx": 9958 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1336756, + "ts": 1655274443690.213, "dur": 0.432, + "args": { + "External id": 4052048,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[32000, 2048]], "Ev Idx": 9959 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336756, "tid": 1336756, + "ts": 1655274443733.316, "dur": 21.991, + "args": { + "External id": 4052049,"Sequence number": 40618572, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[1], [], []], "Ev Idx": 9960 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336756, "tid": 1336756, + "ts": 1655274443757.094, "dur": 12.945, + "args": { + "External id": 4052050,"Sequence number": 40618573, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[1], [], []], "Ev Idx": 9961 + } + }, + { + "ph": "s", "id": 9, "pid": 1336756, "tid": 1336756, "ts": 1655274443757.094, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1336756, + "ts": 1655274443775.722, "dur": 5.025, + "args": { + "External id": 4052051,"Sequence number": 40618574, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "0", "0", "9223372036854775807", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 1], [], [], [], []], "Input Dims": [[16, 4, 4096], [], [], [], []], "Ev Idx": 9962 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274443778.658, "dur": 0.827, + "args": { + "External id": 4052052,"Record function id": 0, "Concrete Inputs": ["", "[16, 4, 4096]", "[8192, 1, 1]", "1"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[8192, 1, 1], [], [], []], "Input Dims": [[16, 4, 4096], [], [], []], "Ev Idx": 9963 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select", "pid": 1336756, "tid": 1336756, + "ts": 1655274443783.213, "dur": 10.672, + "args": { + "External id": 4052053,"Sequence number": 40618574, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "1", "3"], "Input type": ["long int", "Scalar", "Scalar"], "Input Strides": [[8192, 1, 1], [], []], "Input Dims": [[16, 4, 4096], [], []], "Ev Idx": 9964 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274443790.710, "dur": 1.938, + "args": { + "External id": 4052054,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096]", "[8192, 1]", "4"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[8192, 1, 1], [], [], []], "Input Dims": [[16, 4, 4096], [], [], []], "Ev Idx": 9965 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1336756, + "ts": 1655274443797.016, "dur": 3.009, + "args": { + "External id": 4052055,"Sequence number": 40618574, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "1", "0", "9223372036854775807", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8192, 1], [], [], [], []], "Input Dims": [[16, 4096], [], [], [], []], "Ev Idx": 9966 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274443798.384, "dur": 1.069, + "args": { + "External id": 4052056,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096]", "[8192, 1]", "4"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[8192, 1], [], [], []], "Input Dims": [[16, 4096], [], [], []], "Ev Idx": 9967 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1336756, + "ts": 1655274443804.187, "dur": 6.227, + "args": { + "External id": 4052057,"Sequence number": 40618574, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "0", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[33554432, 8192, 2048, 1], [], [], [], []], "Input Dims": [[16, 4096, 4, 2048], [], [], [], []], "Ev Idx": 9968 + } + }, + { + "ph": "s", "id": 8, "pid": 1336756, "tid": 1336756, "ts": 1655274443804.187, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274443807.894, "dur": 1.275, + "args": { + "External id": 4052058,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 4, 2048]", "[33554432, 8192, 2048, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[33554432, 8192, 2048, 1], [], [], []], "Input Dims": [[16, 4096, 4, 2048], [], [], []], "Ev Idx": 9969 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1336756, + "ts": 1655274443811.487, "dur": 6.665, + "args": { + "External id": 4052059,"Sequence number": 40618575, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "1", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[33554432, 8192, 2048, 1], [], [], [], []], "Input Dims": [[16, 4096, 4, 2048], [], [], [], []], "Ev Idx": 9970 + } + }, + { + "ph": "s", "id": 7, "pid": 1336756, "tid": 1336756, "ts": 1655274443811.487, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274443816.717, "dur": 0.637, + "args": { + "External id": 4052060,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 4, 2048]", "[33554432, 8192, 2048, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[33554432, 8192, 2048, 1], [], [], []], "Input Dims": [[16, 4096, 4, 2048], [], [], []], "Ev Idx": 9971 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select", "pid": 1336756, "tid": 1336756, + "ts": 1655274443819.266, "dur": 4.280, + "args": { + "External id": 4052061,"Sequence number": 40618576, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "2", "3"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[33554432, 8192, 2048, 1], [], []], "Input Dims": [[16, 4096, 4, 2048], [], []], "Ev Idx": 9972 + } + }, + { + "ph": "s", "id": 6, "pid": 1336756, "tid": 1336756, "ts": 1655274443819.266, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274443821.976, "dur": 0.622, + "args": { + "External id": 4052062,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]", "[33554432, 8192, 1]", "6144"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[33554432, 8192, 2048, 1], [], [], []], "Input Dims": [[16, 4096, 4, 2048], [], [], []], "Ev Idx": 9973 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1336756, + "ts": 1655274443824.520, "dur": 4.832, + "args": { + "External id": 4052063,"Sequence number": 40618577, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "2", "0", "9223372036854775807", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[33554432, 8192, 1], [], [], [], []], "Input Dims": [[16, 4096, 2048], [], [], [], []], "Ev Idx": 9974 + } + }, + { + "ph": "s", "id": 5, "pid": 1336756, "tid": 1336756, "ts": 1655274443824.520, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274443826.662, "dur": 1.956, + "args": { + "External id": 4052064,"Record function id": 0, "Concrete Inputs": ["", "[16, 4096, 2048]", "[33554432, 8192, 1]", "6144"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[33554432, 8192, 1], [], [], []], "Input Dims": [[16, 4096, 2048], [], [], []], "Ev Idx": 9975 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::contiguous", "pid": 1336756, "tid": 1336756, + "ts": 1655274443833.233, "dur": 28.292, + "args": { + "External id": 4052065,"Sequence number": 40618578, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["long int", "Scalar"], "Input Strides": [[8192, 1], []], "Input Dims": [[16, 4096], []], "Ev Idx": 9976 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 1336756, "tid": 1336756, + "ts": 1655274443834.651, "dur": 26.632, + "args": { + "External id": 4052066,"Sequence number": 40618578, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["long int", "Scalar"], "Input Strides": [[8192, 1], []], "Input Dims": [[16, 4096], []], "Ev Idx": 9977 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336756, "tid": 1336756, + "ts": 1655274443836.856, "dur": 7.441, + "args": { + "External id": 4052067,"Record function id": 0, "Concrete Inputs": ["", "4", "0", "", "", "0"], "Input type": ["long int", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[8192, 1], [], [], [], [], []], "Input Dims": [[16, 4096], [], [], [], [], []], "Ev Idx": 9978 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274443840.552, "dur": 3.161, + "args": { + "External id": 4052068,"Record function id": 0, "Concrete Inputs": ["[16, 4096]", "4", "0", "", "", "0"], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9979 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1336756, + "ts": 1655274443845.034, "dur": 15.677, + "args": { + "External id": 4052069,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["long int", "long int", "Scalar"], "Input Strides": [[4096, 1], [8192, 1], []], "Input Dims": [[16, 4096], [16, 4096], []], "Ev Idx": 9980 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274443885.704, "dur": 3.676, + "args": { + "External id": 4052070,"Sequence number": 40618578, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[-1, 2048]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[33554432, 8192, 1], []], "Input Dims": [[16, 4096, 2048], []], "Ev Idx": 9981 + } + }, + { + "ph": "s", "id": 4, "pid": 1336756, "tid": 1336756, "ts": 1655274443885.704, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274443891.669, "dur": 1.133, + "args": { + "External id": 4052071,"Sequence number": 40618579, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["long int", "ScalarList"], "Input Strides": [[4096, 1], []], "Input Dims": [[16, 4096], []], "Ev Idx": 9982 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "FusedLinearCrossEntropyFunction", "pid": 1336756, "tid": 1336756, + "ts": 1655274443924.213, "dur": 43560.039, + "args": { + "External id": 4052072,"Sequence number": 40618579, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "-100", "0.", "1.", "8"], "Input type": ["c10::BFloat16", "long int", "c10::BFloat16", "", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[8192, 1], [1], [2048, 1], [], [], [], [], []], "Input Dims": [[65536, 2048], [65536], [32000, 2048], [], [], [], [], []], "Ev Idx": 9983 + } + }, + { + "ph": "s", "id": 3, "pid": 1336756, "tid": 1336756, "ts": 1655274443924.213, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::contiguous", "pid": 1336756, "tid": 1336756, + "ts": 1655274443937.864, "dur": 24.954, + "args": { + "External id": 4052073,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[8192, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 9984 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 1336756, "tid": 1336756, + "ts": 1655274443938.476, "dur": 24.125, + "args": { + "External id": 4052074,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[8192, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 9985 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336756, "tid": 1336756, + "ts": 1655274443939.586, "dur": 7.522, + "args": { + "External id": 4052075,"Record function id": 0, "Concrete Inputs": ["", "15", "0", "", "", "0"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[8192, 1], [], [], [], [], []], "Input Dims": [[65536, 2048], [], [], [], [], []], "Ev Idx": 9986 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274443942.336, "dur": 4.316, + "args": { + "External id": 4052076,"Record function id": 0, "Concrete Inputs": ["[65536, 2048]", "15", "0", "", "", "0"], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9987 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1336756, + "ts": 1655274443947.691, "dur": 14.523, + "args": { + "External id": 4052077,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [8192, 1], []], "Input Dims": [[65536, 2048], [65536, 2048], []], "Ev Idx": 9988 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros_like", "pid": 1336756, "tid": 1336756, + "ts": 1655274443977.468, "dur": 63.825, + "args": { + "External id": 4052078,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", ""], "Input type": ["c10::BFloat16", "", "", "", "Scalar", ""], "Input Strides": [[2048, 1], [], [], [], [], []], "Input Dims": [[65536, 2048], [], [], [], [], []], "Ev Idx": 9989 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336756, "tid": 1336756, + "ts": 1655274443978.428, "dur": 5.381, + "args": { + "External id": 4052079,"Record function id": 0, "Concrete Inputs": ["", "15", "0", "", "False", ""], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[2048, 1], [], [], [], [], []], "Input Dims": [[65536, 2048], [], [], [], [], []], "Ev Idx": 9990 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274443980.102, "dur": 3.427, + "args": { + "External id": 4052080,"Record function id": 0, "Concrete Inputs": ["[65536, 2048]", "[2048, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9991 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 1336756, "tid": 1336756, + "ts": 1655274444022.468, "dur": 18.612, + "args": { + "External id": 4052081,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[65536, 2048]], "Ev Idx": 9992 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 1336756, "tid": 1336756, + "ts": 1655274444024.469, "dur": 15.981, + "args": { + "External id": 4052082,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], []], "Input Dims": [[65536, 2048], []], "Ev Idx": 9993 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros_like", "pid": 1336756, "tid": 1336756, + "ts": 1655274444045.765, "dur": 20.605, + "args": { + "External id": 4052083,"Record function id": 0, "Concrete Inputs": ["", "6", "", "", "False", ""], "Input type": ["c10::BFloat16", "Scalar", "", "", "Scalar", ""], "Input Strides": [[2048, 1], [], [], [], [], []], "Input Dims": [[32000, 2048], [], [], [], [], []], "Ev Idx": 9994 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336756, "tid": 1336756, + "ts": 1655274444046.794, "dur": 4.873, + "args": { + "External id": 4052084,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "False", ""], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[2048, 1], [], [], [], [], []], "Input Dims": [[32000, 2048], [], [], [], [], []], "Ev Idx": 9995 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274444048.330, "dur": 3.076, + "args": { + "External id": 4052085,"Record function id": 0, "Concrete Inputs": ["[32000, 2048]", "[2048, 1]", "6", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 9996 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 1336756, "tid": 1336756, + "ts": 1655274444053.982, "dur": 12.196, + "args": { + "External id": 4052086,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[2048, 1]], "Input Dims": [[32000, 2048]], "Ev Idx": 9997 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 1336756, "tid": 1336756, + "ts": 1655274444054.454, "dur": 11.339, + "args": { + "External id": 4052087,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[2048, 1], []], "Input Dims": [[32000, 2048], []], "Ev Idx": 9998 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros", "pid": 1336756, "tid": 1336756, + "ts": 1655274444072.080, "dur": 17.066, + "args": { + "External id": 4052088,"Record function id": 0, "Concrete Inputs": ["[65536]", "6", "", "", "False"], "Input type": ["ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 9999 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274444073.583, "dur": 3.398, + "args": { + "External id": 4052089,"Record function id": 0, "Concrete Inputs": ["[65536]", "6", "", "", "False", ""], "Input type": ["ScalarList", "Scalar", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10000 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 1336756, "tid": 1336756, + "ts": 1655274444077.780, "dur": 11.105, + "args": { + "External id": 4052090,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[65536]], "Ev Idx": 10001 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 1336756, "tid": 1336756, + "ts": 1655274444078.345, "dur": 10.246, + "args": { + "External id": 4052091,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[65536], []], "Ev Idx": 10002 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::ne", "pid": 1336756, "tid": 1336756, + "ts": 1655274444093.395, "dur": 19.699, + "args": { + "External id": 4052092,"Record function id": 0, "Concrete Inputs": ["", "-100"], "Input type": ["long int", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[65536], []], "Ev Idx": 10003 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 1336756, "tid": 1336756, + "ts": 1655274444115.520, "dur": 46.127, + "args": { + "External id": 4052093,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["bool", ""], "Input Strides": [[1], []], "Input Dims": [[65536], []], "Ev Idx": 10004 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 1336756, "tid": 1336756, + "ts": 1655274444119.012, "dur": 42.253, + "args": { + "External id": 4052094,"Record function id": 0, "Concrete Inputs": ["", "[]", "False", ""], "Input type": ["bool", "ScalarList", "Scalar", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 10005 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274444125.037, "dur": 0.800, + "args": { + "External id": 4052095,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[0]", ""], "Input type": ["long int", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10006 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655274444127.052, "dur": 20.310, + "args": { + "External id": 4052096,"Record function id": 0, "Concrete Inputs": ["", "4", "False", "False", ""], "Input type": ["bool", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 10007 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336756, "tid": 1336756, + "ts": 1655274444128.456, "dur": 18.710, + "args": { + "External id": 4052097,"Record function id": 0, "Concrete Inputs": ["", "4", "", "", "", "False", ""], "Input type": ["bool", "Scalar", "", "", "", "Scalar", ""], "Input Strides": [[1], [], [], [], [], [], []], "Input Dims": [[65536], [], [], [], [], [], []], "Ev Idx": 10008 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274444130.530, "dur": 2.933, + "args": { + "External id": 4052098,"Record function id": 0, "Concrete Inputs": ["[65536]", "[1]", "4", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10009 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1336756, + "ts": 1655274444134.329, "dur": 12.522, + "args": { + "External id": 4052099,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["long int", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[65536], [65536], []], "Ev Idx": 10010 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::item", "pid": 1336756, "tid": 1336756, + "ts": 1655274444165.247, "dur": 38057.633, + "args": { + "External id": 4052100,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["long int"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 10011 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_local_scalar_dense", "pid": 1336756, "tid": 1336756, + "ts": 1655274444166.804, "dur": 38055.238, + "args": { + "External id": 4052101,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["long int"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 10012 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1336756, + "ts": 1655274482232.338, "dur": 6.191, + "args": { + "External id": 4052102,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "8192", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], [], [], []], "Input Dims": [[65536, 2048], [], [], [], []], "Ev Idx": 10013 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274482236.017, "dur": 0.806, + "args": { + "External id": 4052103,"Record function id": 0, "Concrete Inputs": ["", "[8192, 2048]", "[2048, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[65536, 2048], [], [], []], "Ev Idx": 10014 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336756, "tid": 1336756, + "ts": 1655274482244.841, "dur": 93.471, + "args": { + "External id": 4052104,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[8192, 2048], [32000, 2048], []], "Ev Idx": 10015 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1336756, + "ts": 1655274482246.402, "dur": 5.478, + "args": { + "External id": 4052105,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[32000, 2048]], "Ev Idx": 10016 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1336756, + "ts": 1655274482248.326, "dur": 2.686, + "args": { + "External id": 4052106,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[32000, 2048], [], []], "Ev Idx": 10017 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274482249.867, "dur": 0.857, + "args": { + "External id": 4052107,"Record function id": 0, "Concrete Inputs": ["", "[2048, 32000]", "[1, 2048]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[32000, 2048], [], [], []], "Ev Idx": 10018 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336756, "tid": 1336756, + "ts": 1655274482253.002, "dur": 84.687, + "args": { + "External id": 4052108,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048]], "Input Dims": [[8192, 2048], [2048, 32000]], "Ev Idx": 10019 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274482254.509, "dur": 82.197, + "args": { + "External id": 4052109,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048]], "Input Dims": [[8192, 2048], [2048, 32000]], "Ev Idx": 10020 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1336756, + "ts": 1655274482342.029, "dur": 4.514, + "args": { + "External id": 4052110,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "8192", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 10021 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274482344.010, "dur": 0.961, + "args": { + "External id": 4052111,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "0"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 10022 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274482354.298, "dur": 2.146, + "args": { + "External id": 4052112,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[8192, 32000], []], "Ev Idx": 10023 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274482364.945, "dur": 5.751, + "args": { + "External id": 4052113,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[8192, 32000], [], [], [], [], []], "Ev Idx": 10024 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274482366.631, "dur": 3.747, + "args": { + "External id": 4052114,"Record function id": 0, "Concrete Inputs": ["[8192, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10025 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 1336756, "tid": 1336756, + "ts": 1655274482504.957, "dur": 185.968, + "args": { + "External id": 4052115,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 10026 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274482508.915, "dur": 2.802, + "args": { + "External id": 4052116,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10027 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 1336756, "tid": 1336756, + "ts": 1655274482515.007, "dur": 175.493, + "args": { + "External id": 4052117,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[8192, 1], [], [], [0]], "Ev Idx": 10028 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 1336756, "tid": 1336756, + "ts": 1655274482516.470, "dur": 0.389, + "args": { + "External id": 4052118,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 10029 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 1336756, "tid": 1336756, + "ts": 1655274482518.223, "dur": 23.614, + "args": { + "External id": 4052119,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 10030 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 1336756, "tid": 1336756, + "ts": 1655274482543.494, "dur": 4.873, + "args": { + "External id": 4052120,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[8192, 1], []], "Ev Idx": 10031 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274482547.396, "dur": 0.676, + "args": { + "External id": 4052121,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[8192, 1], [], [], []], "Ev Idx": 10032 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336756, "tid": 1336756, + "ts": 1655274482549.282, "dur": 21.530, + "args": { + "External id": 4052122,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 10033 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274482550.555, "dur": 1.311, + "args": { + "External id": 4052123,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10034 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336756, "tid": 1336756, + "ts": 1655274482553.328, "dur": 17.266, + "args": { + "External id": 4052124,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[8192], [0]], "Ev Idx": 10035 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336756, "tid": 1336756, + "ts": 1655274482556.521, "dur": 2.651, + "args": { + "External id": 4052125,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 10036 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 1336756, "tid": 1336756, + "ts": 1655274482574.141, "dur": 22.293, + "args": { + "External id": 4052126,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 10037 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 1336756, "tid": 1336756, + "ts": 1655274482598.122, "dur": 14.494, + "args": { + "External id": 4052127,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 10038 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 1336756, "tid": 1336756, + "ts": 1655274482615.354, "dur": 13.333, + "args": { + "External id": 4052128,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[8192, 1], [8192, 1], []], "Ev Idx": 10039 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 1336756, "tid": 1336756, + "ts": 1655274482630.101, "dur": 12.002, + "args": { + "External id": 4052129,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 10040 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 1336756, "tid": 1336756, + "ts": 1655274482644.010, "dur": 18.857, + "args": { + "External id": 4052130,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[8192, 1], [], [], [], [0]], "Ev Idx": 10041 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336756, "tid": 1336756, + "ts": 1655274482645.877, "dur": 1.592, + "args": { + "External id": 4052131,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 10042 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274482649.355, "dur": 0.776, + "args": { + "External id": 4052132,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[8192], [], [], []], "Ev Idx": 10043 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 1336756, "tid": 1336756, + "ts": 1655274482665.775, "dur": 11.320, + "args": { + "External id": 4052133,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 10044 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336756, "tid": 1336756, + "ts": 1655274482678.296, "dur": 10.975, + "args": { + "External id": 4052134,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 10045 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274482697.660, "dur": 2.069, + "args": { + "External id": 4052135,"Record function id": 0, "Concrete Inputs": ["", "[8192]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 10046 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1336756, + "ts": 1655274482705.853, "dur": 4.154, + "args": { + "External id": 4052136,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "8192", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 10047 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274482708.233, "dur": 0.820, + "args": { + "External id": 4052137,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "0"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 10048 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274482776.833, "dur": 63.207, + "args": { + "External id": 4052138,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [2048, 1]], "Input Dims": [[8192, 32000], [32000, 2048]], "Ev Idx": 10049 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1336756, + "ts": 1655274482845.205, "dur": 5.241, + "args": { + "External id": 4052139,"Record function id": 0, "Concrete Inputs": ["", "0", "0", "8192", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], [], [], []], "Input Dims": [[65536, 2048], [], [], [], []], "Ev Idx": 10050 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274482847.642, "dur": 0.608, + "args": { + "External id": 4052140,"Record function id": 0, "Concrete Inputs": ["", "[8192, 2048]", "[2048, 1]", "0"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[65536, 2048], [], [], []], "Ev Idx": 10051 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1336756, + "ts": 1655274482853.697, "dur": 23.050, + "args": { + "External id": 4052141,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[8192, 2048], [8192, 2048], []], "Ev Idx": 10052 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1336756, + "ts": 1655274482882.019, "dur": 5.518, + "args": { + "External id": 4052142,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[8192, 32000]], "Ev Idx": 10053 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1336756, + "ts": 1655274482883.577, "dur": 3.325, + "args": { + "External id": 4052143,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[8192, 32000], [], []], "Ev Idx": 10054 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274482885.554, "dur": 1.122, + "args": { + "External id": 4052144,"Record function id": 0, "Concrete Inputs": ["", "[32000, 8192]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[8192, 32000], [], [], []], "Ev Idx": 10055 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336756, "tid": 1336756, + "ts": 1655274482890.667, "dur": 41.385, + "args": { + "External id": 4052145,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [2048, 1]], "Input Dims": [[32000, 8192], [8192, 2048]], "Ev Idx": 10056 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274482891.537, "dur": 39.758, + "args": { + "External id": 4052146,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [2048, 1]], "Input Dims": [[32000, 8192], [8192, 2048]], "Ev Idx": 10057 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336756, "tid": 1336756, + "ts": 1655274482936.161, "dur": 14.112, + "args": { + "External id": 4052147,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[32000, 2048], [32000, 2048], []], "Ev Idx": 10058 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1336756, + "ts": 1655274482957.579, "dur": 3.300, + "args": { + "External id": 4052148,"Record function id": 0, "Concrete Inputs": ["", "0", "8192", "16384", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], [], [], []], "Input Dims": [[65536, 2048], [], [], [], []], "Ev Idx": 10059 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274482959.292, "dur": 0.855, + "args": { + "External id": 4052149,"Record function id": 0, "Concrete Inputs": ["", "[8192, 2048]", "[2048, 1]", "16777216"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[65536, 2048], [], [], []], "Ev Idx": 10060 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336756, "tid": 1336756, + "ts": 1655274482964.863, "dur": 86.873, + "args": { + "External id": 4052150,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[8192, 2048], [32000, 2048], []], "Ev Idx": 10061 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1336756, + "ts": 1655274482965.712, "dur": 3.271, + "args": { + "External id": 4052151,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[32000, 2048]], "Ev Idx": 10062 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1336756, + "ts": 1655274482966.446, "dur": 1.994, + "args": { + "External id": 4052152,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[32000, 2048], [], []], "Ev Idx": 10063 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274482967.635, "dur": 0.660, + "args": { + "External id": 4052153,"Record function id": 0, "Concrete Inputs": ["", "[2048, 32000]", "[1, 2048]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[32000, 2048], [], [], []], "Ev Idx": 10064 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336756, "tid": 1336756, + "ts": 1655274482971.251, "dur": 79.709, + "args": { + "External id": 4052154,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048]], "Input Dims": [[8192, 2048], [2048, 32000]], "Ev Idx": 10065 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274482971.966, "dur": 77.910, + "args": { + "External id": 4052155,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048]], "Input Dims": [[8192, 2048], [2048, 32000]], "Ev Idx": 10066 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1336756, + "ts": 1655274483057.621, "dur": 5.835, + "args": { + "External id": 4052156,"Record function id": 0, "Concrete Inputs": ["", "0", "8192", "16384", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 10067 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274483060.031, "dur": 2.079, + "args": { + "External id": 4052157,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "8192"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 10068 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274483069.988, "dur": 1.670, + "args": { + "External id": 4052158,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[8192, 32000], []], "Ev Idx": 10069 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274483079.402, "dur": 8.123, + "args": { + "External id": 4052159,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[8192, 32000], [], [], [], [], []], "Ev Idx": 10070 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274483083.212, "dur": 4.002, + "args": { + "External id": 4052160,"Record function id": 0, "Concrete Inputs": ["[8192, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10071 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 1336756, "tid": 1336756, + "ts": 1655274483174.213, "dur": 167.014, + "args": { + "External id": 4052161,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 10072 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274483176.259, "dur": 2.144, + "args": { + "External id": 4052162,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10073 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 1336756, "tid": 1336756, + "ts": 1655274483179.682, "dur": 161.211, + "args": { + "External id": 4052163,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[8192, 1], [], [], [0]], "Ev Idx": 10074 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 1336756, "tid": 1336756, + "ts": 1655274483180.918, "dur": 0.458, + "args": { + "External id": 4052164,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 10075 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 1336756, "tid": 1336756, + "ts": 1655274483182.357, "dur": 22.032, + "args": { + "External id": 4052165,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 10076 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 1336756, "tid": 1336756, + "ts": 1655274483205.821, "dur": 2.521, + "args": { + "External id": 4052166,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[8192, 1], []], "Ev Idx": 10077 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274483207.511, "dur": 0.582, + "args": { + "External id": 4052167,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[8192, 1], [], [], []], "Ev Idx": 10078 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336756, "tid": 1336756, + "ts": 1655274483211.093, "dur": 21.790, + "args": { + "External id": 4052168,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 10079 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274483212.250, "dur": 1.558, + "args": { + "External id": 4052169,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10080 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336756, "tid": 1336756, + "ts": 1655274483214.975, "dur": 17.597, + "args": { + "External id": 4052170,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[8192], [0]], "Ev Idx": 10081 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336756, "tid": 1336756, + "ts": 1655274483219.049, "dur": 2.821, + "args": { + "External id": 4052171,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 10082 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 1336756, "tid": 1336756, + "ts": 1655274483234.342, "dur": 19.289, + "args": { + "External id": 4052172,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 10083 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 1336756, "tid": 1336756, + "ts": 1655274483254.928, "dur": 11.871, + "args": { + "External id": 4052173,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 10084 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 1336756, "tid": 1336756, + "ts": 1655274483269.410, "dur": 12.713, + "args": { + "External id": 4052174,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[8192, 1], [8192, 1], []], "Ev Idx": 10085 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 1336756, "tid": 1336756, + "ts": 1655274483283.337, "dur": 11.444, + "args": { + "External id": 4052175,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 10086 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 1336756, "tid": 1336756, + "ts": 1655274483296.365, "dur": 19.510, + "args": { + "External id": 4052176,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[8192, 1], [], [], [], [0]], "Ev Idx": 10087 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336756, "tid": 1336756, + "ts": 1655274483299.641, "dur": 1.590, + "args": { + "External id": 4052177,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 10088 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274483303.109, "dur": 0.597, + "args": { + "External id": 4052178,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[8192], [], [], []], "Ev Idx": 10089 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 1336756, "tid": 1336756, + "ts": 1655274483317.113, "dur": 10.968, + "args": { + "External id": 4052179,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 10090 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336756, "tid": 1336756, + "ts": 1655274483329.067, "dur": 10.929, + "args": { + "External id": 4052180,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 10091 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274483347.448, "dur": 1.606, + "args": { + "External id": 4052181,"Record function id": 0, "Concrete Inputs": ["", "[8192]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 10092 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1336756, + "ts": 1655274483356.546, "dur": 3.845, + "args": { + "External id": 4052182,"Record function id": 0, "Concrete Inputs": ["", "0", "8192", "16384", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 10093 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274483358.826, "dur": 0.606, + "args": { + "External id": 4052183,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "8192"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 10094 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274483440.470, "dur": 57.862, + "args": { + "External id": 4052184,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [2048, 1]], "Input Dims": [[8192, 32000], [32000, 2048]], "Ev Idx": 10095 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1336756, + "ts": 1655274483505.531, "dur": 5.954, + "args": { + "External id": 4052185,"Record function id": 0, "Concrete Inputs": ["", "0", "8192", "16384", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], [], [], []], "Input Dims": [[65536, 2048], [], [], [], []], "Ev Idx": 10096 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274483508.637, "dur": 1.475, + "args": { + "External id": 4052186,"Record function id": 0, "Concrete Inputs": ["", "[8192, 2048]", "[2048, 1]", "16777216"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[65536, 2048], [], [], []], "Ev Idx": 10097 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1336756, + "ts": 1655274483513.016, "dur": 22.943, + "args": { + "External id": 4052187,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[8192, 2048], [8192, 2048], []], "Ev Idx": 10098 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1336756, + "ts": 1655274483540.752, "dur": 5.189, + "args": { + "External id": 4052188,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[8192, 32000]], "Ev Idx": 10099 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1336756, + "ts": 1655274483542.220, "dur": 2.958, + "args": { + "External id": 4052189,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[8192, 32000], [], []], "Ev Idx": 10100 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274483543.903, "dur": 1.037, + "args": { + "External id": 4052190,"Record function id": 0, "Concrete Inputs": ["", "[32000, 8192]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[8192, 32000], [], [], []], "Ev Idx": 10101 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336756, "tid": 1336756, + "ts": 1655274483550.116, "dur": 40.318, + "args": { + "External id": 4052191,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [2048, 1]], "Input Dims": [[32000, 8192], [8192, 2048]], "Ev Idx": 10102 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274483551.184, "dur": 38.635, + "args": { + "External id": 4052192,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [2048, 1]], "Input Dims": [[32000, 8192], [8192, 2048]], "Ev Idx": 10103 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336756, "tid": 1336756, + "ts": 1655274483594.380, "dur": 14.672, + "args": { + "External id": 4052193,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[32000, 2048], [32000, 2048], []], "Ev Idx": 10104 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1336756, + "ts": 1655274483614.698, "dur": 3.640, + "args": { + "External id": 4052194,"Record function id": 0, "Concrete Inputs": ["", "0", "16384", "24576", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], [], [], []], "Input Dims": [[65536, 2048], [], [], [], []], "Ev Idx": 10105 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274483616.683, "dur": 0.862, + "args": { + "External id": 4052195,"Record function id": 0, "Concrete Inputs": ["", "[8192, 2048]", "[2048, 1]", "33554432"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[65536, 2048], [], [], []], "Ev Idx": 10106 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336756, "tid": 1336756, + "ts": 1655274483622.346, "dur": 51.010, + "args": { + "External id": 4052196,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[8192, 2048], [32000, 2048], []], "Ev Idx": 10107 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1336756, + "ts": 1655274483623.217, "dur": 6.910, + "args": { + "External id": 4052197,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[32000, 2048]], "Ev Idx": 10108 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1336756, + "ts": 1655274483625.705, "dur": 3.895, + "args": { + "External id": 4052198,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[32000, 2048], [], []], "Ev Idx": 10109 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274483629.055, "dur": 0.434, + "args": { + "External id": 4052199,"Record function id": 0, "Concrete Inputs": ["", "[2048, 32000]", "[1, 2048]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[32000, 2048], [], [], []], "Ev Idx": 10110 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336756, "tid": 1336756, + "ts": 1655274483630.755, "dur": 42.242, + "args": { + "External id": 4052200,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048]], "Input Dims": [[8192, 2048], [2048, 32000]], "Ev Idx": 10111 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274483631.713, "dur": 40.624, + "args": { + "External id": 4052201,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048]], "Input Dims": [[8192, 2048], [2048, 32000]], "Ev Idx": 10112 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1336756, + "ts": 1655274483677.094, "dur": 3.293, + "args": { + "External id": 4052202,"Record function id": 0, "Concrete Inputs": ["", "0", "16384", "24576", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 10113 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274483678.864, "dur": 0.510, + "args": { + "External id": 4052203,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "16384"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 10114 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274483685.854, "dur": 1.414, + "args": { + "External id": 4052204,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[8192, 32000], []], "Ev Idx": 10115 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274483695.971, "dur": 5.712, + "args": { + "External id": 4052205,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[8192, 32000], [], [], [], [], []], "Ev Idx": 10116 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274483697.585, "dur": 3.796, + "args": { + "External id": 4052206,"Record function id": 0, "Concrete Inputs": ["[8192, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10117 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 1336756, "tid": 1336756, + "ts": 1655274483784.295, "dur": 169.333, + "args": { + "External id": 4052207,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 10118 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274483786.371, "dur": 1.952, + "args": { + "External id": 4052208,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10119 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 1336756, "tid": 1336756, + "ts": 1655274483789.753, "dur": 163.525, + "args": { + "External id": 4052209,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[8192, 1], [], [], [0]], "Ev Idx": 10120 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 1336756, "tid": 1336756, + "ts": 1655274483792.374, "dur": 0.222, + "args": { + "External id": 4052210,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 10121 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 1336756, "tid": 1336756, + "ts": 1655274483793.512, "dur": 18.937, + "args": { + "External id": 4052211,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 10122 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 1336756, "tid": 1336756, + "ts": 1655274483814.288, "dur": 2.666, + "args": { + "External id": 4052212,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[8192, 1], []], "Ev Idx": 10123 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274483816.140, "dur": 0.588, + "args": { + "External id": 4052213,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[8192, 1], [], [], []], "Ev Idx": 10124 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336756, "tid": 1336756, + "ts": 1655274483819.359, "dur": 22.755, + "args": { + "External id": 4052214,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 10125 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274483822.486, "dur": 1.464, + "args": { + "External id": 4052215,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10126 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336756, "tid": 1336756, + "ts": 1655274483825.141, "dur": 16.727, + "args": { + "External id": 4052216,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[8192], [0]], "Ev Idx": 10127 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336756, "tid": 1336756, + "ts": 1655274483827.679, "dur": 2.478, + "args": { + "External id": 4052217,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 10128 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 1336756, "tid": 1336756, + "ts": 1655274483843.330, "dur": 17.934, + "args": { + "External id": 4052218,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 10129 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 1336756, "tid": 1336756, + "ts": 1655274483862.744, "dur": 12.623, + "args": { + "External id": 4052219,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 10130 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 1336756, "tid": 1336756, + "ts": 1655274483878.280, "dur": 12.193, + "args": { + "External id": 4052220,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[8192, 1], [8192, 1], []], "Ev Idx": 10131 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 1336756, "tid": 1336756, + "ts": 1655274483891.827, "dur": 12.372, + "args": { + "External id": 4052221,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 10132 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 1336756, "tid": 1336756, + "ts": 1655274483905.832, "dur": 22.140, + "args": { + "External id": 4052222,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[8192, 1], [], [], [], [0]], "Ev Idx": 10133 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336756, "tid": 1336756, + "ts": 1655274483909.212, "dur": 1.397, + "args": { + "External id": 4052223,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 10134 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274483912.305, "dur": 0.665, + "args": { + "External id": 4052224,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[8192], [], [], []], "Ev Idx": 10135 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 1336756, "tid": 1336756, + "ts": 1655274483929.155, "dur": 11.247, + "args": { + "External id": 4052225,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 10136 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336756, "tid": 1336756, + "ts": 1655274483941.575, "dur": 10.745, + "args": { + "External id": 4052226,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 10137 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274483959.942, "dur": 1.683, + "args": { + "External id": 4052227,"Record function id": 0, "Concrete Inputs": ["", "[8192]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 10138 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1336756, + "ts": 1655274483969.434, "dur": 3.139, + "args": { + "External id": 4052228,"Record function id": 0, "Concrete Inputs": ["", "0", "16384", "24576", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 10139 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274483971.412, "dur": 0.357, + "args": { + "External id": 4052229,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "16384"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 10140 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274484074.730, "dur": 56.012, + "args": { + "External id": 4052230,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [2048, 1]], "Input Dims": [[8192, 32000], [32000, 2048]], "Ev Idx": 10141 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1336756, + "ts": 1655274484136.034, "dur": 7.070, + "args": { + "External id": 4052231,"Record function id": 0, "Concrete Inputs": ["", "0", "16384", "24576", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], [], [], []], "Input Dims": [[65536, 2048], [], [], [], []], "Ev Idx": 10142 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274484138.931, "dur": 2.667, + "args": { + "External id": 4052232,"Record function id": 0, "Concrete Inputs": ["", "[8192, 2048]", "[2048, 1]", "33554432"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[65536, 2048], [], [], []], "Ev Idx": 10143 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1336756, + "ts": 1655274484144.551, "dur": 22.480, + "args": { + "External id": 4052233,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[8192, 2048], [8192, 2048], []], "Ev Idx": 10144 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1336756, + "ts": 1655274484172.554, "dur": 6.823, + "args": { + "External id": 4052234,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[8192, 32000]], "Ev Idx": 10145 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1336756, + "ts": 1655274484174.156, "dur": 4.607, + "args": { + "External id": 4052235,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[8192, 32000], [], []], "Ev Idx": 10146 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274484177.703, "dur": 0.843, + "args": { + "External id": 4052236,"Record function id": 0, "Concrete Inputs": ["", "[32000, 8192]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[8192, 32000], [], [], []], "Ev Idx": 10147 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336756, "tid": 1336756, + "ts": 1655274484181.973, "dur": 69.046, + "args": { + "External id": 4052237,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [2048, 1]], "Input Dims": [[32000, 8192], [8192, 2048]], "Ev Idx": 10148 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274484182.959, "dur": 67.377, + "args": { + "External id": 4052238,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [2048, 1]], "Input Dims": [[32000, 8192], [8192, 2048]], "Ev Idx": 10149 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336756, "tid": 1336756, + "ts": 1655274484254.659, "dur": 34.325, + "args": { + "External id": 4052239,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[32000, 2048], [32000, 2048], []], "Ev Idx": 10150 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1336756, + "ts": 1655274484294.710, "dur": 3.429, + "args": { + "External id": 4052240,"Record function id": 0, "Concrete Inputs": ["", "0", "24576", "32768", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], [], [], []], "Input Dims": [[65536, 2048], [], [], [], []], "Ev Idx": 10151 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274484296.706, "dur": 0.581, + "args": { + "External id": 4052241,"Record function id": 0, "Concrete Inputs": ["", "[8192, 2048]", "[2048, 1]", "50331648"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[65536, 2048], [], [], []], "Ev Idx": 10152 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336756, "tid": 1336756, + "ts": 1655274484301.863, "dur": 77.109, + "args": { + "External id": 4052242,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[8192, 2048], [32000, 2048], []], "Ev Idx": 10153 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1336756, + "ts": 1655274484304.179, "dur": 3.477, + "args": { + "External id": 4052243,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[32000, 2048]], "Ev Idx": 10154 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1336756, + "ts": 1655274484305.004, "dur": 2.107, + "args": { + "External id": 4052244,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[32000, 2048], [], []], "Ev Idx": 10155 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274484306.345, "dur": 0.631, + "args": { + "External id": 4052245,"Record function id": 0, "Concrete Inputs": ["", "[2048, 32000]", "[1, 2048]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[32000, 2048], [], [], []], "Ev Idx": 10156 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336756, "tid": 1336756, + "ts": 1655274484308.216, "dur": 70.286, + "args": { + "External id": 4052246,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048]], "Input Dims": [[8192, 2048], [2048, 32000]], "Ev Idx": 10157 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274484308.947, "dur": 69.052, + "args": { + "External id": 4052247,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048]], "Input Dims": [[8192, 2048], [2048, 32000]], "Ev Idx": 10158 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1336756, + "ts": 1655274484382.618, "dur": 3.669, + "args": { + "External id": 4052248,"Record function id": 0, "Concrete Inputs": ["", "0", "24576", "32768", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 10159 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274484384.598, "dur": 0.570, + "args": { + "External id": 4052249,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "24576"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 10160 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274484393.610, "dur": 1.359, + "args": { + "External id": 4052250,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[8192, 32000], []], "Ev Idx": 10161 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274484402.122, "dur": 6.240, + "args": { + "External id": 4052251,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[8192, 32000], [], [], [], [], []], "Ev Idx": 10162 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274484403.889, "dur": 4.210, + "args": { + "External id": 4052252,"Record function id": 0, "Concrete Inputs": ["[8192, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10163 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 1336756, "tid": 1336756, + "ts": 1655274484511.950, "dur": 185.114, + "args": { + "External id": 4052253,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 10164 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274484514.192, "dur": 4.313, + "args": { + "External id": 4052254,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10165 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 1336756, "tid": 1336756, + "ts": 1655274484521.943, "dur": 174.606, + "args": { + "External id": 4052255,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[8192, 1], [], [], [0]], "Ev Idx": 10166 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 1336756, "tid": 1336756, + "ts": 1655274484523.168, "dur": 0.371, + "args": { + "External id": 4052256,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 10167 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 1336756, "tid": 1336756, + "ts": 1655274484536.712, "dur": 22.146, + "args": { + "External id": 4052257,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 10168 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 1336756, "tid": 1336756, + "ts": 1655274484560.509, "dur": 4.898, + "args": { + "External id": 4052258,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[8192, 1], []], "Ev Idx": 10169 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274484564.022, "dur": 1.109, + "args": { + "External id": 4052259,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[8192, 1], [], [], []], "Ev Idx": 10170 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336756, "tid": 1336756, + "ts": 1655274484566.147, "dur": 19.834, + "args": { + "External id": 4052260,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 10171 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274484567.077, "dur": 1.471, + "args": { + "External id": 4052261,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10172 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336756, "tid": 1336756, + "ts": 1655274484569.615, "dur": 16.118, + "args": { + "External id": 4052262,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[8192], [0]], "Ev Idx": 10173 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336756, "tid": 1336756, + "ts": 1655274484572.456, "dur": 2.522, + "args": { + "External id": 4052263,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 10174 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 1336756, "tid": 1336756, + "ts": 1655274484589.307, "dur": 19.832, + "args": { + "External id": 4052264,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 10175 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 1336756, "tid": 1336756, + "ts": 1655274484610.460, "dur": 11.998, + "args": { + "External id": 4052265,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 10176 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 1336756, "tid": 1336756, + "ts": 1655274484625.125, "dur": 12.553, + "args": { + "External id": 4052266,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[8192, 1], [8192, 1], []], "Ev Idx": 10177 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 1336756, "tid": 1336756, + "ts": 1655274484638.805, "dur": 10.973, + "args": { + "External id": 4052267,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 10178 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 1336756, "tid": 1336756, + "ts": 1655274484651.333, "dur": 19.410, + "args": { + "External id": 4052268,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[8192, 1], [], [], [], [0]], "Ev Idx": 10179 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336756, "tid": 1336756, + "ts": 1655274484654.959, "dur": 1.188, + "args": { + "External id": 4052269,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 10180 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274484658.049, "dur": 0.586, + "args": { + "External id": 4052270,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[8192], [], [], []], "Ev Idx": 10181 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 1336756, "tid": 1336756, + "ts": 1655274484671.930, "dur": 11.286, + "args": { + "External id": 4052271,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 10182 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336756, "tid": 1336756, + "ts": 1655274484685.993, "dur": 9.751, + "args": { + "External id": 4052272,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 10183 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274484703.367, "dur": 2.381, + "args": { + "External id": 4052273,"Record function id": 0, "Concrete Inputs": ["", "[8192]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 10184 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1336756, + "ts": 1655274484713.754, "dur": 3.957, + "args": { + "External id": 4052274,"Record function id": 0, "Concrete Inputs": ["", "0", "24576", "32768", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 10185 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274484716.265, "dur": 0.448, + "args": { + "External id": 4052275,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "24576"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 10186 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274484776.727, "dur": 51.509, + "args": { + "External id": 4052276,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [2048, 1]], "Input Dims": [[8192, 32000], [32000, 2048]], "Ev Idx": 10187 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1336756, + "ts": 1655274484832.666, "dur": 4.415, + "args": { + "External id": 4052277,"Record function id": 0, "Concrete Inputs": ["", "0", "24576", "32768", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], [], [], []], "Input Dims": [[65536, 2048], [], [], [], []], "Ev Idx": 10188 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274484835.328, "dur": 0.747, + "args": { + "External id": 4052278,"Record function id": 0, "Concrete Inputs": ["", "[8192, 2048]", "[2048, 1]", "50331648"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[65536, 2048], [], [], []], "Ev Idx": 10189 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1336756, + "ts": 1655274484838.323, "dur": 21.850, + "args": { + "External id": 4052279,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[8192, 2048], [8192, 2048], []], "Ev Idx": 10190 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1336756, + "ts": 1655274484866.266, "dur": 5.041, + "args": { + "External id": 4052280,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[8192, 32000]], "Ev Idx": 10191 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1336756, + "ts": 1655274484867.526, "dur": 3.191, + "args": { + "External id": 4052281,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[8192, 32000], [], []], "Ev Idx": 10192 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274484869.361, "dur": 1.210, + "args": { + "External id": 4052282,"Record function id": 0, "Concrete Inputs": ["", "[32000, 8192]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[8192, 32000], [], [], []], "Ev Idx": 10193 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336756, "tid": 1336756, + "ts": 1655274484873.419, "dur": 39.143, + "args": { + "External id": 4052283,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [2048, 1]], "Input Dims": [[32000, 8192], [8192, 2048]], "Ev Idx": 10194 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274484874.420, "dur": 37.592, + "args": { + "External id": 4052284,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [2048, 1]], "Input Dims": [[32000, 8192], [8192, 2048]], "Ev Idx": 10195 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336756, "tid": 1336756, + "ts": 1655274484916.233, "dur": 13.344, + "args": { + "External id": 4052285,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[32000, 2048], [32000, 2048], []], "Ev Idx": 10196 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1336756, + "ts": 1655274484935.016, "dur": 4.804, + "args": { + "External id": 4052286,"Record function id": 0, "Concrete Inputs": ["", "0", "32768", "40960", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], [], [], []], "Input Dims": [[65536, 2048], [], [], [], []], "Ev Idx": 10197 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274484938.374, "dur": 0.728, + "args": { + "External id": 4052287,"Record function id": 0, "Concrete Inputs": ["", "[8192, 2048]", "[2048, 1]", "67108864"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[65536, 2048], [], [], []], "Ev Idx": 10198 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336756, "tid": 1336756, + "ts": 1655274484943.107, "dur": 82.582, + "args": { + "External id": 4052288,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[8192, 2048], [32000, 2048], []], "Ev Idx": 10199 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1336756, + "ts": 1655274484943.876, "dur": 3.306, + "args": { + "External id": 4052289,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[32000, 2048]], "Ev Idx": 10200 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1336756, + "ts": 1655274484944.482, "dur": 2.220, + "args": { + "External id": 4052290,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[32000, 2048], [], []], "Ev Idx": 10201 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274484945.798, "dur": 0.773, + "args": { + "External id": 4052291,"Record function id": 0, "Concrete Inputs": ["", "[2048, 32000]", "[1, 2048]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[32000, 2048], [], [], []], "Ev Idx": 10202 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336756, "tid": 1336756, + "ts": 1655274484947.778, "dur": 77.297, + "args": { + "External id": 4052292,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048]], "Input Dims": [[8192, 2048], [2048, 32000]], "Ev Idx": 10203 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274484950.682, "dur": 73.395, + "args": { + "External id": 4052293,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048]], "Input Dims": [[8192, 2048], [2048, 32000]], "Ev Idx": 10204 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1336756, + "ts": 1655274485031.924, "dur": 4.462, + "args": { + "External id": 4052294,"Record function id": 0, "Concrete Inputs": ["", "0", "32768", "40960", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 10205 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274485034.382, "dur": 0.795, + "args": { + "External id": 4052295,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "32768"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 10206 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274485042.544, "dur": 1.453, + "args": { + "External id": 4052296,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[8192, 32000], []], "Ev Idx": 10207 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274485051.244, "dur": 6.305, + "args": { + "External id": 4052297,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[8192, 32000], [], [], [], [], []], "Ev Idx": 10208 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274485053.215, "dur": 4.065, + "args": { + "External id": 4052298,"Record function id": 0, "Concrete Inputs": ["[8192, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10209 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 1336756, "tid": 1336756, + "ts": 1655274485137.790, "dur": 170.080, + "args": { + "External id": 4052299,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 10210 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274485141.444, "dur": 2.284, + "args": { + "External id": 4052300,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10211 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 1336756, "tid": 1336756, + "ts": 1655274485144.814, "dur": 162.534, + "args": { + "External id": 4052301,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[8192, 1], [], [], [0]], "Ev Idx": 10212 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 1336756, "tid": 1336756, + "ts": 1655274485145.832, "dur": 0.233, + "args": { + "External id": 4052302,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 10213 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 1336756, "tid": 1336756, + "ts": 1655274485147.088, "dur": 20.024, + "args": { + "External id": 4052303,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 10214 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 1336756, "tid": 1336756, + "ts": 1655274485168.437, "dur": 4.367, + "args": { + "External id": 4052304,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[8192, 1], []], "Ev Idx": 10215 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274485171.849, "dur": 0.668, + "args": { + "External id": 4052305,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[8192, 1], [], [], []], "Ev Idx": 10216 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336756, "tid": 1336756, + "ts": 1655274485177.861, "dur": 21.173, + "args": { + "External id": 4052306,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 10217 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274485180.697, "dur": 1.873, + "args": { + "External id": 4052307,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10218 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336756, "tid": 1336756, + "ts": 1655274485183.682, "dur": 15.122, + "args": { + "External id": 4052308,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[8192], [0]], "Ev Idx": 10219 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336756, "tid": 1336756, + "ts": 1655274485186.321, "dur": 2.178, + "args": { + "External id": 4052309,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 10220 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 1336756, "tid": 1336756, + "ts": 1655274485200.498, "dur": 18.729, + "args": { + "External id": 4052310,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 10221 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 1336756, "tid": 1336756, + "ts": 1655274485220.477, "dur": 14.472, + "args": { + "External id": 4052311,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 10222 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 1336756, "tid": 1336756, + "ts": 1655274485237.216, "dur": 12.073, + "args": { + "External id": 4052312,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[8192, 1], [8192, 1], []], "Ev Idx": 10223 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 1336756, "tid": 1336756, + "ts": 1655274485250.748, "dur": 11.214, + "args": { + "External id": 4052313,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 10224 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 1336756, "tid": 1336756, + "ts": 1655274485263.489, "dur": 18.735, + "args": { + "External id": 4052314,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[8192, 1], [], [], [], [0]], "Ev Idx": 10225 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336756, "tid": 1336756, + "ts": 1655274485265.252, "dur": 1.351, + "args": { + "External id": 4052315,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 10226 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274485269.692, "dur": 0.622, + "args": { + "External id": 4052316,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[8192], [], [], []], "Ev Idx": 10227 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 1336756, "tid": 1336756, + "ts": 1655274485283.424, "dur": 10.841, + "args": { + "External id": 4052317,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 10228 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336756, "tid": 1336756, + "ts": 1655274485295.120, "dur": 11.253, + "args": { + "External id": 4052318,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 10229 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274485313.805, "dur": 1.843, + "args": { + "External id": 4052319,"Record function id": 0, "Concrete Inputs": ["", "[8192]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 10230 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1336756, + "ts": 1655274485322.664, "dur": 3.160, + "args": { + "External id": 4052320,"Record function id": 0, "Concrete Inputs": ["", "0", "32768", "40960", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 10231 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274485324.613, "dur": 0.458, + "args": { + "External id": 4052321,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "32768"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 10232 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274485383.177, "dur": 69.046, + "args": { + "External id": 4052322,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [2048, 1]], "Input Dims": [[8192, 32000], [32000, 2048]], "Ev Idx": 10233 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1336756, + "ts": 1655274485458.319, "dur": 6.981, + "args": { + "External id": 4052323,"Record function id": 0, "Concrete Inputs": ["", "0", "32768", "40960", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], [], [], []], "Input Dims": [[65536, 2048], [], [], [], []], "Ev Idx": 10234 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274485462.622, "dur": 1.260, + "args": { + "External id": 4052324,"Record function id": 0, "Concrete Inputs": ["", "[8192, 2048]", "[2048, 1]", "67108864"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[65536, 2048], [], [], []], "Ev Idx": 10235 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1336756, + "ts": 1655274485466.745, "dur": 21.612, + "args": { + "External id": 4052325,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[8192, 2048], [8192, 2048], []], "Ev Idx": 10236 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1336756, + "ts": 1655274485493.344, "dur": 5.119, + "args": { + "External id": 4052326,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[8192, 32000]], "Ev Idx": 10237 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1336756, + "ts": 1655274485494.890, "dur": 2.958, + "args": { + "External id": 4052327,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[8192, 32000], [], []], "Ev Idx": 10238 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274485496.419, "dur": 1.240, + "args": { + "External id": 4052328,"Record function id": 0, "Concrete Inputs": ["", "[32000, 8192]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[8192, 32000], [], [], []], "Ev Idx": 10239 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336756, "tid": 1336756, + "ts": 1655274485501.272, "dur": 44.369, + "args": { + "External id": 4052329,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [2048, 1]], "Input Dims": [[32000, 8192], [8192, 2048]], "Ev Idx": 10240 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274485504.077, "dur": 40.900, + "args": { + "External id": 4052330,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [2048, 1]], "Input Dims": [[32000, 8192], [8192, 2048]], "Ev Idx": 10241 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336756, "tid": 1336756, + "ts": 1655274485549.284, "dur": 13.716, + "args": { + "External id": 4052331,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[32000, 2048], [32000, 2048], []], "Ev Idx": 10242 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1336756, + "ts": 1655274485568.444, "dur": 3.452, + "args": { + "External id": 4052332,"Record function id": 0, "Concrete Inputs": ["", "0", "40960", "49152", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], [], [], []], "Input Dims": [[65536, 2048], [], [], [], []], "Ev Idx": 10243 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274485570.374, "dur": 0.608, + "args": { + "External id": 4052333,"Record function id": 0, "Concrete Inputs": ["", "[8192, 2048]", "[2048, 1]", "83886080"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[65536, 2048], [], [], []], "Ev Idx": 10244 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336756, "tid": 1336756, + "ts": 1655274485575.590, "dur": 45.492, + "args": { + "External id": 4052334,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[8192, 2048], [32000, 2048], []], "Ev Idx": 10245 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1336756, + "ts": 1655274485576.280, "dur": 4.755, + "args": { + "External id": 4052335,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[32000, 2048]], "Ev Idx": 10246 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1336756, + "ts": 1655274485577.011, "dur": 3.565, + "args": { + "External id": 4052336,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[32000, 2048], [], []], "Ev Idx": 10247 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274485579.848, "dur": 0.596, + "args": { + "External id": 4052337,"Record function id": 0, "Concrete Inputs": ["", "[2048, 32000]", "[1, 2048]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[32000, 2048], [], [], []], "Ev Idx": 10248 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336756, "tid": 1336756, + "ts": 1655274485581.549, "dur": 39.051, + "args": { + "External id": 4052338,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048]], "Input Dims": [[8192, 2048], [2048, 32000]], "Ev Idx": 10249 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274485582.059, "dur": 38.019, + "args": { + "External id": 4052339,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048]], "Input Dims": [[8192, 2048], [2048, 32000]], "Ev Idx": 10250 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1336756, + "ts": 1655274485624.640, "dur": 3.262, + "args": { + "External id": 4052340,"Record function id": 0, "Concrete Inputs": ["", "0", "40960", "49152", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 10251 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274485626.486, "dur": 0.454, + "args": { + "External id": 4052341,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "40960"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 10252 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274485633.238, "dur": 1.329, + "args": { + "External id": 4052342,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[8192, 32000], []], "Ev Idx": 10253 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274485642.849, "dur": 7.106, + "args": { + "External id": 4052343,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[8192, 32000], [], [], [], [], []], "Ev Idx": 10254 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274485644.365, "dur": 5.319, + "args": { + "External id": 4052344,"Record function id": 0, "Concrete Inputs": ["[8192, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10255 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 1336756, "tid": 1336756, + "ts": 1655274485725.595, "dur": 163.075, + "args": { + "External id": 4052345,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 10256 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274485727.238, "dur": 1.941, + "args": { + "External id": 4052346,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10257 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 1336756, "tid": 1336756, + "ts": 1655274485730.516, "dur": 157.703, + "args": { + "External id": 4052347,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[8192, 1], [], [], [0]], "Ev Idx": 10258 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 1336756, "tid": 1336756, + "ts": 1655274485731.612, "dur": 0.188, + "args": { + "External id": 4052348,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 10259 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 1336756, "tid": 1336756, + "ts": 1655274485734.322, "dur": 20.323, + "args": { + "External id": 4052349,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 10260 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 1336756, "tid": 1336756, + "ts": 1655274485756.152, "dur": 2.559, + "args": { + "External id": 4052350,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[8192, 1], []], "Ev Idx": 10261 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274485757.630, "dur": 0.820, + "args": { + "External id": 4052351,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[8192, 1], [], [], []], "Ev Idx": 10262 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336756, "tid": 1336756, + "ts": 1655274485759.407, "dur": 22.134, + "args": { + "External id": 4052352,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 10263 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274485760.311, "dur": 1.735, + "args": { + "External id": 4052353,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10264 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336756, "tid": 1336756, + "ts": 1655274485763.019, "dur": 18.268, + "args": { + "External id": 4052354,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[8192], [0]], "Ev Idx": 10265 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336756, "tid": 1336756, + "ts": 1655274485767.308, "dur": 2.631, + "args": { + "External id": 4052355,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 10266 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 1336756, "tid": 1336756, + "ts": 1655274485783.010, "dur": 18.442, + "args": { + "External id": 4052356,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 10267 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 1336756, "tid": 1336756, + "ts": 1655274485802.794, "dur": 12.002, + "args": { + "External id": 4052357,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 10268 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 1336756, "tid": 1336756, + "ts": 1655274485817.319, "dur": 12.933, + "args": { + "External id": 4052358,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[8192, 1], [8192, 1], []], "Ev Idx": 10269 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 1336756, "tid": 1336756, + "ts": 1655274485831.396, "dur": 10.713, + "args": { + "External id": 4052359,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 10270 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 1336756, "tid": 1336756, + "ts": 1655274485845.008, "dur": 18.049, + "args": { + "External id": 4052360,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[8192, 1], [], [], [], [0]], "Ev Idx": 10271 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336756, "tid": 1336756, + "ts": 1655274485846.843, "dur": 1.488, + "args": { + "External id": 4052361,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 10272 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274485850.259, "dur": 0.669, + "args": { + "External id": 4052362,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[8192], [], [], []], "Ev Idx": 10273 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 1336756, "tid": 1336756, + "ts": 1655274485864.274, "dur": 10.884, + "args": { + "External id": 4052363,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 10274 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336756, "tid": 1336756, + "ts": 1655274485876.104, "dur": 11.048, + "args": { + "External id": 4052364,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 10275 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274485895.812, "dur": 1.588, + "args": { + "External id": 4052365,"Record function id": 0, "Concrete Inputs": ["", "[8192]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 10276 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1336756, + "ts": 1655274485905.310, "dur": 3.197, + "args": { + "External id": 4052366,"Record function id": 0, "Concrete Inputs": ["", "0", "40960", "49152", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 10277 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274485907.407, "dur": 0.412, + "args": { + "External id": 4052367,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "40960"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 10278 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274485970.487, "dur": 88.437, + "args": { + "External id": 4052368,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [2048, 1]], "Input Dims": [[8192, 32000], [32000, 2048]], "Ev Idx": 10279 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1336756, + "ts": 1655274486066.064, "dur": 6.344, + "args": { + "External id": 4052369,"Record function id": 0, "Concrete Inputs": ["", "0", "40960", "49152", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], [], [], []], "Input Dims": [[65536, 2048], [], [], [], []], "Ev Idx": 10280 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274486069.430, "dur": 1.403, + "args": { + "External id": 4052370,"Record function id": 0, "Concrete Inputs": ["", "[8192, 2048]", "[2048, 1]", "83886080"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[65536, 2048], [], [], []], "Ev Idx": 10281 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1336756, + "ts": 1655274486073.792, "dur": 24.205, + "args": { + "External id": 4052371,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[8192, 2048], [8192, 2048], []], "Ev Idx": 10282 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1336756, + "ts": 1655274486103.661, "dur": 6.600, + "args": { + "External id": 4052372,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[8192, 32000]], "Ev Idx": 10283 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1336756, + "ts": 1655274486105.020, "dur": 4.356, + "args": { + "External id": 4052373,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[8192, 32000], [], []], "Ev Idx": 10284 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274486108.174, "dur": 0.996, + "args": { + "External id": 4052374,"Record function id": 0, "Concrete Inputs": ["", "[32000, 8192]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[8192, 32000], [], [], []], "Ev Idx": 10285 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336756, "tid": 1336756, + "ts": 1655274486113.222, "dur": 43.097, + "args": { + "External id": 4052375,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [2048, 1]], "Input Dims": [[32000, 8192], [8192, 2048]], "Ev Idx": 10286 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274486114.286, "dur": 41.335, + "args": { + "External id": 4052376,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [2048, 1]], "Input Dims": [[32000, 8192], [8192, 2048]], "Ev Idx": 10287 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336756, "tid": 1336756, + "ts": 1655274486160.397, "dur": 14.715, + "args": { + "External id": 4052377,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[32000, 2048], [32000, 2048], []], "Ev Idx": 10288 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1336756, + "ts": 1655274486180.899, "dur": 3.506, + "args": { + "External id": 4052378,"Record function id": 0, "Concrete Inputs": ["", "0", "49152", "57344", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], [], [], []], "Input Dims": [[65536, 2048], [], [], [], []], "Ev Idx": 10289 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274486182.958, "dur": 0.623, + "args": { + "External id": 4052379,"Record function id": 0, "Concrete Inputs": ["", "[8192, 2048]", "[2048, 1]", "100663296"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[65536, 2048], [], [], []], "Ev Idx": 10290 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336756, "tid": 1336756, + "ts": 1655274486189.751, "dur": 48.004, + "args": { + "External id": 4052380,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[8192, 2048], [32000, 2048], []], "Ev Idx": 10291 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1336756, + "ts": 1655274486190.743, "dur": 5.071, + "args": { + "External id": 4052381,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[32000, 2048]], "Ev Idx": 10292 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1336756, + "ts": 1655274486191.443, "dur": 3.772, + "args": { + "External id": 4052382,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[32000, 2048], [], []], "Ev Idx": 10293 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274486192.778, "dur": 2.260, + "args": { + "External id": 4052383,"Record function id": 0, "Concrete Inputs": ["", "[2048, 32000]", "[1, 2048]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[32000, 2048], [], [], []], "Ev Idx": 10294 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336756, "tid": 1336756, + "ts": 1655274486196.343, "dur": 41.003, + "args": { + "External id": 4052384,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048]], "Input Dims": [[8192, 2048], [2048, 32000]], "Ev Idx": 10295 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274486197.031, "dur": 39.687, + "args": { + "External id": 4052385,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048]], "Input Dims": [[8192, 2048], [2048, 32000]], "Ev Idx": 10296 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1336756, + "ts": 1655274486241.583, "dur": 3.571, + "args": { + "External id": 4052386,"Record function id": 0, "Concrete Inputs": ["", "0", "49152", "57344", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 10297 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274486243.531, "dur": 0.627, + "args": { + "External id": 4052387,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "49152"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 10298 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274486252.431, "dur": 1.458, + "args": { + "External id": 4052388,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[8192, 32000], []], "Ev Idx": 10299 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274486261.558, "dur": 5.606, + "args": { + "External id": 4052389,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[8192, 32000], [], [], [], [], []], "Ev Idx": 10300 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274486263.057, "dur": 3.852, + "args": { + "External id": 4052390,"Record function id": 0, "Concrete Inputs": ["[8192, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10301 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 1336756, "tid": 1336756, + "ts": 1655274486348.660, "dur": 185.170, + "args": { + "External id": 4052391,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 10302 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274486350.668, "dur": 1.660, + "args": { + "External id": 4052392,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10303 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 1336756, "tid": 1336756, + "ts": 1655274486353.997, "dur": 179.286, + "args": { + "External id": 4052393,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[8192, 1], [], [], [0]], "Ev Idx": 10304 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 1336756, "tid": 1336756, + "ts": 1655274486356.686, "dur": 0.329, + "args": { + "External id": 4052394,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 10305 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 1336756, "tid": 1336756, + "ts": 1655274486359.868, "dur": 19.662, + "args": { + "External id": 4052395,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 10306 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 1336756, "tid": 1336756, + "ts": 1655274486380.918, "dur": 2.506, + "args": { + "External id": 4052396,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[8192, 1], []], "Ev Idx": 10307 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274486382.597, "dur": 0.590, + "args": { + "External id": 4052397,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[8192, 1], [], [], []], "Ev Idx": 10308 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336756, "tid": 1336756, + "ts": 1655274486384.353, "dur": 20.879, + "args": { + "External id": 4052398,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 10309 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274486385.442, "dur": 2.973, + "args": { + "External id": 4052399,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10310 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336756, "tid": 1336756, + "ts": 1655274486389.441, "dur": 15.520, + "args": { + "External id": 4052400,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[8192], [0]], "Ev Idx": 10311 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336756, "tid": 1336756, + "ts": 1655274486391.770, "dur": 2.850, + "args": { + "External id": 4052401,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 10312 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 1336756, "tid": 1336756, + "ts": 1655274486406.652, "dur": 35.798, + "args": { + "External id": 4052402,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 10313 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 1336756, "tid": 1336756, + "ts": 1655274486444.641, "dur": 12.772, + "args": { + "External id": 4052403,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 10314 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 1336756, "tid": 1336756, + "ts": 1655274486461.763, "dur": 12.545, + "args": { + "External id": 4052404,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[8192, 1], [8192, 1], []], "Ev Idx": 10315 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 1336756, "tid": 1336756, + "ts": 1655274486475.668, "dur": 11.922, + "args": { + "External id": 4052405,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 10316 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 1336756, "tid": 1336756, + "ts": 1655274486489.477, "dur": 17.794, + "args": { + "External id": 4052406,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[8192, 1], [], [], [], [0]], "Ev Idx": 10317 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336756, "tid": 1336756, + "ts": 1655274486491.141, "dur": 1.462, + "args": { + "External id": 4052407,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 10318 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274486494.228, "dur": 0.958, + "args": { + "External id": 4052408,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[8192], [], [], []], "Ev Idx": 10319 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 1336756, "tid": 1336756, + "ts": 1655274486508.560, "dur": 11.526, + "args": { + "External id": 4052409,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 10320 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336756, "tid": 1336756, + "ts": 1655274486521.128, "dur": 11.177, + "args": { + "External id": 4052410,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 10321 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274486542.225, "dur": 2.221, + "args": { + "External id": 4052411,"Record function id": 0, "Concrete Inputs": ["", "[8192]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 10322 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1336756, + "ts": 1655274486552.111, "dur": 3.482, + "args": { + "External id": 4052412,"Record function id": 0, "Concrete Inputs": ["", "0", "49152", "57344", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 10323 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274486554.298, "dur": 0.369, + "args": { + "External id": 4052413,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "49152"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 10324 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274486616.899, "dur": 50.354, + "args": { + "External id": 4052414,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [2048, 1]], "Input Dims": [[8192, 32000], [32000, 2048]], "Ev Idx": 10325 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1336756, + "ts": 1655274486671.889, "dur": 4.758, + "args": { + "External id": 4052415,"Record function id": 0, "Concrete Inputs": ["", "0", "49152", "57344", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], [], [], []], "Input Dims": [[65536, 2048], [], [], [], []], "Ev Idx": 10326 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274486674.664, "dur": 1.004, + "args": { + "External id": 4052416,"Record function id": 0, "Concrete Inputs": ["", "[8192, 2048]", "[2048, 1]", "100663296"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[65536, 2048], [], [], []], "Ev Idx": 10327 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1336756, + "ts": 1655274486678.043, "dur": 20.230, + "args": { + "External id": 4052417,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[8192, 2048], [8192, 2048], []], "Ev Idx": 10328 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1336756, + "ts": 1655274486702.508, "dur": 7.970, + "args": { + "External id": 4052418,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[8192, 32000]], "Ev Idx": 10329 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1336756, + "ts": 1655274486705.457, "dur": 4.298, + "args": { + "External id": 4052419,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[8192, 32000], [], []], "Ev Idx": 10330 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274486707.223, "dur": 2.372, + "args": { + "External id": 4052420,"Record function id": 0, "Concrete Inputs": ["", "[32000, 8192]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[8192, 32000], [], [], []], "Ev Idx": 10331 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336756, "tid": 1336756, + "ts": 1655274486713.063, "dur": 38.727, + "args": { + "External id": 4052421,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [2048, 1]], "Input Dims": [[32000, 8192], [8192, 2048]], "Ev Idx": 10332 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274486714.024, "dur": 37.130, + "args": { + "External id": 4052422,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [2048, 1]], "Input Dims": [[32000, 8192], [8192, 2048]], "Ev Idx": 10333 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336756, "tid": 1336756, + "ts": 1655274486755.447, "dur": 14.918, + "args": { + "External id": 4052423,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[32000, 2048], [32000, 2048], []], "Ev Idx": 10334 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1336756, + "ts": 1655274486775.744, "dur": 5.543, + "args": { + "External id": 4052424,"Record function id": 0, "Concrete Inputs": ["", "0", "57344", "65536", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], [], [], []], "Input Dims": [[65536, 2048], [], [], [], []], "Ev Idx": 10335 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274486779.506, "dur": 0.935, + "args": { + "External id": 4052425,"Record function id": 0, "Concrete Inputs": ["", "[8192, 2048]", "[2048, 1]", "117440512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[65536, 2048], [], [], []], "Ev Idx": 10336 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336756, "tid": 1336756, + "ts": 1655274486784.735, "dur": 45.712, + "args": { + "External id": 4052426,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["c10::BFloat16", "c10::BFloat16", ""], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[8192, 2048], [32000, 2048], []], "Ev Idx": 10337 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1336756, + "ts": 1655274486785.598, "dur": 3.360, + "args": { + "External id": 4052427,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[32000, 2048]], "Ev Idx": 10338 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1336756, + "ts": 1655274486786.397, "dur": 1.960, + "args": { + "External id": 4052428,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], []], "Input Dims": [[32000, 2048], [], []], "Ev Idx": 10339 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274486787.624, "dur": 0.519, + "args": { + "External id": 4052429,"Record function id": 0, "Concrete Inputs": ["", "[2048, 32000]", "[1, 2048]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[32000, 2048], [], [], []], "Ev Idx": 10340 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336756, "tid": 1336756, + "ts": 1655274486789.747, "dur": 40.263, + "args": { + "External id": 4052430,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048]], "Input Dims": [[8192, 2048], [2048, 32000]], "Ev Idx": 10341 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274486790.175, "dur": 39.272, + "args": { + "External id": 4052431,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[2048, 1], [1, 2048]], "Input Dims": [[8192, 2048], [2048, 32000]], "Ev Idx": 10342 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1336756, + "ts": 1655274486835.882, "dur": 3.380, + "args": { + "External id": 4052432,"Record function id": 0, "Concrete Inputs": ["", "0", "57344", "65536", "1"], "Input type": ["long int", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 10343 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274486837.585, "dur": 0.564, + "args": { + "External id": 4052433,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "57344"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 10344 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274486843.720, "dur": 1.328, + "args": { + "External id": 4052434,"Record function id": 0, "Concrete Inputs": ["", "[-1, 32000]"], "Input type": ["c10::BFloat16", "ScalarList"], "Input Strides": [[32000, 1], []], "Input Dims": [[8192, 32000], []], "Ev Idx": 10345 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::new_empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274486851.722, "dur": 5.394, + "args": { + "External id": 4052435,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "6", "", "", "False"], "Input type": ["c10::BFloat16", "ScalarList", "Scalar", "", "", "Scalar"], "Input Strides": [[32000, 1], [], [], [], [], []], "Input Dims": [[8192, 32000], [], [], [], [], []], "Ev Idx": 10346 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274486853.360, "dur": 3.495, + "args": { + "External id": 4052436,"Record function id": 0, "Concrete Inputs": ["[8192, 1]", "6", "0", "", "False", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10347 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 1336756, "tid": 1336756, + "ts": 1655274486931.364, "dur": 200.861, + "args": { + "External id": 4052437,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 10348 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274486933.098, "dur": 1.984, + "args": { + "External id": 4052438,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10349 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::logsumexp", "pid": 1336756, "tid": 1336756, + "ts": 1655274486938.470, "dur": 193.311, + "args": { + "External id": 4052439,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", "float"], "Input Strides": [[1, 1], [], [], [1]], "Input Dims": [[8192, 1], [], [], [0]], "Ev Idx": 10350 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::real", "pid": 1336756, "tid": 1336756, + "ts": 1655274486939.698, "dur": 0.222, + "args": { + "External id": 4052440,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 10351 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::amax", "pid": 1336756, "tid": 1336756, + "ts": 1655274486940.777, "dur": 17.590, + "args": { + "External id": 4052441,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "True"], "Input type": ["float", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[8192, 1], [], []], "Ev Idx": 10352 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::squeeze", "pid": 1336756, "tid": 1336756, + "ts": 1655274486959.644, "dur": 4.438, + "args": { + "External id": 4052442,"Record function id": 0, "Concrete Inputs": ["", "[-1]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1, 1], []], "Input Dims": [[8192, 1], []], "Ev Idx": 10353 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274486961.424, "dur": 2.367, + "args": { + "External id": 4052443,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[8192, 1], [], [], []], "Ev Idx": 10354 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336756, "tid": 1336756, + "ts": 1655274486964.854, "dur": 54.737, + "args": { + "External id": 4052444,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 10355 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655274486966.076, "dur": 1.400, + "args": { + "External id": 4052445,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10356 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336756, "tid": 1336756, + "ts": 1655274486969.952, "dur": 48.843, + "args": { + "External id": 4052446,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[1], [1]], "Input Dims": [[8192], [0]], "Ev Idx": 10357 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336756, "tid": 1336756, + "ts": 1655274486972.086, "dur": 1.910, + "args": { + "External id": 4052447,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 10358 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 1336756, "tid": 1336756, + "ts": 1655274487021.719, "dur": 22.163, + "args": { + "External id": 4052448,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 10359 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::masked_fill_", "pid": 1336756, "tid": 1336756, + "ts": 1655274487045.220, "dur": 12.228, + "args": { + "External id": 4052449,"Record function id": 0, "Concrete Inputs": ["", "", "0"], "Input type": ["float", "bool", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 10360 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sub", "pid": 1336756, "tid": 1336756, + "ts": 1655274487059.888, "dur": 12.382, + "args": { + "External id": 4052450,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1, 1], [1, 1], []], "Input Dims": [[8192, 1], [8192, 1], []], "Ev Idx": 10361 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::exp_", "pid": 1336756, "tid": 1336756, + "ts": 1655274487073.531, "dur": 11.366, + "args": { + "External id": 4052451,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1, 1]], "Input Dims": [[8192, 1]], "Ev Idx": 10362 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 1336756, "tid": 1336756, + "ts": 1655274487086.654, "dur": 18.181, + "args": { + "External id": 4052452,"Record function id": 0, "Concrete Inputs": ["", "[-1]", "False", "", ""], "Input type": ["float", "ScalarList", "Scalar", "", "float"], "Input Strides": [[1, 1], [], [], [], [1]], "Input Dims": [[8192, 1], [], [], [], [0]], "Ev Idx": 10363 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336756, "tid": 1336756, + "ts": 1655274487088.422, "dur": 1.499, + "args": { + "External id": 4052453,"Record function id": 0, "Concrete Inputs": ["", "[8192]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 10364 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274487091.632, "dur": 0.597, + "args": { + "External id": 4052454,"Record function id": 0, "Concrete Inputs": ["", "[8192, 1]", "[1, 0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[8192], [], [], []], "Ev Idx": 10365 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::log_", "pid": 1336756, "tid": 1336756, + "ts": 1655274487107.763, "dur": 10.505, + "args": { + "External id": 4052455,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[8192]], "Ev Idx": 10366 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336756, "tid": 1336756, + "ts": 1655274487119.384, "dur": 11.319, + "args": { + "External id": 4052456,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[8192], [8192], []], "Ev Idx": 10367 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655274487139.055, "dur": 2.077, + "args": { + "External id": 4052457,"Record function id": 0, "Concrete Inputs": ["", "[8192]"], "Input type": ["float", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[8192], []], "Ev Idx": 10368 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1336756, + "ts": 1655274487149.459, "dur": 3.800, + "args": { + "External id": 4052458,"Record function id": 0, "Concrete Inputs": ["", "0", "57344", "65536", "1"], "Input type": ["float", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], []], "Input Dims": [[65536], [], [], [], []], "Ev Idx": 10369 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274487151.867, "dur": 0.546, + "args": { + "External id": 4052459,"Record function id": 0, "Concrete Inputs": ["", "[8192]", "[1]", "57344"], "Input type": ["float", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 10370 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274487214.133, "dur": 51.932, + "args": { + "External id": 4052460,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[32000, 1], [2048, 1]], "Input Dims": [[8192, 32000], [32000, 2048]], "Ev Idx": 10371 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1336756, + "ts": 1655274487270.654, "dur": 7.197, + "args": { + "External id": 4052461,"Record function id": 0, "Concrete Inputs": ["", "0", "57344", "65536", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar", "Scalar", "Scalar"], "Input Strides": [[2048, 1], [], [], [], []], "Input Dims": [[65536, 2048], [], [], [], []], "Ev Idx": 10372 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274487274.402, "dur": 2.435, + "args": { + "External id": 4052462,"Record function id": 0, "Concrete Inputs": ["", "[8192, 2048]", "[2048, 1]", "117440512"], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[2048, 1], [], [], []], "Input Dims": [[65536, 2048], [], [], []], "Ev Idx": 10373 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1336756, + "ts": 1655274487279.282, "dur": 21.553, + "args": { + "External id": 4052463,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[8192, 2048], [8192, 2048], []], "Ev Idx": 10374 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1336756, + "ts": 1655274487305.163, "dur": 4.871, + "args": { + "External id": 4052464,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[32000, 1]], "Input Dims": [[8192, 32000]], "Ev Idx": 10375 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1336756, + "ts": 1655274487306.479, "dur": 2.934, + "args": { + "External id": 4052465,"Record function id": 0, "Concrete Inputs": ["", "0", "1"], "Input type": ["c10::BFloat16", "Scalar", "Scalar"], "Input Strides": [[32000, 1], [], []], "Input Dims": [[8192, 32000], [], []], "Ev Idx": 10376 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274487308.421, "dur": 0.784, + "args": { + "External id": 4052466,"Record function id": 0, "Concrete Inputs": ["", "[32000, 8192]", "[1, 32000]", ""], "Input type": ["c10::BFloat16", "ScalarList", "ScalarList", ""], "Input Strides": [[32000, 1], [], [], []], "Input Dims": [[8192, 32000], [], [], []], "Ev Idx": 10377 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::matmul", "pid": 1336756, "tid": 1336756, + "ts": 1655274487312.491, "dur": 38.873, + "args": { + "External id": 4052467,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [2048, 1]], "Input Dims": [[32000, 8192], [8192, 2048]], "Ev Idx": 10378 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1655274487313.479, "dur": 37.261, + "args": { + "External id": 4052468,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["c10::BFloat16", "c10::BFloat16"], "Input Strides": [[1, 32000], [2048, 1]], "Input Dims": [[32000, 8192], [8192, 2048]], "Ev Idx": 10379 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336756, "tid": 1336756, + "ts": 1655274487356.352, "dur": 12.708, + "args": { + "External id": 4052469,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "c10::BFloat16", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[32000, 2048], [32000, 2048], []], "Ev Idx": 10380 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 1336756, "tid": 1336756, + "ts": 1655274487373.849, "dur": 20.550, + "args": { + "External id": 4052470,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", ""], "Input Strides": [[1], []], "Input Dims": [[65536], []], "Ev Idx": 10381 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 1336756, "tid": 1336756, + "ts": 1655274487375.877, "dur": 18.181, + "args": { + "External id": 4052471,"Record function id": 0, "Concrete Inputs": ["", "[]", "False", ""], "Input type": ["float", "ScalarList", "Scalar", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[65536], [], [], []], "Ev Idx": 10382 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274487380.628, "dur": 0.833, + "args": { + "External id": 4052472,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10383 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655274487399.128, "dur": 40.916, + "args": { + "External id": 4052473,"Record function id": 0, "Concrete Inputs": ["", "", "15", "False", "False", ""], "Input type": ["float", "", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[2048, 1], [], [], [], [], []], "Input Dims": [[32000, 2048], [], [], [], [], []], "Ev Idx": 10384 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336756, "tid": 1336756, + "ts": 1655274487400.784, "dur": 38.988, + "args": { + "External id": 4052474,"Record function id": 0, "Concrete Inputs": ["", "15", "", "", "", "False", ""], "Input type": ["float", "Scalar", "", "", "", "Scalar", ""], "Input Strides": [[2048, 1], [], [], [], [], [], []], "Input Dims": [[32000, 2048], [], [], [], [], [], []], "Ev Idx": 10385 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274487405.026, "dur": 3.970, + "args": { + "External id": 4052475,"Record function id": 0, "Concrete Inputs": ["[32000, 2048]", "[2048, 1]", "15", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10386 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1336756, + "ts": 1655274487410.221, "dur": 28.717, + "args": { + "External id": 4052476,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["c10::BFloat16", "float", "Scalar"], "Input Strides": [[2048, 1], [2048, 1], []], "Input Dims": [[32000, 2048], [32000, 2048], []], "Ev Idx": 10387 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1336756, + "ts": 1655274487453.080, "dur": 6.768, + "args": { + "External id": 4052477,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[65536, 2048]], "Ev Idx": 10388 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1336756, + "ts": 1655274487456.698, "dur": 2.874, + "args": { + "External id": 4052478,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[65536, 2048]], "Ev Idx": 10389 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1336756, + "ts": 1655274487461.116, "dur": 0.998, + "args": { + "External id": 4052479,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[32000, 2048]], "Ev Idx": 10390 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1336756, + "ts": 1655274487461.530, "dur": 0.478, + "args": { + "External id": 4052480,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["c10::BFloat16"], "Input Strides": [[2048, 1]], "Input Dims": [[32000, 2048]], "Ev Idx": 10391 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336756, "tid": 1336756, + "ts": 1655274487540.030, "dur": 25.851, + "args": { + "External id": 4052481,"Sequence number": 40618580, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[1], [], []], "Ev Idx": 10392 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add_", "pid": 1336756, "tid": 1336756, + "ts": 1655274487567.940, "dur": 12.205, + "args": { + "External id": 4052482,"Sequence number": 40618581, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[1], [], []], "Ev Idx": 10393 + } + }, + { + "ph": "s", "id": 2, "pid": 1336756, "tid": 1336756, "ts": 1655274487567.940, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward", "pid": 1336756, "tid": 1336756, + "ts": 1655274487682.777, "dur": 38.085, + "args": { + "External id": 4052483,"Record function id": 0, "Ev Idx": 10394 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::div", "pid": 1336756, "tid": 1336756, + "ts": 1655274487813.086, "dur": 34.599, + "args": { + "External id": 4052484,"Sequence number": 40618582, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "long int"], "Input Strides": [[1], []], "Input Dims": [[1], []], "Ev Idx": 10395 + } + }, + { + "ph": "s", "id": 1, "pid": 1336756, "tid": 1336756, "ts": 1655274487813.086, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::ones_like", "pid": 1336756, "tid": 1336756, + "ts": 1655274487899.775, "dur": 26.052, + "args": { + "External id": 4052485,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "1"], "Input type": ["float", "", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[1], [], [], [], [], []], "Ev Idx": 10396 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336756, "tid": 1336756, + "ts": 1655274487901.588, "dur": 7.902, + "args": { + "External id": 4052486,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "False", "1"], "Input type": ["float", "", "", "", "Scalar", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[1], [], [], [], [], []], "Ev Idx": 10397 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655274487904.813, "dur": 4.049, + "args": { + "External id": 4052487,"Record function id": 0, "Concrete Inputs": ["[1]", "[1]", "6", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10398 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 1336756, "tid": 1336756, + "ts": 1655274487910.831, "dur": 14.616, + "args": { + "External id": 4052488,"Record function id": 0, "Concrete Inputs": ["", "1."], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[1], []], "Ev Idx": 10399 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::div", "pid": 1336756, "tid": 1336756, + "ts": 1655275817139.615, "dur": 71.030, + "args": { + "External id": 4052489,"Sequence number": 40618583, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "long int"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10400 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::div", "pid": 1336756, "tid": 1336756, + "ts": 1655275817220.344, "dur": 20.063, + "args": { + "External id": 4052490,"Sequence number": 40618584, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "long int"], "Input Strides": [[1], []], "Input Dims": [[1], []], "Ev Idx": 10401 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add", "pid": 1336756, "tid": 1336756, + "ts": 1655275817248.235, "dur": 96.928, + "args": { + "External id": 4052491,"Sequence number": 40618585, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "long int", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[1], [], []], "Ev Idx": 10402 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add", "pid": 1336756, "tid": 1336756, + "ts": 1655275817756.178, "dur": 27.077, + "args": { + "External id": 4052492,"Sequence number": 40618586, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "long int", "Scalar"], "Input Strides": [[], [], []], "Input Dims": [[], [], []], "Ev Idx": 10403 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add", "pid": 1336756, "tid": 1336756, + "ts": 1655275817789.795, "dur": 13.798, + "args": { + "External id": 4052493,"Sequence number": 40618587, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "long int", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[1], [], []], "Ev Idx": 10404 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_norm", "pid": 1336756, "tid": 1336756, + "ts": 1655275819319.244, "dur": 2718.227, + "args": { + "External id": 4052494,"Record function id": 0, "Concrete Inputs": ["", "2.", ""], "Input type": ["TensorList", "Scalar", ""], "Input Strides": [[], [], []], "Input Dims": [[], [], []], "Ev Idx": 10405 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_norm", "pid": 1336756, "tid": 1336756, + "ts": 1655275819862.431, "dur": 814.689, + "args": { + "External id": 4052495,"Record function id": 0, "Concrete Inputs": ["", "2.", ""], "Input type": ["TensorList", "Scalar", ""], "Input Strides": [[], [], []], "Input Dims": [[], [], []], "Ev Idx": 10406 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zeros", "pid": 1336756, "tid": 1336756, + "ts": 1655275819882.578, "dur": 62.115, + "args": { + "External id": 4052496,"Record function id": 0, "Concrete Inputs": ["[36375]", "6", "0", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 10407 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655275819885.517, "dur": 11.321, + "args": { + "External id": 4052497,"Record function id": 0, "Concrete Inputs": ["[36375]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 10408 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::zero_", "pid": 1336756, "tid": 1336756, + "ts": 1655275819899.401, "dur": 44.991, + "args": { + "External id": 4052498,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[36375]], "Ev Idx": 10409 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 1336756, "tid": 1336756, + "ts": 1655275819904.461, "dur": 39.221, + "args": { + "External id": 4052499,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[36375], []], "Ev Idx": 10410 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822067.698, "dur": 4.252, + "args": { + "External id": 4052500,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10411 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822073.994, "dur": 0.524, + "args": { + "External id": 4052501,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10412 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822075.671, "dur": 0.664, + "args": { + "External id": 4052502,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10413 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822077.322, "dur": 0.427, + "args": { + "External id": 4052503,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10414 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822078.876, "dur": 0.292, + "args": { + "External id": 4052504,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10415 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822084.188, "dur": 0.233, + "args": { + "External id": 4052505,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10416 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822085.634, "dur": 0.230, + "args": { + "External id": 4052506,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10417 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822088.700, "dur": 0.454, + "args": { + "External id": 4052507,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10418 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822089.979, "dur": 0.416, + "args": { + "External id": 4052508,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10419 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822091.342, "dur": 0.450, + "args": { + "External id": 4052509,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10420 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822092.757, "dur": 0.280, + "args": { + "External id": 4052510,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10421 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822093.848, "dur": 0.227, + "args": { + "External id": 4052511,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10422 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822094.808, "dur": 0.220, + "args": { + "External id": 4052512,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10423 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822095.976, "dur": 0.227, + "args": { + "External id": 4052513,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10424 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822096.926, "dur": 0.228, + "args": { + "External id": 4052514,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10425 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822099.537, "dur": 0.219, + "args": { + "External id": 4052515,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10426 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822100.654, "dur": 0.229, + "args": { + "External id": 4052516,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10427 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822101.822, "dur": 0.272, + "args": { + "External id": 4052517,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10428 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822102.822, "dur": 0.221, + "args": { + "External id": 4052518,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10429 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822103.933, "dur": 0.221, + "args": { + "External id": 4052519,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10430 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822104.982, "dur": 0.231, + "args": { + "External id": 4052520,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10431 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822105.998, "dur": 0.216, + "args": { + "External id": 4052521,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10432 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822107.028, "dur": 0.253, + "args": { + "External id": 4052522,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10433 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822109.429, "dur": 0.390, + "args": { + "External id": 4052523,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10434 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822110.548, "dur": 0.220, + "args": { + "External id": 4052524,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10435 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822111.694, "dur": 0.212, + "args": { + "External id": 4052525,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10436 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822112.768, "dur": 0.218, + "args": { + "External id": 4052526,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10437 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822113.761, "dur": 0.213, + "args": { + "External id": 4052527,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10438 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822114.729, "dur": 0.219, + "args": { + "External id": 4052528,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10439 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822115.736, "dur": 0.212, + "args": { + "External id": 4052529,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10440 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822116.914, "dur": 0.219, + "args": { + "External id": 4052530,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10441 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822119.676, "dur": 0.213, + "args": { + "External id": 4052531,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10442 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822120.648, "dur": 0.219, + "args": { + "External id": 4052532,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10443 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822121.931, "dur": 0.229, + "args": { + "External id": 4052533,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10444 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822122.885, "dur": 0.222, + "args": { + "External id": 4052534,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10445 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822123.845, "dur": 0.230, + "args": { + "External id": 4052535,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10446 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822124.820, "dur": 0.230, + "args": { + "External id": 4052536,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10447 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822125.791, "dur": 0.219, + "args": { + "External id": 4052537,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10448 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822126.734, "dur": 0.223, + "args": { + "External id": 4052538,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10449 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822129.240, "dur": 0.227, + "args": { + "External id": 4052539,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10450 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822130.191, "dur": 0.218, + "args": { + "External id": 4052540,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10451 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822131.353, "dur": 0.221, + "args": { + "External id": 4052541,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10452 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822132.303, "dur": 0.218, + "args": { + "External id": 4052542,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10453 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822133.305, "dur": 0.214, + "args": { + "External id": 4052543,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10454 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822134.253, "dur": 0.222, + "args": { + "External id": 4052544,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10455 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822135.210, "dur": 0.213, + "args": { + "External id": 4052545,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10456 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822136.244, "dur": 0.233, + "args": { + "External id": 4052546,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10457 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822138.823, "dur": 0.215, + "args": { + "External id": 4052547,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10458 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822139.870, "dur": 0.230, + "args": { + "External id": 4052548,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10459 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822140.839, "dur": 0.214, + "args": { + "External id": 4052549,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10460 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822143.278, "dur": 0.244, + "args": { + "External id": 4052550,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10461 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822144.297, "dur": 0.215, + "args": { + "External id": 4052551,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10462 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822145.346, "dur": 0.456, + "args": { + "External id": 4052552,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10463 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822146.778, "dur": 0.214, + "args": { + "External id": 4052553,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10464 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822147.768, "dur": 0.215, + "args": { + "External id": 4052554,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10465 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822150.232, "dur": 0.475, + "args": { + "External id": 4052555,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10466 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822151.549, "dur": 0.429, + "args": { + "External id": 4052556,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10467 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822152.746, "dur": 0.211, + "args": { + "External id": 4052557,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10468 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822153.915, "dur": 0.184, + "args": { + "External id": 4052558,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10469 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822154.847, "dur": 0.414, + "args": { + "External id": 4052559,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10470 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822155.992, "dur": 0.386, + "args": { + "External id": 4052560,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10471 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822157.126, "dur": 0.431, + "args": { + "External id": 4052561,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10472 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822158.292, "dur": 0.433, + "args": { + "External id": 4052562,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10473 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822161.017, "dur": 0.219, + "args": { + "External id": 4052563,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10474 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822161.982, "dur": 0.221, + "args": { + "External id": 4052564,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10475 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822163.425, "dur": 0.212, + "args": { + "External id": 4052565,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10476 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822164.529, "dur": 0.229, + "args": { + "External id": 4052566,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10477 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822165.710, "dur": 0.214, + "args": { + "External id": 4052567,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10478 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822166.823, "dur": 0.218, + "args": { + "External id": 4052568,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10479 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822167.795, "dur": 0.213, + "args": { + "External id": 4052569,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10480 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822168.932, "dur": 0.215, + "args": { + "External id": 4052570,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10481 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822171.245, "dur": 0.220, + "args": { + "External id": 4052571,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10482 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822172.202, "dur": 0.216, + "args": { + "External id": 4052572,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10483 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822173.398, "dur": 0.216, + "args": { + "External id": 4052573,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10484 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822174.378, "dur": 0.219, + "args": { + "External id": 4052574,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10485 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822175.522, "dur": 0.219, + "args": { + "External id": 4052575,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10486 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822176.645, "dur": 0.216, + "args": { + "External id": 4052576,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10487 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822179.040, "dur": 0.210, + "args": { + "External id": 4052577,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10488 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822180.181, "dur": 0.230, + "args": { + "External id": 4052578,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10489 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822182.659, "dur": 0.219, + "args": { + "External id": 4052579,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10490 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822183.623, "dur": 0.219, + "args": { + "External id": 4052580,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10491 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822184.584, "dur": 0.213, + "args": { + "External id": 4052581,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10492 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822185.529, "dur": 0.215, + "args": { + "External id": 4052582,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10493 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822186.502, "dur": 0.215, + "args": { + "External id": 4052583,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10494 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822187.457, "dur": 0.217, + "args": { + "External id": 4052584,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10495 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822188.412, "dur": 0.213, + "args": { + "External id": 4052585,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10496 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822189.354, "dur": 0.218, + "args": { + "External id": 4052586,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10497 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822192.095, "dur": 0.211, + "args": { + "External id": 4052587,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10498 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822193.038, "dur": 0.213, + "args": { + "External id": 4052588,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10499 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822194.018, "dur": 0.212, + "args": { + "External id": 4052589,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10500 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822194.992, "dur": 0.213, + "args": { + "External id": 4052590,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10501 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822195.963, "dur": 0.212, + "args": { + "External id": 4052591,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10502 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822196.916, "dur": 0.215, + "args": { + "External id": 4052592,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10503 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822198.554, "dur": 0.208, + "args": { + "External id": 4052593,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10504 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822199.511, "dur": 0.215, + "args": { + "External id": 4052594,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10505 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822202.012, "dur": 0.213, + "args": { + "External id": 4052595,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10506 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822202.973, "dur": 0.225, + "args": { + "External id": 4052596,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10507 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822203.939, "dur": 0.213, + "args": { + "External id": 4052597,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10508 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822204.889, "dur": 0.420, + "args": { + "External id": 4052598,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10509 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822206.139, "dur": 0.210, + "args": { + "External id": 4052599,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10510 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822207.111, "dur": 0.445, + "args": { + "External id": 4052600,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10511 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822208.299, "dur": 0.213, + "args": { + "External id": 4052601,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10512 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822209.309, "dur": 0.219, + "args": { + "External id": 4052602,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10513 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822212.229, "dur": 0.220, + "args": { + "External id": 4052603,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10514 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822213.188, "dur": 0.414, + "args": { + "External id": 4052604,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10515 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822214.345, "dur": 0.213, + "args": { + "External id": 4052605,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10516 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822215.288, "dur": 0.409, + "args": { + "External id": 4052606,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10517 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822216.632, "dur": 0.210, + "args": { + "External id": 4052607,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10518 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822217.651, "dur": 0.662, + "args": { + "External id": 4052608,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10519 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822219.418, "dur": 0.398, + "args": { + "External id": 4052609,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10520 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822220.722, "dur": 0.235, + "args": { + "External id": 4052610,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10521 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822223.161, "dur": 0.298, + "args": { + "External id": 4052611,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10522 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822224.392, "dur": 0.420, + "args": { + "External id": 4052612,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10523 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822225.738, "dur": 0.216, + "args": { + "External id": 4052613,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10524 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822226.835, "dur": 0.401, + "args": { + "External id": 4052614,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10525 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822228.002, "dur": 0.214, + "args": { + "External id": 4052615,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10526 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822229.116, "dur": 3.366, + "args": { + "External id": 4052616,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10527 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822233.228, "dur": 0.212, + "args": { + "External id": 4052617,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10528 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822234.338, "dur": 0.216, + "args": { + "External id": 4052618,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10529 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822237.061, "dur": 0.224, + "args": { + "External id": 4052619,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10530 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822238.265, "dur": 0.216, + "args": { + "External id": 4052620,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10531 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822239.220, "dur": 0.213, + "args": { + "External id": 4052621,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10532 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822240.167, "dur": 0.219, + "args": { + "External id": 4052622,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10533 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822241.132, "dur": 0.213, + "args": { + "External id": 4052623,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10534 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822242.076, "dur": 0.216, + "args": { + "External id": 4052624,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10535 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822243.029, "dur": 0.212, + "args": { + "External id": 4052625,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10536 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822243.980, "dur": 0.213, + "args": { + "External id": 4052626,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10537 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822246.428, "dur": 0.222, + "args": { + "External id": 4052627,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10538 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822247.376, "dur": 0.237, + "args": { + "External id": 4052628,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10539 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822248.909, "dur": 0.220, + "args": { + "External id": 4052629,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10540 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822249.870, "dur": 0.384, + "args": { + "External id": 4052630,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10541 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822251.066, "dur": 0.414, + "args": { + "External id": 4052631,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10542 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822252.407, "dur": 0.391, + "args": { + "External id": 4052632,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10543 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822253.534, "dur": 0.413, + "args": { + "External id": 4052633,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10544 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822254.825, "dur": 0.486, + "args": { + "External id": 4052634,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10545 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822257.755, "dur": 0.264, + "args": { + "External id": 4052635,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10546 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822258.756, "dur": 0.220, + "args": { + "External id": 4052636,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10547 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822259.798, "dur": 0.219, + "args": { + "External id": 4052637,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10548 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822260.905, "dur": 0.219, + "args": { + "External id": 4052638,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10549 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822261.856, "dur": 0.212, + "args": { + "External id": 4052639,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10550 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822262.892, "dur": 0.222, + "args": { + "External id": 4052640,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10551 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822263.855, "dur": 0.223, + "args": { + "External id": 4052641,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10552 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822264.804, "dur": 0.222, + "args": { + "External id": 4052642,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10553 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822267.253, "dur": 0.214, + "args": { + "External id": 4052643,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10554 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822268.196, "dur": 0.224, + "args": { + "External id": 4052644,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10555 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822269.192, "dur": 0.210, + "args": { + "External id": 4052645,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10556 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822270.160, "dur": 0.215, + "args": { + "External id": 4052646,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10557 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822271.373, "dur": 0.213, + "args": { + "External id": 4052647,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10558 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822272.313, "dur": 0.216, + "args": { + "External id": 4052648,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10559 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822273.549, "dur": 0.210, + "args": { + "External id": 4052649,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10560 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822274.512, "dur": 0.214, + "args": { + "External id": 4052650,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10561 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822276.932, "dur": 0.211, + "args": { + "External id": 4052651,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10562 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822277.903, "dur": 0.219, + "args": { + "External id": 4052652,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10563 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822278.885, "dur": 0.213, + "args": { + "External id": 4052653,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10564 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822279.829, "dur": 0.217, + "args": { + "External id": 4052654,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10565 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822280.783, "dur": 0.213, + "args": { + "External id": 4052655,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10566 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822281.721, "dur": 0.215, + "args": { + "External id": 4052656,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10567 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822282.673, "dur": 0.212, + "args": { + "External id": 4052657,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10568 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822283.638, "dur": 0.219, + "args": { + "External id": 4052658,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10569 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822285.945, "dur": 0.213, + "args": { + "External id": 4052659,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10570 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822287.053, "dur": 0.237, + "args": { + "External id": 4052660,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10571 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822291.322, "dur": 0.214, + "args": { + "External id": 4052661,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10572 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822292.443, "dur": 0.215, + "args": { + "External id": 4052662,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10573 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822293.398, "dur": 0.211, + "args": { + "External id": 4052663,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10574 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822295.149, "dur": 0.222, + "args": { + "External id": 4052664,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10575 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822296.189, "dur": 0.211, + "args": { + "External id": 4052665,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10576 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822297.200, "dur": 0.218, + "args": { + "External id": 4052666,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10577 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822299.489, "dur": 0.213, + "args": { + "External id": 4052667,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10578 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822300.433, "dur": 0.219, + "args": { + "External id": 4052668,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10579 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822301.420, "dur": 0.211, + "args": { + "External id": 4052669,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10580 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822302.360, "dur": 0.216, + "args": { + "External id": 4052670,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10581 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822303.399, "dur": 0.212, + "args": { + "External id": 4052671,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10582 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822304.397, "dur": 0.596, + "args": { + "External id": 4052672,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10583 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822306.019, "dur": 0.213, + "args": { + "External id": 4052673,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10584 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822306.972, "dur": 0.222, + "args": { + "External id": 4052674,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10585 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822309.155, "dur": 0.212, + "args": { + "External id": 4052675,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10586 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822310.117, "dur": 0.427, + "args": { + "External id": 4052676,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10587 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822311.287, "dur": 0.405, + "args": { + "External id": 4052677,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10588 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822312.438, "dur": 0.421, + "args": { + "External id": 4052678,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10589 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822313.678, "dur": 0.218, + "args": { + "External id": 4052679,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10590 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822314.717, "dur": 0.228, + "args": { + "External id": 4052680,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10591 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822315.678, "dur": 0.213, + "args": { + "External id": 4052681,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10592 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822316.613, "dur": 0.217, + "args": { + "External id": 4052682,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10593 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822318.886, "dur": 0.291, + "args": { + "External id": 4052683,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10594 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822319.958, "dur": 0.230, + "args": { + "External id": 4052684,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10595 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822321.017, "dur": 0.219, + "args": { + "External id": 4052685,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10596 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822321.973, "dur": 0.392, + "args": { + "External id": 4052686,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10597 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822323.191, "dur": 0.219, + "args": { + "External id": 4052687,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10598 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822324.222, "dur": 0.484, + "args": { + "External id": 4052688,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10599 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822325.522, "dur": 0.238, + "args": { + "External id": 4052689,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10600 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822326.569, "dur": 0.225, + "args": { + "External id": 4052690,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10601 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822328.922, "dur": 0.229, + "args": { + "External id": 4052691,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10602 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822329.889, "dur": 0.214, + "args": { + "External id": 4052692,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10603 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822330.856, "dur": 0.213, + "args": { + "External id": 4052693,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10604 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822331.802, "dur": 0.215, + "args": { + "External id": 4052694,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10605 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822332.776, "dur": 0.214, + "args": { + "External id": 4052695,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10606 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822333.733, "dur": 0.217, + "args": { + "External id": 4052696,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10607 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822334.688, "dur": 0.212, + "args": { + "External id": 4052697,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10608 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822335.644, "dur": 0.218, + "args": { + "External id": 4052698,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10609 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822338.079, "dur": 0.215, + "args": { + "External id": 4052699,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10610 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822339.056, "dur": 0.219, + "args": { + "External id": 4052700,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10611 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822340.708, "dur": 0.214, + "args": { + "External id": 4052701,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10612 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822341.825, "dur": 0.437, + "args": { + "External id": 4052702,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10613 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822343.149, "dur": 0.220, + "args": { + "External id": 4052703,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10614 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822344.241, "dur": 0.430, + "args": { + "External id": 4052704,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10615 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822345.549, "dur": 0.430, + "args": { + "External id": 4052705,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10616 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822346.861, "dur": 0.427, + "args": { + "External id": 4052706,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10617 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822349.737, "dur": 0.274, + "args": { + "External id": 4052707,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10618 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822350.744, "dur": 0.423, + "args": { + "External id": 4052708,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10619 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822351.906, "dur": 0.216, + "args": { + "External id": 4052709,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10620 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822352.853, "dur": 0.390, + "args": { + "External id": 4052710,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10621 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822354.066, "dur": 0.219, + "args": { + "External id": 4052711,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10622 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822355.100, "dur": 0.227, + "args": { + "External id": 4052712,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10623 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822356.129, "dur": 0.213, + "args": { + "External id": 4052713,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10624 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822357.138, "dur": 0.228, + "args": { + "External id": 4052714,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10625 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822359.648, "dur": 0.218, + "args": { + "External id": 4052715,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10626 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822360.613, "dur": 0.220, + "args": { + "External id": 4052716,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10627 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822361.570, "dur": 0.217, + "args": { + "External id": 4052717,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10628 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822362.515, "dur": 0.217, + "args": { + "External id": 4052718,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10629 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822363.464, "dur": 0.216, + "args": { + "External id": 4052719,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10630 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822364.405, "dur": 0.233, + "args": { + "External id": 4052720,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10631 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822365.379, "dur": 0.212, + "args": { + "External id": 4052721,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10632 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822366.319, "dur": 0.220, + "args": { + "External id": 4052722,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10633 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822368.753, "dur": 0.215, + "args": { + "External id": 4052723,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10634 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822369.706, "dur": 0.218, + "args": { + "External id": 4052724,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10635 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822370.666, "dur": 0.215, + "args": { + "External id": 4052725,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10636 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822371.676, "dur": 0.218, + "args": { + "External id": 4052726,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10637 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822372.809, "dur": 0.214, + "args": { + "External id": 4052727,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10638 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822373.755, "dur": 0.219, + "args": { + "External id": 4052728,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10639 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822374.714, "dur": 0.212, + "args": { + "External id": 4052729,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10640 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822375.711, "dur": 0.217, + "args": { + "External id": 4052730,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10641 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822378.228, "dur": 0.216, + "args": { + "External id": 4052731,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10642 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822379.173, "dur": 0.218, + "args": { + "External id": 4052732,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10643 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822380.412, "dur": 0.211, + "args": { + "External id": 4052733,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10644 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822381.360, "dur": 0.216, + "args": { + "External id": 4052734,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10645 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822382.309, "dur": 0.218, + "args": { + "External id": 4052735,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10646 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822383.259, "dur": 0.215, + "args": { + "External id": 4052736,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10647 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822384.315, "dur": 0.211, + "args": { + "External id": 4052737,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10648 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822385.293, "dur": 0.216, + "args": { + "External id": 4052738,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10649 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822387.680, "dur": 0.213, + "args": { + "External id": 4052739,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10650 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822388.623, "dur": 0.217, + "args": { + "External id": 4052740,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10651 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822389.579, "dur": 0.215, + "args": { + "External id": 4052741,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10652 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822390.519, "dur": 0.220, + "args": { + "External id": 4052742,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10653 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822391.473, "dur": 0.213, + "args": { + "External id": 4052743,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10654 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822392.575, "dur": 0.217, + "args": { + "External id": 4052744,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10655 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822393.680, "dur": 0.424, + "args": { + "External id": 4052745,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10656 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822395.013, "dur": 0.218, + "args": { + "External id": 4052746,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10657 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822397.554, "dur": 0.212, + "args": { + "External id": 4052747,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10658 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822398.688, "dur": 0.213, + "args": { + "External id": 4052748,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10659 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822399.644, "dur": 0.211, + "args": { + "External id": 4052749,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10660 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822400.591, "dur": 0.218, + "args": { + "External id": 4052750,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10661 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822401.552, "dur": 0.216, + "args": { + "External id": 4052751,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10662 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822402.532, "dur": 0.217, + "args": { + "External id": 4052752,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10663 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822403.492, "dur": 0.212, + "args": { + "External id": 4052753,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10664 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822404.543, "dur": 0.247, + "args": { + "External id": 4052754,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10665 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822406.978, "dur": 0.214, + "args": { + "External id": 4052755,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10666 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822407.925, "dur": 0.431, + "args": { + "External id": 4052756,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10667 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822409.101, "dur": 0.210, + "args": { + "External id": 4052757,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10668 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822410.047, "dur": 0.408, + "args": { + "External id": 4052758,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10669 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822411.195, "dur": 0.213, + "args": { + "External id": 4052759,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10670 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822412.135, "dur": 0.239, + "args": { + "External id": 4052760,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10671 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822427.908, "dur": 0.872, + "args": { + "External id": 4052761,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10672 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822432.231, "dur": 0.209, + "args": { + "External id": 4052762,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10673 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822434.758, "dur": 0.384, + "args": { + "External id": 4052763,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10674 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822435.944, "dur": 0.240, + "args": { + "External id": 4052764,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10675 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822437.081, "dur": 0.220, + "args": { + "External id": 4052765,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10676 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822438.050, "dur": 0.405, + "args": { + "External id": 4052766,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10677 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822439.479, "dur": 0.185, + "args": { + "External id": 4052767,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10678 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822440.417, "dur": 0.448, + "args": { + "External id": 4052768,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10679 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822442.363, "dur": 0.434, + "args": { + "External id": 4052769,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10680 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822443.583, "dur": 0.239, + "args": { + "External id": 4052770,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10681 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822446.004, "dur": 0.222, + "args": { + "External id": 4052771,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10682 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822447.032, "dur": 0.430, + "args": { + "External id": 4052772,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10683 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822448.230, "dur": 0.473, + "args": { + "External id": 4052773,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10684 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822449.440, "dur": 0.450, + "args": { + "External id": 4052774,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10685 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822450.625, "dur": 0.466, + "args": { + "External id": 4052775,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10686 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822451.819, "dur": 0.404, + "args": { + "External id": 4052776,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10687 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822454.199, "dur": 0.266, + "args": { + "External id": 4052777,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10688 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822455.390, "dur": 0.225, + "args": { + "External id": 4052778,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10689 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822457.663, "dur": 0.432, + "args": { + "External id": 4052779,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10690 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822459.041, "dur": 0.414, + "args": { + "External id": 4052780,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10691 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822460.365, "dur": 0.223, + "args": { + "External id": 4052781,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10692 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822461.578, "dur": 0.216, + "args": { + "External id": 4052782,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10693 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822462.519, "dur": 0.385, + "args": { + "External id": 4052783,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10694 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822463.644, "dur": 0.391, + "args": { + "External id": 4052784,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10695 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822464.765, "dur": 0.237, + "args": { + "External id": 4052785,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10696 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822466.188, "dur": 0.220, + "args": { + "External id": 4052786,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10697 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822468.506, "dur": 0.226, + "args": { + "External id": 4052787,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10698 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822469.743, "dur": 0.220, + "args": { + "External id": 4052788,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10699 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822470.752, "dur": 0.220, + "args": { + "External id": 4052789,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10700 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275822471.954, "dur": 0.221, + "args": { + "External id": 4052790,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 10701 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::stack", "pid": 1336756, "tid": 1336756, + "ts": 1655275822526.527, "dur": 1441.712, + "args": { + "External id": 4052791,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["TensorList", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10702 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::stack", "pid": 1336756, "tid": 1336756, + "ts": 1655275822950.602, "dur": 946.962, + "args": { + "External id": 4052792,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["TensorList", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10703 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275822959.134, "dur": 7.467, + "args": { + "External id": 4052793,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10704 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275822963.217, "dur": 2.959, + "args": { + "External id": 4052794,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10705 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275822967.161, "dur": 3.363, + "args": { + "External id": 4052795,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10706 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275822968.009, "dur": 2.401, + "args": { + "External id": 4052796,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10707 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275822971.292, "dur": 2.527, + "args": { + "External id": 4052797,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10708 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275822973.333, "dur": 0.411, + "args": { + "External id": 4052798,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10709 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275822974.357, "dur": 1.085, + "args": { + "External id": 4052799,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10710 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275822974.807, "dur": 0.559, + "args": { + "External id": 4052800,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10711 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275822977.156, "dur": 4.065, + "args": { + "External id": 4052801,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10712 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275822980.600, "dur": 0.549, + "args": { + "External id": 4052802,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10713 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275822981.707, "dur": 30.353, + "args": { + "External id": 4052803,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10714 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823010.953, "dur": 0.707, + "args": { + "External id": 4052804,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10715 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823012.852, "dur": 1.943, + "args": { + "External id": 4052805,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10716 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823013.736, "dur": 0.992, + "args": { + "External id": 4052806,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10717 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823015.228, "dur": 3.600, + "args": { + "External id": 4052807,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10718 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823018.097, "dur": 0.663, + "args": { + "External id": 4052808,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10719 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823019.624, "dur": 1.888, + "args": { + "External id": 4052809,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10720 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823020.652, "dur": 0.790, + "args": { + "External id": 4052810,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10721 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823021.740, "dur": 2.705, + "args": { + "External id": 4052811,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10722 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823022.346, "dur": 2.027, + "args": { + "External id": 4052812,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10723 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823024.678, "dur": 1.924, + "args": { + "External id": 4052813,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10724 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823026.111, "dur": 0.421, + "args": { + "External id": 4052814,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10725 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823026.826, "dur": 1.154, + "args": { + "External id": 4052815,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10726 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823027.182, "dur": 0.733, + "args": { + "External id": 4052816,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10727 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823029.801, "dur": 3.706, + "args": { + "External id": 4052817,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10728 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823033.019, "dur": 0.418, + "args": { + "External id": 4052818,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10729 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823033.959, "dur": 1.549, + "args": { + "External id": 4052819,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10730 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823034.725, "dur": 0.714, + "args": { + "External id": 4052820,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10731 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823035.788, "dur": 1.580, + "args": { + "External id": 4052821,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10732 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823036.526, "dur": 0.775, + "args": { + "External id": 4052822,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10733 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823037.592, "dur": 2.825, + "args": { + "External id": 4052823,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10734 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823039.683, "dur": 0.662, + "args": { + "External id": 4052824,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10735 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823040.637, "dur": 1.477, + "args": { + "External id": 4052825,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10736 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823041.216, "dur": 0.832, + "args": { + "External id": 4052826,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10737 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823042.519, "dur": 2.853, + "args": { + "External id": 4052827,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10738 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823043.315, "dur": 1.903, + "args": { + "External id": 4052828,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10739 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823045.825, "dur": 2.436, + "args": { + "External id": 4052829,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10740 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823047.630, "dur": 0.560, + "args": { + "External id": 4052830,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10741 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823048.761, "dur": 1.284, + "args": { + "External id": 4052831,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10742 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823049.328, "dur": 0.650, + "args": { + "External id": 4052832,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10743 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823052.082, "dur": 3.595, + "args": { + "External id": 4052833,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10744 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823055.171, "dur": 0.434, + "args": { + "External id": 4052834,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10745 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823055.921, "dur": 1.313, + "args": { + "External id": 4052835,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10746 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823056.478, "dur": 0.690, + "args": { + "External id": 4052836,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10747 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823057.661, "dur": 1.603, + "args": { + "External id": 4052837,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10748 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823058.481, "dur": 0.717, + "args": { + "External id": 4052838,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10749 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823059.524, "dur": 2.972, + "args": { + "External id": 4052839,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10750 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823061.747, "dur": 0.677, + "args": { + "External id": 4052840,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10751 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823062.897, "dur": 1.508, + "args": { + "External id": 4052841,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10752 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823063.606, "dur": 0.729, + "args": { + "External id": 4052842,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10753 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823064.718, "dur": 2.387, + "args": { + "External id": 4052843,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10754 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823065.235, "dur": 1.805, + "args": { + "External id": 4052844,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10755 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823067.331, "dur": 2.403, + "args": { + "External id": 4052845,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10756 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823069.012, "dur": 0.651, + "args": { + "External id": 4052846,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10757 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823069.951, "dur": 1.224, + "args": { + "External id": 4052847,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10758 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823070.300, "dur": 0.814, + "args": { + "External id": 4052848,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10759 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823073.195, "dur": 4.042, + "args": { + "External id": 4052849,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10760 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823076.687, "dur": 0.479, + "args": { + "External id": 4052850,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10761 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823077.677, "dur": 1.543, + "args": { + "External id": 4052851,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10762 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823078.499, "dur": 0.654, + "args": { + "External id": 4052852,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10763 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823079.649, "dur": 1.350, + "args": { + "External id": 4052853,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10764 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823080.226, "dur": 0.707, + "args": { + "External id": 4052854,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10765 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823081.422, "dur": 2.251, + "args": { + "External id": 4052855,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10766 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823083.187, "dur": 0.421, + "args": { + "External id": 4052856,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10767 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823084.093, "dur": 1.459, + "args": { + "External id": 4052857,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10768 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823084.850, "dur": 0.635, + "args": { + "External id": 4052858,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10769 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823085.783, "dur": 2.653, + "args": { + "External id": 4052859,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10770 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823086.495, "dur": 1.870, + "args": { + "External id": 4052860,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10771 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823088.867, "dur": 2.641, + "args": { + "External id": 4052861,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10772 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823090.699, "dur": 0.736, + "args": { + "External id": 4052862,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10773 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823091.917, "dur": 1.194, + "args": { + "External id": 4052863,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10774 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823092.279, "dur": 0.764, + "args": { + "External id": 4052864,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10775 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823094.975, "dur": 3.764, + "args": { + "External id": 4052865,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10776 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823098.239, "dur": 0.436, + "args": { + "External id": 4052866,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10777 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823098.983, "dur": 1.184, + "args": { + "External id": 4052867,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10778 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823099.497, "dur": 0.599, + "args": { + "External id": 4052868,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10779 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823100.385, "dur": 1.110, + "args": { + "External id": 4052869,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10780 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823100.730, "dur": 0.700, + "args": { + "External id": 4052870,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10781 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823101.956, "dur": 3.990, + "args": { + "External id": 4052871,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10782 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823105.224, "dur": 0.652, + "args": { + "External id": 4052872,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10783 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823106.164, "dur": 1.304, + "args": { + "External id": 4052873,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10784 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823106.803, "dur": 0.596, + "args": { + "External id": 4052874,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10785 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823107.955, "dur": 2.435, + "args": { + "External id": 4052875,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10786 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823108.520, "dur": 1.800, + "args": { + "External id": 4052876,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10787 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823110.841, "dur": 2.334, + "args": { + "External id": 4052877,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10788 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823112.555, "dur": 0.547, + "args": { + "External id": 4052878,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10789 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823113.686, "dur": 1.246, + "args": { + "External id": 4052879,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10790 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823114.234, "dur": 0.632, + "args": { + "External id": 4052880,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10791 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823116.825, "dur": 3.660, + "args": { + "External id": 4052881,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10792 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823119.919, "dur": 0.501, + "args": { + "External id": 4052882,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10793 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823120.939, "dur": 1.211, + "args": { + "External id": 4052883,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10794 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823121.616, "dur": 0.465, + "args": { + "External id": 4052884,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10795 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823122.652, "dur": 1.174, + "args": { + "External id": 4052885,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10796 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823123.250, "dur": 0.511, + "args": { + "External id": 4052886,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10797 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823124.069, "dur": 2.741, + "args": { + "External id": 4052887,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10798 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823126.182, "dur": 0.559, + "args": { + "External id": 4052888,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10799 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823127.030, "dur": 1.214, + "args": { + "External id": 4052889,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10800 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823127.621, "dur": 0.552, + "args": { + "External id": 4052890,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10801 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823128.722, "dur": 2.752, + "args": { + "External id": 4052891,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10802 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823129.408, "dur": 1.996, + "args": { + "External id": 4052892,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10803 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823131.886, "dur": 2.217, + "args": { + "External id": 4052893,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10804 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823133.323, "dur": 0.711, + "args": { + "External id": 4052894,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10805 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823134.590, "dur": 1.360, + "args": { + "External id": 4052895,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10806 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823135.138, "dur": 0.747, + "args": { + "External id": 4052896,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10807 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823137.790, "dur": 3.297, + "args": { + "External id": 4052897,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10808 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823140.356, "dur": 0.663, + "args": { + "External id": 4052898,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10809 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823141.346, "dur": 1.374, + "args": { + "External id": 4052899,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10810 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823141.960, "dur": 0.692, + "args": { + "External id": 4052900,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10811 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823143.252, "dur": 2.044, + "args": { + "External id": 4052901,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10812 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823144.319, "dur": 0.912, + "args": { + "External id": 4052902,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10813 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823145.974, "dur": 3.219, + "args": { + "External id": 4052903,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10814 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823148.363, "dur": 0.763, + "args": { + "External id": 4052904,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10815 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823149.613, "dur": 1.937, + "args": { + "External id": 4052905,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10816 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823150.828, "dur": 0.651, + "args": { + "External id": 4052906,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10817 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823151.815, "dur": 2.315, + "args": { + "External id": 4052907,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10818 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823152.446, "dur": 1.613, + "args": { + "External id": 4052908,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10819 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823154.356, "dur": 1.703, + "args": { + "External id": 4052909,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10820 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823155.495, "dur": 0.497, + "args": { + "External id": 4052910,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10821 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823156.363, "dur": 1.174, + "args": { + "External id": 4052911,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10822 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823156.938, "dur": 0.534, + "args": { + "External id": 4052912,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10823 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823159.096, "dur": 3.288, + "args": { + "External id": 4052913,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10824 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823161.867, "dur": 0.447, + "args": { + "External id": 4052914,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10825 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823163.110, "dur": 1.809, + "args": { + "External id": 4052915,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10826 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823164.209, "dur": 0.643, + "args": { + "External id": 4052916,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10827 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823165.340, "dur": 1.979, + "args": { + "External id": 4052917,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10828 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823166.542, "dur": 0.711, + "args": { + "External id": 4052918,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10829 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823167.923, "dur": 2.975, + "args": { + "External id": 4052919,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10830 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823170.208, "dur": 0.620, + "args": { + "External id": 4052920,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10831 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823171.136, "dur": 2.129, + "args": { + "External id": 4052921,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10832 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823172.347, "dur": 0.851, + "args": { + "External id": 4052922,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10833 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823173.504, "dur": 3.027, + "args": { + "External id": 4052923,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10834 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823174.152, "dur": 2.306, + "args": { + "External id": 4052924,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10835 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823176.755, "dur": 1.564, + "args": { + "External id": 4052925,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10836 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823177.685, "dur": 0.568, + "args": { + "External id": 4052926,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10837 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823178.598, "dur": 1.252, + "args": { + "External id": 4052927,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10838 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823179.243, "dur": 0.542, + "args": { + "External id": 4052928,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10839 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823181.811, "dur": 3.135, + "args": { + "External id": 4052929,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10840 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823184.421, "dur": 0.453, + "args": { + "External id": 4052930,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10841 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823185.419, "dur": 1.671, + "args": { + "External id": 4052931,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10842 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823186.374, "dur": 0.648, + "args": { + "External id": 4052932,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10843 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823187.498, "dur": 1.658, + "args": { + "External id": 4052933,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10844 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823188.527, "dur": 0.564, + "args": { + "External id": 4052934,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10845 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823189.474, "dur": 2.791, + "args": { + "External id": 4052935,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10846 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823191.726, "dur": 0.470, + "args": { + "External id": 4052936,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10847 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823192.686, "dur": 1.804, + "args": { + "External id": 4052937,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10848 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823193.598, "dur": 0.820, + "args": { + "External id": 4052938,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10849 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823194.824, "dur": 2.971, + "args": { + "External id": 4052939,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10850 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823195.522, "dur": 2.005, + "args": { + "External id": 4052940,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10851 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823198.016, "dur": 1.621, + "args": { + "External id": 4052941,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10852 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823199.111, "dur": 0.460, + "args": { + "External id": 4052942,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10853 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823199.874, "dur": 1.438, + "args": { + "External id": 4052943,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10854 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823200.666, "dur": 0.572, + "args": { + "External id": 4052944,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10855 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823202.876, "dur": 3.047, + "args": { + "External id": 4052945,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10856 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823205.369, "dur": 0.485, + "args": { + "External id": 4052946,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10857 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823206.183, "dur": 1.201, + "args": { + "External id": 4052947,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10858 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823206.885, "dur": 0.433, + "args": { + "External id": 4052948,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10859 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823207.603, "dur": 1.427, + "args": { + "External id": 4052949,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10860 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823208.385, "dur": 0.581, + "args": { + "External id": 4052950,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10861 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823209.267, "dur": 2.824, + "args": { + "External id": 4052951,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10862 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823211.474, "dur": 0.551, + "args": { + "External id": 4052952,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10863 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823212.353, "dur": 1.728, + "args": { + "External id": 4052953,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10864 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823213.385, "dur": 0.624, + "args": { + "External id": 4052954,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10865 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823214.555, "dur": 2.913, + "args": { + "External id": 4052955,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10866 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823215.746, "dur": 1.652, + "args": { + "External id": 4052956,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10867 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823217.878, "dur": 1.779, + "args": { + "External id": 4052957,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10868 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823218.984, "dur": 0.605, + "args": { + "External id": 4052958,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10869 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823220.147, "dur": 1.496, + "args": { + "External id": 4052959,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10870 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823220.907, "dur": 0.673, + "args": { + "External id": 4052960,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10871 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823223.613, "dur": 3.274, + "args": { + "External id": 4052961,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10872 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823226.309, "dur": 0.509, + "args": { + "External id": 4052962,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10873 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823227.164, "dur": 1.533, + "args": { + "External id": 4052963,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10874 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823227.980, "dur": 0.648, + "args": { + "External id": 4052964,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10875 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823228.960, "dur": 2.012, + "args": { + "External id": 4052965,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10876 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823230.144, "dur": 0.765, + "args": { + "External id": 4052966,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10877 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823231.209, "dur": 2.971, + "args": { + "External id": 4052967,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10878 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823233.572, "dur": 0.543, + "args": { + "External id": 4052968,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10879 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823234.608, "dur": 1.228, + "args": { + "External id": 4052969,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10880 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823235.344, "dur": 0.425, + "args": { + "External id": 4052970,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10881 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823236.122, "dur": 2.324, + "args": { + "External id": 4052971,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10882 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823236.692, "dur": 1.685, + "args": { + "External id": 4052972,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10883 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823238.708, "dur": 1.533, + "args": { + "External id": 4052973,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10884 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823239.725, "dur": 0.443, + "args": { + "External id": 4052974,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10885 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823240.604, "dur": 1.163, + "args": { + "External id": 4052975,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10886 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823241.174, "dur": 0.525, + "args": { + "External id": 4052976,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10887 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823243.460, "dur": 2.781, + "args": { + "External id": 4052977,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10888 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823245.647, "dur": 0.527, + "args": { + "External id": 4052978,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10889 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823246.503, "dur": 1.382, + "args": { + "External id": 4052979,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10890 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823247.154, "dur": 0.662, + "args": { + "External id": 4052980,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10891 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823248.105, "dur": 1.576, + "args": { + "External id": 4052981,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10892 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823249.116, "dur": 0.502, + "args": { + "External id": 4052982,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10893 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823250.041, "dur": 2.713, + "args": { + "External id": 4052983,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10894 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823252.158, "dur": 0.530, + "args": { + "External id": 4052984,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10895 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823253.040, "dur": 1.639, + "args": { + "External id": 4052985,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10896 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823254.087, "dur": 0.524, + "args": { + "External id": 4052986,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10897 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823254.918, "dur": 2.397, + "args": { + "External id": 4052987,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10898 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823255.487, "dur": 1.660, + "args": { + "External id": 4052988,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10899 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823257.787, "dur": 1.487, + "args": { + "External id": 4052989,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10900 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823258.635, "dur": 0.576, + "args": { + "External id": 4052990,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10901 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823259.531, "dur": 1.349, + "args": { + "External id": 4052991,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10902 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823260.263, "dur": 0.555, + "args": { + "External id": 4052992,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10903 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823281.595, "dur": 2.965, + "args": { + "External id": 4059137,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10904 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823284.026, "dur": 0.423, + "args": { + "External id": 4059138,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10905 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823284.881, "dur": 1.107, + "args": { + "External id": 4059139,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10906 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823285.532, "dur": 0.389, + "args": { + "External id": 4059140,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10907 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823286.255, "dur": 1.551, + "args": { + "External id": 4059141,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10908 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823287.220, "dur": 0.517, + "args": { + "External id": 4059142,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10909 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823288.049, "dur": 2.366, + "args": { + "External id": 4059143,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10910 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823289.926, "dur": 0.420, + "args": { + "External id": 4059144,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10911 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823290.638, "dur": 1.147, + "args": { + "External id": 4059145,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10912 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823291.316, "dur": 0.400, + "args": { + "External id": 4059146,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10913 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823292.032, "dur": 2.426, + "args": { + "External id": 4059147,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10914 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823292.599, "dur": 1.787, + "args": { + "External id": 4059148,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10915 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823294.707, "dur": 1.657, + "args": { + "External id": 4059149,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10916 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823295.667, "dur": 0.628, + "args": { + "External id": 4059150,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10917 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823296.638, "dur": 1.557, + "args": { + "External id": 4059151,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10918 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823297.325, "dur": 0.804, + "args": { + "External id": 4059152,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10919 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823299.839, "dur": 2.871, + "args": { + "External id": 4059153,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10920 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823302.116, "dur": 0.526, + "args": { + "External id": 4059154,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10921 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823303.004, "dur": 1.204, + "args": { + "External id": 4059155,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10922 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823303.647, "dur": 0.492, + "args": { + "External id": 4059156,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10923 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823304.519, "dur": 1.457, + "args": { + "External id": 4059157,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10924 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823305.353, "dur": 0.557, + "args": { + "External id": 4059158,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10925 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823306.265, "dur": 2.450, + "args": { + "External id": 4059159,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10926 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823308.091, "dur": 0.556, + "args": { + "External id": 4059160,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10927 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823308.934, "dur": 1.545, + "args": { + "External id": 4059161,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10928 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823309.804, "dur": 0.607, + "args": { + "External id": 4059162,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10929 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823310.715, "dur": 2.729, + "args": { + "External id": 4059163,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10930 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823311.521, "dur": 1.851, + "args": { + "External id": 4059164,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10931 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823313.676, "dur": 1.568, + "args": { + "External id": 4059165,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10932 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823314.655, "dur": 0.523, + "args": { + "External id": 4059166,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10933 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823315.604, "dur": 1.357, + "args": { + "External id": 4059167,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10934 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823316.339, "dur": 0.554, + "args": { + "External id": 4059168,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10935 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823318.879, "dur": 2.835, + "args": { + "External id": 4059169,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10936 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823321.087, "dur": 0.560, + "args": { + "External id": 4059170,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10937 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823322.003, "dur": 1.160, + "args": { + "External id": 4059171,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10938 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823322.655, "dur": 0.440, + "args": { + "External id": 4059172,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10939 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823323.409, "dur": 1.455, + "args": { + "External id": 4059173,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10940 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823324.294, "dur": 0.503, + "args": { + "External id": 4059174,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10941 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823325.117, "dur": 2.579, + "args": { + "External id": 4059175,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10942 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823327.074, "dur": 0.553, + "args": { + "External id": 4059176,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10943 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823328.007, "dur": 1.413, + "args": { + "External id": 4059177,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10944 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823328.837, "dur": 0.516, + "args": { + "External id": 4059178,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10945 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823329.694, "dur": 2.471, + "args": { + "External id": 4059179,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10946 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823330.468, "dur": 1.535, + "args": { + "External id": 4059180,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10947 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823332.385, "dur": 1.559, + "args": { + "External id": 4059181,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10948 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823333.359, "dur": 0.518, + "args": { + "External id": 4059182,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10949 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823334.184, "dur": 1.221, + "args": { + "External id": 4059183,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10950 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823334.750, "dur": 0.588, + "args": { + "External id": 4059184,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10951 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823337.130, "dur": 2.591, + "args": { + "External id": 4059185,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10952 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823339.173, "dur": 0.482, + "args": { + "External id": 4059186,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10953 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823339.982, "dur": 1.072, + "args": { + "External id": 4059187,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10954 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823340.562, "dur": 0.425, + "args": { + "External id": 4059188,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10955 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823341.310, "dur": 1.562, + "args": { + "External id": 4059189,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10956 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823342.258, "dur": 0.550, + "args": { + "External id": 4059190,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10957 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823343.114, "dur": 2.595, + "args": { + "External id": 4059191,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10958 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823345.077, "dur": 0.566, + "args": { + "External id": 4059192,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10959 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823346.133, "dur": 1.396, + "args": { + "External id": 4059193,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10960 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823346.982, "dur": 0.478, + "args": { + "External id": 4059194,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10961 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823347.767, "dur": 2.855, + "args": { + "External id": 4059195,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10962 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823348.532, "dur": 1.931, + "args": { + "External id": 4059196,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10963 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823350.844, "dur": 1.529, + "args": { + "External id": 4059197,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10964 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823351.656, "dur": 0.648, + "args": { + "External id": 4059198,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10965 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823352.691, "dur": 1.328, + "args": { + "External id": 4059199,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10966 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823353.435, "dur": 0.520, + "args": { + "External id": 4059200,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10967 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823355.953, "dur": 2.956, + "args": { + "External id": 4059201,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10968 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823358.322, "dur": 0.520, + "args": { + "External id": 4059202,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10969 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823359.179, "dur": 1.274, + "args": { + "External id": 4059203,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10970 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823359.965, "dur": 0.419, + "args": { + "External id": 4059204,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10971 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823360.669, "dur": 1.696, + "args": { + "External id": 4059205,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10972 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823361.762, "dur": 0.535, + "args": { + "External id": 4059206,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10973 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823362.626, "dur": 2.318, + "args": { + "External id": 4059207,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10974 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823364.436, "dur": 0.440, + "args": { + "External id": 4059208,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10975 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823365.162, "dur": 1.642, + "args": { + "External id": 4059209,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10976 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823366.052, "dur": 0.681, + "args": { + "External id": 4059210,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10977 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823367.039, "dur": 2.373, + "args": { + "External id": 4059211,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10978 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823367.601, "dur": 1.737, + "args": { + "External id": 4059212,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10979 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823369.633, "dur": 1.325, + "args": { + "External id": 4059213,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10980 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823370.401, "dur": 0.487, + "args": { + "External id": 4059214,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10981 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823371.199, "dur": 1.214, + "args": { + "External id": 4059215,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10982 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823371.784, "dur": 0.564, + "args": { + "External id": 4059216,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10983 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823374.086, "dur": 3.142, + "args": { + "External id": 4059217,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10984 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823376.474, "dur": 0.682, + "args": { + "External id": 4059218,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10985 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823377.488, "dur": 1.128, + "args": { + "External id": 4059219,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10986 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823378.042, "dur": 0.503, + "args": { + "External id": 4059220,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10987 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823378.918, "dur": 1.444, + "args": { + "External id": 4059221,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10988 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823379.782, "dur": 0.517, + "args": { + "External id": 4059222,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10989 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823380.609, "dur": 2.582, + "args": { + "External id": 4059223,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10990 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823382.616, "dur": 0.507, + "args": { + "External id": 4059224,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10991 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823383.412, "dur": 1.294, + "args": { + "External id": 4059225,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10992 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823384.154, "dur": 0.484, + "args": { + "External id": 4059226,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10993 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823384.944, "dur": 2.566, + "args": { + "External id": 4059227,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10994 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823385.802, "dur": 1.637, + "args": { + "External id": 4059228,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10995 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823387.733, "dur": 1.488, + "args": { + "External id": 4059229,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10996 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823388.751, "dur": 0.403, + "args": { + "External id": 4059230,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10997 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823389.560, "dur": 1.430, + "args": { + "External id": 4059231,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 10998 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823390.304, "dur": 0.622, + "args": { + "External id": 4059232,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 10999 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823392.736, "dur": 2.610, + "args": { + "External id": 4059233,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11000 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823394.888, "dur": 0.392, + "args": { + "External id": 4059234,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11001 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823395.718, "dur": 1.091, + "args": { + "External id": 4059235,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11002 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823396.359, "dur": 0.382, + "args": { + "External id": 4059236,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11003 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823397.031, "dur": 1.536, + "args": { + "External id": 4059237,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11004 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823397.994, "dur": 0.510, + "args": { + "External id": 4059238,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11005 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823398.805, "dur": 2.266, + "args": { + "External id": 4059239,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11006 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823400.576, "dur": 0.430, + "args": { + "External id": 4059240,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11007 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823401.325, "dur": 1.529, + "args": { + "External id": 4059241,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11008 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823402.259, "dur": 0.530, + "args": { + "External id": 4059242,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11009 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823403.090, "dur": 2.396, + "args": { + "External id": 4059243,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11010 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823403.746, "dur": 1.666, + "args": { + "External id": 4059244,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11011 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823405.710, "dur": 1.494, + "args": { + "External id": 4059245,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11012 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823406.704, "dur": 0.436, + "args": { + "External id": 4059246,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11013 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823407.545, "dur": 1.401, + "args": { + "External id": 4059247,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11014 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823408.151, "dur": 0.729, + "args": { + "External id": 4059248,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11015 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823410.560, "dur": 3.050, + "args": { + "External id": 4059249,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11016 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823413.121, "dur": 0.420, + "args": { + "External id": 4059250,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11017 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823413.869, "dur": 13.869, + "args": { + "External id": 4059251,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11018 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823426.294, "dur": 0.930, + "args": { + "External id": 4059252,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11019 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823428.550, "dur": 1.662, + "args": { + "External id": 4059253,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11020 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823429.430, "dur": 0.717, + "args": { + "External id": 4059254,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11021 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823430.493, "dur": 2.779, + "args": { + "External id": 4059255,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11022 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823432.637, "dur": 0.571, + "args": { + "External id": 4059256,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11023 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823433.500, "dur": 1.564, + "args": { + "External id": 4059257,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11024 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823434.477, "dur": 0.520, + "args": { + "External id": 4059258,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11025 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823435.316, "dur": 2.756, + "args": { + "External id": 4059259,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11026 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823436.002, "dur": 1.812, + "args": { + "External id": 4059260,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11027 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823438.304, "dur": 1.339, + "args": { + "External id": 4059261,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11028 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823439.140, "dur": 0.435, + "args": { + "External id": 4059262,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11029 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823439.890, "dur": 1.461, + "args": { + "External id": 4059263,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11030 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823440.743, "dur": 0.524, + "args": { + "External id": 4059264,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11031 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823443.532, "dur": 2.830, + "args": { + "External id": 4059265,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11032 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823445.840, "dur": 0.453, + "args": { + "External id": 4059266,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11033 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823446.630, "dur": 1.199, + "args": { + "External id": 4059267,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11034 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823447.252, "dur": 0.509, + "args": { + "External id": 4059268,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11035 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823448.118, "dur": 1.531, + "args": { + "External id": 4059269,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11036 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823449.109, "dur": 0.473, + "args": { + "External id": 4059270,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11037 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823449.981, "dur": 3.666, + "args": { + "External id": 4059271,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11038 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823453.110, "dur": 0.467, + "args": { + "External id": 4059272,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11039 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823453.941, "dur": 1.596, + "args": { + "External id": 4059273,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11040 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823454.980, "dur": 0.490, + "args": { + "External id": 4059274,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11041 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823455.781, "dur": 2.650, + "args": { + "External id": 4059275,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11042 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823456.537, "dur": 1.823, + "args": { + "External id": 4059276,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11043 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823458.658, "dur": 1.685, + "args": { + "External id": 4059277,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11044 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823459.678, "dur": 0.594, + "args": { + "External id": 4059278,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11045 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823460.695, "dur": 1.417, + "args": { + "External id": 4059279,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11046 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823461.468, "dur": 0.577, + "args": { + "External id": 4059280,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11047 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823463.843, "dur": 3.060, + "args": { + "External id": 4059281,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11048 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823466.415, "dur": 0.423, + "args": { + "External id": 4059282,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11049 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823467.170, "dur": 1.193, + "args": { + "External id": 4059283,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11050 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823467.863, "dur": 0.433, + "args": { + "External id": 4059284,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11051 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823468.687, "dur": 1.711, + "args": { + "External id": 4059285,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11052 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823469.834, "dur": 0.497, + "args": { + "External id": 4059286,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11053 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823470.649, "dur": 2.656, + "args": { + "External id": 4059287,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11054 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823472.823, "dur": 0.417, + "args": { + "External id": 4059288,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11055 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823473.563, "dur": 1.462, + "args": { + "External id": 4059289,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11056 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823474.415, "dur": 0.546, + "args": { + "External id": 4059290,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11057 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823475.269, "dur": 2.588, + "args": { + "External id": 4059291,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11058 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823476.024, "dur": 1.707, + "args": { + "External id": 4059292,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11059 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823478.189, "dur": 1.574, + "args": { + "External id": 4059293,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11060 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823479.089, "dur": 0.605, + "args": { + "External id": 4059294,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11061 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823480.110, "dur": 1.198, + "args": { + "External id": 4059295,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11062 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823480.728, "dur": 0.514, + "args": { + "External id": 4059296,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11063 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823483.038, "dur": 2.929, + "args": { + "External id": 4059297,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11064 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823485.455, "dur": 0.444, + "args": { + "External id": 4059298,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11065 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823486.230, "dur": 1.196, + "args": { + "External id": 4059299,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11066 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823486.865, "dur": 0.495, + "args": { + "External id": 4059300,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11067 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823487.854, "dur": 1.255, + "args": { + "External id": 4059301,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11068 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823488.516, "dur": 0.526, + "args": { + "External id": 4059302,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11069 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823489.351, "dur": 2.568, + "args": { + "External id": 4059303,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11070 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823491.438, "dur": 0.417, + "args": { + "External id": 4059304,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11071 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823492.151, "dur": 1.713, + "args": { + "External id": 4059305,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11072 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823493.270, "dur": 0.527, + "args": { + "External id": 4059306,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11073 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823494.285, "dur": 2.578, + "args": { + "External id": 4059307,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11074 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823495.082, "dur": 1.707, + "args": { + "External id": 4059308,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11075 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823497.098, "dur": 1.414, + "args": { + "External id": 4059309,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11076 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823498.045, "dur": 0.400, + "args": { + "External id": 4059310,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11077 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823498.808, "dur": 1.285, + "args": { + "External id": 4059311,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11078 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823499.412, "dur": 0.616, + "args": { + "External id": 4059312,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11079 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823501.564, "dur": 3.121, + "args": { + "External id": 4059313,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11080 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823503.937, "dur": 0.683, + "args": { + "External id": 4059314,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11081 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823504.953, "dur": 1.338, + "args": { + "External id": 4059315,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11082 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823505.724, "dur": 0.499, + "args": { + "External id": 4059316,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11083 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823506.612, "dur": 1.641, + "args": { + "External id": 4059317,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11084 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823507.787, "dur": 0.400, + "args": { + "External id": 4059318,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11085 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823508.501, "dur": 2.396, + "args": { + "External id": 4059319,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11086 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823510.427, "dur": 0.402, + "args": { + "External id": 4059320,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11087 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823511.125, "dur": 1.587, + "args": { + "External id": 4059321,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11088 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823512.067, "dur": 0.580, + "args": { + "External id": 4059322,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11089 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823512.954, "dur": 2.191, + "args": { + "External id": 4059323,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11090 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823513.585, "dur": 1.489, + "args": { + "External id": 4059324,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11091 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823515.375, "dur": 1.654, + "args": { + "External id": 4059325,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11092 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823516.380, "dur": 0.581, + "args": { + "External id": 4059326,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11093 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823517.445, "dur": 1.158, + "args": { + "External id": 4059327,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11094 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823518.001, "dur": 0.536, + "args": { + "External id": 4059328,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11095 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823520.373, "dur": 3.377, + "args": { + "External id": 4059329,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11096 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823523.119, "dur": 0.561, + "args": { + "External id": 4059330,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11097 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823524.013, "dur": 1.132, + "args": { + "External id": 4059331,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11098 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823524.622, "dur": 0.453, + "args": { + "External id": 4059332,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11099 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823525.477, "dur": 1.505, + "args": { + "External id": 4059333,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11100 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823526.287, "dur": 0.630, + "args": { + "External id": 4059334,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11101 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823527.223, "dur": 2.029, + "args": { + "External id": 4059335,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11102 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823528.749, "dur": 0.437, + "args": { + "External id": 4059336,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11103 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823529.473, "dur": 1.547, + "args": { + "External id": 4059337,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11104 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823530.456, "dur": 0.495, + "args": { + "External id": 4059338,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11105 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823531.349, "dur": 2.428, + "args": { + "External id": 4059339,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11106 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823531.946, "dur": 1.757, + "args": { + "External id": 4059340,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11107 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823534.027, "dur": 1.541, + "args": { + "External id": 4059341,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11108 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823535.046, "dur": 0.453, + "args": { + "External id": 4059342,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11109 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823535.809, "dur": 1.190, + "args": { + "External id": 4059343,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11110 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823536.401, "dur": 0.531, + "args": { + "External id": 4059344,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11111 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823538.566, "dur": 2.892, + "args": { + "External id": 4059345,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11112 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823540.921, "dur": 0.471, + "args": { + "External id": 4059346,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11113 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823541.726, "dur": 1.163, + "args": { + "External id": 4059347,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11114 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823542.392, "dur": 0.431, + "args": { + "External id": 4059348,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11115 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823543.212, "dur": 1.288, + "args": { + "External id": 4059349,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11116 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823544.023, "dur": 0.411, + "args": { + "External id": 4059350,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11117 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823544.829, "dur": 2.351, + "args": { + "External id": 4059351,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11118 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823546.681, "dur": 0.431, + "args": { + "External id": 4059352,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11119 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823547.406, "dur": 1.475, + "args": { + "External id": 4059353,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11120 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823548.334, "dur": 0.478, + "args": { + "External id": 4059354,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11121 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823549.124, "dur": 2.108, + "args": { + "External id": 4059355,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11122 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823549.736, "dur": 1.422, + "args": { + "External id": 4059356,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11123 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823551.462, "dur": 1.357, + "args": { + "External id": 4059357,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11124 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823552.325, "dur": 0.427, + "args": { + "External id": 4059358,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11125 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823553.072, "dur": 1.150, + "args": { + "External id": 4059359,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11126 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823553.613, "dur": 0.546, + "args": { + "External id": 4059360,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11127 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823555.807, "dur": 3.086, + "args": { + "External id": 4059361,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11128 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823558.260, "dur": 0.565, + "args": { + "External id": 4059362,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11129 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823559.174, "dur": 1.362, + "args": { + "External id": 4059363,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11130 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823559.805, "dur": 0.667, + "args": { + "External id": 4059364,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11131 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823560.763, "dur": 1.464, + "args": { + "External id": 4059365,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11132 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823561.540, "dur": 0.625, + "args": { + "External id": 4059366,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11133 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823562.495, "dur": 2.622, + "args": { + "External id": 4059367,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11134 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823564.537, "dur": 0.513, + "args": { + "External id": 4059368,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11135 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823565.338, "dur": 1.495, + "args": { + "External id": 4059369,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11136 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823566.091, "dur": 0.675, + "args": { + "External id": 4059370,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11137 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823567.082, "dur": 2.247, + "args": { + "External id": 4059371,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11138 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823567.799, "dur": 1.454, + "args": { + "External id": 4059372,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11139 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823569.557, "dur": 1.774, + "args": { + "External id": 4059373,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11140 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823570.446, "dur": 0.819, + "args": { + "External id": 4059374,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11141 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823571.661, "dur": 1.352, + "args": { + "External id": 4059375,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11142 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823572.248, "dur": 0.699, + "args": { + "External id": 4059376,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11143 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823575.080, "dur": 3.076, + "args": { + "External id": 4059377,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11144 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823577.634, "dur": 0.457, + "args": { + "External id": 4059378,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11145 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823578.421, "dur": 1.119, + "args": { + "External id": 4059379,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11146 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823579.056, "dur": 0.415, + "args": { + "External id": 4059380,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11147 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823579.766, "dur": 1.577, + "args": { + "External id": 4059381,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11148 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823580.619, "dur": 0.659, + "args": { + "External id": 4059382,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11149 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823581.713, "dur": 2.350, + "args": { + "External id": 4059383,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11150 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823583.589, "dur": 0.408, + "args": { + "External id": 4059384,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11151 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823584.377, "dur": 1.406, + "args": { + "External id": 4059385,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11152 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823585.265, "dur": 0.448, + "args": { + "External id": 4059386,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11153 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823586.023, "dur": 3.233, + "args": { + "External id": 4059387,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11154 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823586.689, "dur": 2.404, + "args": { + "External id": 4059388,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11155 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823589.523, "dur": 1.547, + "args": { + "External id": 4059389,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11156 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823590.483, "dur": 0.516, + "args": { + "External id": 4059390,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11157 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823591.800, "dur": 1.302, + "args": { + "External id": 4059391,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11158 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823592.449, "dur": 0.588, + "args": { + "External id": 4059392,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11159 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823594.869, "dur": 3.040, + "args": { + "External id": 4059393,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11160 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823597.362, "dur": 0.480, + "args": { + "External id": 4059394,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11161 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823598.189, "dur": 1.417, + "args": { + "External id": 4059395,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11162 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823598.980, "dur": 0.560, + "args": { + "External id": 4059396,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11163 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823599.828, "dur": 2.026, + "args": { + "External id": 4059397,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11164 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823600.989, "dur": 0.797, + "args": { + "External id": 4059398,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11165 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823602.182, "dur": 2.414, + "args": { + "External id": 4059399,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11166 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823604.067, "dur": 0.459, + "args": { + "External id": 4059400,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11167 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823604.916, "dur": 1.475, + "args": { + "External id": 4059401,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11168 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823605.870, "dur": 0.451, + "args": { + "External id": 4059402,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11169 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823606.633, "dur": 2.335, + "args": { + "External id": 4059403,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11170 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823607.249, "dur": 1.649, + "args": { + "External id": 4059404,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11171 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823609.211, "dur": 1.558, + "args": { + "External id": 4059405,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11172 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823610.267, "dur": 0.431, + "args": { + "External id": 4059406,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11173 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823611.014, "dur": 1.128, + "args": { + "External id": 4059407,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11174 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823611.569, "dur": 0.508, + "args": { + "External id": 4059408,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11175 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823613.670, "dur": 2.627, + "args": { + "External id": 4059409,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11176 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823615.851, "dur": 0.380, + "args": { + "External id": 4059410,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11177 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823616.568, "dur": 1.194, + "args": { + "External id": 4059411,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11178 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823617.275, "dur": 0.420, + "args": { + "External id": 4059412,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11179 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823618.071, "dur": 1.484, + "args": { + "External id": 4059413,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11180 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823618.995, "dur": 0.488, + "args": { + "External id": 4059414,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11181 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823619.799, "dur": 2.996, + "args": { + "External id": 4059415,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11182 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823621.911, "dur": 0.815, + "args": { + "External id": 4059416,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11183 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823623.048, "dur": 1.816, + "args": { + "External id": 4059417,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11184 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823624.103, "dur": 0.574, + "args": { + "External id": 4059418,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11185 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823625.103, "dur": 2.385, + "args": { + "External id": 4059419,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11186 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823625.789, "dur": 1.629, + "args": { + "External id": 4059420,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11187 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823627.757, "dur": 1.625, + "args": { + "External id": 4059421,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11188 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823628.568, "dur": 0.747, + "args": { + "External id": 4059422,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11189 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823629.624, "dur": 1.554, + "args": { + "External id": 4059423,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11190 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823630.221, "dur": 0.885, + "args": { + "External id": 4059424,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11191 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823633.008, "dur": 2.953, + "args": { + "External id": 4059425,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11192 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823635.306, "dur": 0.586, + "args": { + "External id": 4059426,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11193 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823636.230, "dur": 1.074, + "args": { + "External id": 4059427,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11194 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823636.788, "dur": 0.449, + "args": { + "External id": 4059428,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11195 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823637.531, "dur": 1.536, + "args": { + "External id": 4059429,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11196 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823638.482, "dur": 0.518, + "args": { + "External id": 4059430,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11197 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823639.430, "dur": 2.362, + "args": { + "External id": 4059431,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11198 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823641.295, "dur": 0.429, + "args": { + "External id": 4059432,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11199 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823642.014, "dur": 1.727, + "args": { + "External id": 4059433,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11200 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823643.214, "dur": 0.455, + "args": { + "External id": 4059434,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11201 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823643.986, "dur": 2.701, + "args": { + "External id": 4059435,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11202 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823644.827, "dur": 1.706, + "args": { + "External id": 4059436,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11203 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823646.913, "dur": 1.600, + "args": { + "External id": 4059437,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11204 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823647.847, "dur": 0.594, + "args": { + "External id": 4059438,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11205 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823648.794, "dur": 1.142, + "args": { + "External id": 4059439,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11206 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823649.353, "dur": 0.520, + "args": { + "External id": 4059440,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11207 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823651.899, "dur": 3.271, + "args": { + "External id": 4059441,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11208 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823654.590, "dur": 0.510, + "args": { + "External id": 4059442,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11209 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823655.493, "dur": 1.168, + "args": { + "External id": 4059443,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11210 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823656.141, "dur": 0.447, + "args": { + "External id": 4059444,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11211 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823656.883, "dur": 1.516, + "args": { + "External id": 4059445,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11212 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823657.742, "dur": 0.591, + "args": { + "External id": 4059446,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11213 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823658.641, "dur": 2.373, + "args": { + "External id": 4059447,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11214 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823660.500, "dur": 0.443, + "args": { + "External id": 4059448,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11215 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823661.259, "dur": 1.678, + "args": { + "External id": 4059449,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11216 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823662.269, "dur": 0.417, + "args": { + "External id": 4059450,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11217 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823663.182, "dur": 2.499, + "args": { + "External id": 4059451,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11218 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823663.930, "dur": 1.534, + "args": { + "External id": 4059452,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11219 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823665.928, "dur": 1.719, + "args": { + "External id": 4059453,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11220 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823666.831, "dur": 0.620, + "args": { + "External id": 4059454,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11221 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823667.972, "dur": 1.594, + "args": { + "External id": 4059455,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11222 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823668.853, "dur": 0.555, + "args": { + "External id": 4059456,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11223 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823671.010, "dur": 3.112, + "args": { + "External id": 4059457,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11224 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823673.521, "dur": 0.538, + "args": { + "External id": 4059458,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11225 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823674.388, "dur": 1.223, + "args": { + "External id": 4059459,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11226 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823674.948, "dur": 0.598, + "args": { + "External id": 4059460,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11227 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823675.832, "dur": 1.672, + "args": { + "External id": 4059461,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11228 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823676.803, "dur": 0.636, + "args": { + "External id": 4059462,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11229 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823677.845, "dur": 2.672, + "args": { + "External id": 4059463,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11230 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823679.995, "dur": 0.456, + "args": { + "External id": 4059464,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11231 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823680.736, "dur": 1.447, + "args": { + "External id": 4059465,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11232 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823681.630, "dur": 0.487, + "args": { + "External id": 4059466,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11233 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823682.425, "dur": 2.379, + "args": { + "External id": 4059467,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11234 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823683.207, "dur": 1.528, + "args": { + "External id": 4059468,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11235 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823685.029, "dur": 1.255, + "args": { + "External id": 4059469,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11236 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823685.777, "dur": 0.439, + "args": { + "External id": 4059470,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11237 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823686.636, "dur": 1.329, + "args": { + "External id": 4059471,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11238 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823687.334, "dur": 0.566, + "args": { + "External id": 4059472,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11239 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823689.504, "dur": 2.758, + "args": { + "External id": 4059473,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11240 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823691.718, "dur": 0.480, + "args": { + "External id": 4059474,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11241 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823692.533, "dur": 1.190, + "args": { + "External id": 4059475,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11242 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823693.218, "dur": 0.439, + "args": { + "External id": 4059476,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11243 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823693.944, "dur": 1.369, + "args": { + "External id": 4059477,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11244 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823694.719, "dur": 0.529, + "args": { + "External id": 4059478,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11245 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823695.582, "dur": 2.222, + "args": { + "External id": 4059479,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11246 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823697.251, "dur": 0.488, + "args": { + "External id": 4059480,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11247 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823698.025, "dur": 1.461, + "args": { + "External id": 4059481,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11248 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823698.974, "dur": 0.444, + "args": { + "External id": 4059482,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11249 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823699.729, "dur": 2.553, + "args": { + "External id": 4059483,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11250 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823700.471, "dur": 1.651, + "args": { + "External id": 4059484,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11251 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823702.510, "dur": 1.565, + "args": { + "External id": 4059485,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11252 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823703.393, "dur": 0.613, + "args": { + "External id": 4059486,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11253 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823704.409, "dur": 1.283, + "args": { + "External id": 4059487,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11254 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823705.104, "dur": 0.520, + "args": { + "External id": 4059488,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11255 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823707.496, "dur": 2.953, + "args": { + "External id": 4059489,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11256 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823709.977, "dur": 0.405, + "args": { + "External id": 4059490,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11257 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823710.726, "dur": 1.326, + "args": { + "External id": 4059491,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11258 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823711.488, "dur": 0.498, + "args": { + "External id": 4059492,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11259 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823712.271, "dur": 1.469, + "args": { + "External id": 4059493,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11260 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823712.969, "dur": 0.617, + "args": { + "External id": 4059494,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11261 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823713.976, "dur": 2.370, + "args": { + "External id": 4059495,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11262 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823715.875, "dur": 0.402, + "args": { + "External id": 4059496,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11263 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823716.566, "dur": 1.553, + "args": { + "External id": 4059497,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11264 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823717.492, "dur": 0.560, + "args": { + "External id": 4059498,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11265 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823718.364, "dur": 2.309, + "args": { + "External id": 4059499,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11266 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823719.110, "dur": 1.493, + "args": { + "External id": 4059500,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11267 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823720.900, "dur": 1.555, + "args": { + "External id": 4059501,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11268 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823721.927, "dur": 0.459, + "args": { + "External id": 4059502,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11269 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823722.696, "dur": 1.151, + "args": { + "External id": 4059503,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11270 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823723.230, "dur": 0.552, + "args": { + "External id": 4059504,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11271 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823725.394, "dur": 2.642, + "args": { + "External id": 4059505,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11272 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823727.514, "dur": 0.451, + "args": { + "External id": 4059506,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11273 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823728.342, "dur": 1.191, + "args": { + "External id": 4059507,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11274 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823728.973, "dur": 0.492, + "args": { + "External id": 4059508,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11275 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823729.769, "dur": 1.692, + "args": { + "External id": 4059509,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11276 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823730.786, "dur": 0.612, + "args": { + "External id": 4059510,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11277 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823731.706, "dur": 2.463, + "args": { + "External id": 4059511,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11278 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823733.622, "dur": 0.390, + "args": { + "External id": 4059512,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11279 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823734.411, "dur": 1.424, + "args": { + "External id": 4059513,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11280 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823735.249, "dur": 0.516, + "args": { + "External id": 4059514,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11281 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823736.102, "dur": 2.457, + "args": { + "External id": 4059515,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11282 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823736.754, "dur": 1.542, + "args": { + "External id": 4059516,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11283 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unsqueeze", "pid": 1336756, "tid": 1336756, + "ts": 1655275823738.783, "dur": 1.506, + "args": { + "External id": 4059517,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11284 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275823739.803, "dur": 0.416, + "args": { + "External id": 4059518,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11285 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::cat", "pid": 1336756, "tid": 1336756, + "ts": 1655275823759.642, "dur": 126.719, + "args": { + "External id": 4059519,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["TensorList", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11286 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linalg_vector_norm", "pid": 1336756, "tid": 1336756, + "ts": 1655275823981.815, "dur": 159.530, + "args": { + "External id": 4059520,"Record function id": 0, "Concrete Inputs": ["", "2.", "", "False", ""], "Input type": ["float", "Scalar", "", "Scalar", ""], "Input Strides": [[1], [], [], [], []], "Input Dims": [[291], [], [], [], []], "Ev Idx": 11287 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linalg_vector_norm", "pid": 1336756, "tid": 1336756, + "ts": 1655275824070.352, "dur": 50.465, + "args": { + "External id": 4059521,"Record function id": 0, "Concrete Inputs": ["", "2.", "", "False", ""], "Input type": ["float", "Scalar", "", "Scalar", ""], "Input Strides": [[1], [], [], [], []], "Input Dims": [[291], [], [], [], []], "Ev Idx": 11288 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275824087.025, "dur": 1.125, + "args": { + "External id": 4059522,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[0]", ""], "Input type": ["float", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11289 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Redistribute", "pid": 1336756, "tid": 1336756, + "ts": 1655275824480.466, "dur": 1020.566, + "args": { + "External id": 4059523,"Sequence number": 40618588, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "False"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11290 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::pow", "pid": 1336756, "tid": 1336756, + "ts": 1655275824525.028, "dur": 56.606, + "args": { + "External id": 4059524,"Record function id": 0, "Concrete Inputs": ["", "2."], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11291 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275824529.319, "dur": 1.665, + "args": { + "External id": 4059525,"Record function id": 0, "Concrete Inputs": ["", "2."], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11292 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275824532.856, "dur": 0.561, + "args": { + "External id": 4059526,"Record function id": 0, "Concrete Inputs": ["", "6", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 11293 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "_c10d_functional::all_reduce", "pid": 1336756, "tid": 1336756, + "ts": 1655275824603.793, "dur": 471.348, + "args": { + "External id": 4059527,"Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["float", "", ""], "Input Strides": [[], [], []], "Input Dims": [[], [], []], "Ev Idx": 11294 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 1336756, "tid": 1336756, + "ts": 1655275824610.002, "dur": 41.435, + "args": { + "External id": 4059528,"Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11295 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336756, "tid": 1336756, + "ts": 1655275824613.321, "dur": 8.614, + "args": { + "External id": 4059529,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "0"], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 11296 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655275824617.102, "dur": 4.068, + "args": { + "External id": 4059530,"Record function id": 0, "Concrete Inputs": ["[]", "6", "0", "", "", "0"], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 11297 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1336756, + "ts": 1655275824623.300, "dur": 27.426, + "args": { + "External id": 4059531,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[], [], []], "Input Dims": [[], [], []], "Ev Idx": 11298 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::allreduce_", "pid": 1336756, "tid": 1336756, + "ts": 1655275824660.816, "dur": 410.756, + "args": { + "External id": 4059532,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "-1"], "Input type": ["TensorList", "", "", "", "Scalar"], "Input Strides": [[[]], [], [], [], []], "Input Dims": [[[]], [], [], [], []], "Ev Idx": 11299 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336756, "tid": 1336756, + "ts": 1655275824690.338, "dur": 374.301, + "args": { + "External id": 4059533,"Record function id": 0, "Collective name": "allreduce", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 3, "Input Strides": [[[]], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "3", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 1, "Process Group Name": "0", "Input type": ["TensorList", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[[]], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 11300, "In msg nelems": 1 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:all_reduce", "pid": 1336756, "tid": 1336756, + "ts": 1655275824705.365, "dur": 353.518, + "args": { + "External id": 4059534,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 11301 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::pow", "pid": 1336756, "tid": 1336756, + "ts": 1655275825238.915, "dur": 221.823, + "args": { + "External id": 4059535,"Record function id": 0, "Concrete Inputs": ["", "0.5"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11302 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "_c10d_functional::wait_tensor", "pid": 1336756, "tid": 1336756, + "ts": 1655275825330.245, "dur": 33.695, + "args": { + "External id": 4059536,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 11303 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336756, "tid": 1336756, + "ts": 1655275825349.461, "dur": 5.563, + "args": { + "External id": 4059537,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "3", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 11304, "In msg nelems": 0, "Rank": 3, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::pow", "pid": 1336756, "tid": 1336756, + "ts": 1655275825392.091, "dur": 61.429, + "args": { + "External id": 4059538,"Record function id": 0, "Concrete Inputs": ["", "0.5"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11305 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275825394.865, "dur": 1.027, + "args": { + "External id": 4059539,"Record function id": 0, "Concrete Inputs": ["", "0.5"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11306 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275825397.183, "dur": 0.563, + "args": { + "External id": 4059540,"Record function id": 0, "Concrete Inputs": ["", "6", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 11307 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "_ToTorchTensor", "pid": 1336756, "tid": 1336756, + "ts": 1655275825518.171, "dur": 20.912, + "args": { + "External id": 4059541,"Sequence number": 40618589, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", ""], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11308 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 1336756, "tid": 1336756, + "ts": 1655275825527.651, "dur": 8.416, + "args": { + "External id": 4059542,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11309 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655275825530.178, "dur": 5.693, + "args": { + "External id": 4059543,"Record function id": 0, "Concrete Inputs": ["", "[]"], "Input type": ["float", "ScalarList"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11310 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::add", "pid": 1336756, "tid": 1336756, + "ts": 1655275825836.723, "dur": 33.088, + "args": { + "External id": 4059544,"Record function id": 0, "Concrete Inputs": ["", "", "1"], "Input type": ["float", "double", "Scalar"], "Input Strides": [[], [], []], "Input Dims": [[], [], []], "Ev Idx": 11311 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reciprocal", "pid": 1336756, "tid": 1336756, + "ts": 1655275825878.575, "dur": 22.351, + "args": { + "External id": 4059545,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 11312 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mul", "pid": 1336756, "tid": 1336756, + "ts": 1655275825914.081, "dur": 27.132, + "args": { + "External id": 4059546,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "double"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11313 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clamp", "pid": 1336756, "tid": 1336756, + "ts": 1655275825953.463, "dur": 27.177, + "args": { + "External id": 4059547,"Record function id": 0, "Concrete Inputs": ["", "", "1."], "Input type": ["float", "", "Scalar"], "Input Strides": [[], [], []], "Input Dims": [[], [], []], "Ev Idx": 11314 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275825957.543, "dur": 0.433, + "args": { + "External id": 4059548,"Record function id": 0, "Concrete Inputs": ["", "6", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 11315 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275826035.688, "dur": 0.626, + "args": { + "External id": 4059549,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "False", "False", ""], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], []], "Ev Idx": 11316 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_mul_", "pid": 1336756, "tid": 1336756, + "ts": 1655275826143.305, "dur": 705.333, + "args": { + "External id": 4059550,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["TensorList", "float"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11317 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_mul_", "pid": 1336756, "tid": 1336756, + "ts": 1655275826647.019, "dur": 170.248, + "args": { + "External id": 4059551,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["TensorList", "float"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11318 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::isnan", "pid": 1336756, "tid": 1336756, + "ts": 1655275826892.514, "dur": 33.505, + "args": { + "External id": 4059552,"Sequence number": 40618590, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 11319 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::ne", "pid": 1336756, "tid": 1336756, + "ts": 1655275826896.435, "dur": 28.124, + "args": { + "External id": 4059553,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11320 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::is_nonzero", "pid": 1336756, "tid": 1336756, + "ts": 1655275826931.257, "dur": 2731.828, + "args": { + "External id": 4059554,"Sequence number": 40618590, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["bool"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 11321 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::item", "pid": 1336756, "tid": 1336756, + "ts": 1655275826932.664, "dur": 2730.220, + "args": { + "External id": 4059555,"Sequence number": 40618590, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["bool"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 11322 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_local_scalar_dense", "pid": 1336756, "tid": 1336756, + "ts": 1655275826934.646, "dur": 2727.545, + "args": { + "External id": 4059556,"Sequence number": 40618590, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["bool"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 11323 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::isinf", "pid": 1336756, "tid": 1336756, + "ts": 1655275829670.033, "dur": 65.436, + "args": { + "External id": 4059557,"Sequence number": 40618590, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 11324 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336756, "tid": 1336756, + "ts": 1655275829673.281, "dur": 37.042, + "args": { + "External id": 4059558,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 11325 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655275829681.546, "dur": 3.432, + "args": { + "External id": 4059559,"Record function id": 0, "Concrete Inputs": ["[0]", "6", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 11326 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::abs", "pid": 1336756, "tid": 1336756, + "ts": 1655275829686.672, "dur": 23.239, + "args": { + "External id": 4059560,"Record function id": 0, "Concrete Inputs": ["", ""], "Input type": ["float", "float"], "Input Strides": [[], [1]], "Input Dims": [[], [0]], "Ev Idx": 11327 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resize_", "pid": 1336756, "tid": 1336756, + "ts": 1655275829691.687, "dur": 2.838, + "args": { + "External id": 4059561,"Record function id": 0, "Concrete Inputs": ["", "[]", ""], "Input type": ["float", "ScalarList", ""], "Input Strides": [[1], [], []], "Input Dims": [[0], [], []], "Ev Idx": 11328 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 1336756, "tid": 1336756, + "ts": 1655275829713.529, "dur": 21.046, + "args": { + "External id": 4059562,"Record function id": 0, "Concrete Inputs": ["", "inf"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11329 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::is_nonzero", "pid": 1336756, "tid": 1336756, + "ts": 1655275829737.756, "dur": 35.353, + "args": { + "External id": 4059563,"Sequence number": 40618590, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["bool"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 11330 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::item", "pid": 1336756, "tid": 1336756, + "ts": 1655275829740.416, "dur": 32.443, + "args": { + "External id": 4059564,"Sequence number": 40618590, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["bool"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 11331 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_local_scalar_dense", "pid": 1336756, "tid": 1336756, + "ts": 1655275829741.231, "dur": 31.348, + "args": { + "External id": 4059565,"Sequence number": 40618590, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["bool"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 11332 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "Optimizer.step#OptimizersContainer.step", "pid": 1336756, "tid": 1336756, + "ts": 1655275829803.310, "dur": 5266.369, + "args": { + "External id": 4059566,"Record function id": 0, "Ev Idx": 11333 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "Optimizer.step#AdamW.step", "pid": 1336756, "tid": 1336756, + "ts": 1655275829830.895, "dur": 5218.106, + "args": { + "External id": 4059567,"Record function id": 0, "Ev Idx": 11334 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_add_", "pid": 1336756, "tid": 1336756, + "ts": 1655275830944.019, "dur": 285.624, + "args": { + "External id": 4059568,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["TensorList", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11335 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275830964.732, "dur": 1.104, + "args": { + "External id": 4059569,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11336 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275830967.027, "dur": 0.205, + "args": { + "External id": 4059570,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11337 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275830967.632, "dur": 0.161, + "args": { + "External id": 4059571,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11338 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275830968.202, "dur": 0.166, + "args": { + "External id": 4059572,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11339 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275830968.734, "dur": 0.068, + "args": { + "External id": 4059573,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11340 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275830969.188, "dur": 0.068, + "args": { + "External id": 4059574,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11341 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275830969.654, "dur": 0.186, + "args": { + "External id": 4059575,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11342 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275830970.302, "dur": 0.192, + "args": { + "External id": 4059576,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11343 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275830970.972, "dur": 0.061, + "args": { + "External id": 4059577,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11344 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275830971.422, "dur": 0.159, + "args": { + "External id": 4059578,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11345 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275830971.892, "dur": 0.070, + "args": { + "External id": 4059579,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11346 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275830972.302, "dur": 0.076, + "args": { + "External id": 4059580,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11347 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275830972.712, "dur": 0.057, + "args": { + "External id": 4059581,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11348 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275830973.093, "dur": 0.059, + "args": { + "External id": 4059582,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11349 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275830973.482, "dur": 0.059, + "args": { + "External id": 4059583,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11350 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275830973.887, "dur": 0.059, + "args": { + "External id": 4059584,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11351 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275830974.299, "dur": 0.062, + "args": { + "External id": 4059585,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11352 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275830974.832, "dur": 0.050, + "args": { + "External id": 4059586,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11353 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275830975.266, "dur": 0.060, + "args": { + "External id": 4059587,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11354 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275830975.706, "dur": 0.055, + "args": { + "External id": 4059588,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11355 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275830976.163, "dur": 0.049, + "args": { + "External id": 4059589,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11356 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275830976.512, "dur": 0.060, + "args": { + "External id": 4059590,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11357 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275830976.896, "dur": 0.056, + "args": { + "External id": 4059591,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11358 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275830977.287, "dur": 0.080, + "args": { + "External id": 4059592,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11359 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275830977.731, "dur": 0.061, + "args": { + "External id": 4059593,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11360 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275830978.089, "dur": 0.057, + "args": { + "External id": 4059594,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11361 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275830978.527, "dur": 0.062, + "args": { + "External id": 4059595,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11362 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275830978.879, "dur": 0.070, + "args": { + "External id": 4059596,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11363 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275830979.276, "dur": 0.098, + "args": { + "External id": 4059597,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11364 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275830979.779, "dur": 0.173, + "args": { + "External id": 4059598,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11365 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275830980.254, "dur": 0.054, + "args": { + "External id": 4059599,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11366 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275830980.612, "dur": 0.069, + "args": { + "External id": 4059600,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11367 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831010.622, "dur": 0.536, + "args": { + "External id": 4059601,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11368 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831012.433, "dur": 0.077, + "args": { + "External id": 4059602,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11369 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831012.913, "dur": 0.082, + "args": { + "External id": 4059603,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11370 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831013.558, "dur": 0.076, + "args": { + "External id": 4059604,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11371 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831014.118, "dur": 0.068, + "args": { + "External id": 4059605,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11372 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831014.732, "dur": 0.066, + "args": { + "External id": 4059606,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11373 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831015.234, "dur": 0.051, + "args": { + "External id": 4059607,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11374 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831015.677, "dur": 0.061, + "args": { + "External id": 4059608,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11375 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831016.148, "dur": 0.057, + "args": { + "External id": 4059609,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11376 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831016.553, "dur": 0.061, + "args": { + "External id": 4059610,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11377 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831016.948, "dur": 0.087, + "args": { + "External id": 4059611,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11378 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831017.391, "dur": 0.071, + "args": { + "External id": 4059612,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11379 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831017.832, "dur": 0.067, + "args": { + "External id": 4059613,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11380 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831018.333, "dur": 0.069, + "args": { + "External id": 4059614,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11381 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831018.783, "dur": 0.059, + "args": { + "External id": 4059615,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11382 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831019.233, "dur": 0.057, + "args": { + "External id": 4059616,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11383 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831019.724, "dur": 0.051, + "args": { + "External id": 4059617,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11384 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831020.328, "dur": 0.058, + "args": { + "External id": 4059618,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11385 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831020.820, "dur": 0.049, + "args": { + "External id": 4059619,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11386 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831021.261, "dur": 0.048, + "args": { + "External id": 4059620,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11387 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831021.646, "dur": 0.056, + "args": { + "External id": 4059621,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11388 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831022.007, "dur": 0.070, + "args": { + "External id": 4059622,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11389 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831022.458, "dur": 0.071, + "args": { + "External id": 4059623,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11390 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831022.864, "dur": 0.065, + "args": { + "External id": 4059624,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11391 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831023.330, "dur": 0.060, + "args": { + "External id": 4059625,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11392 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831023.725, "dur": 0.056, + "args": { + "External id": 4059626,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11393 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831024.163, "dur": 0.057, + "args": { + "External id": 4059627,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11394 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831024.573, "dur": 0.052, + "args": { + "External id": 4059628,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11395 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831024.927, "dur": 0.055, + "args": { + "External id": 4059629,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11396 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831025.296, "dur": 0.061, + "args": { + "External id": 4059630,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11397 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831025.696, "dur": 0.056, + "args": { + "External id": 4059631,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11398 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831026.025, "dur": 0.059, + "args": { + "External id": 4059632,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11399 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831026.439, "dur": 0.054, + "args": { + "External id": 4059633,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11400 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831026.856, "dur": 0.056, + "args": { + "External id": 4059634,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11401 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831027.222, "dur": 0.054, + "args": { + "External id": 4059635,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11402 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831027.606, "dur": 0.056, + "args": { + "External id": 4059636,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11403 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831028.006, "dur": 0.059, + "args": { + "External id": 4059637,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11404 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831028.417, "dur": 0.068, + "args": { + "External id": 4059638,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11405 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831028.832, "dur": 0.066, + "args": { + "External id": 4059639,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11406 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831029.229, "dur": 0.282, + "args": { + "External id": 4059640,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11407 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831029.894, "dur": 0.064, + "args": { + "External id": 4059641,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11408 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831030.358, "dur": 0.062, + "args": { + "External id": 4059642,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11409 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831030.773, "dur": 0.160, + "args": { + "External id": 4059643,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11410 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831031.392, "dur": 0.050, + "args": { + "External id": 4059644,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11411 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831031.781, "dur": 0.060, + "args": { + "External id": 4059645,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11412 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831032.309, "dur": 0.179, + "args": { + "External id": 4059646,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11413 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831032.802, "dur": 0.178, + "args": { + "External id": 4059647,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11414 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831033.295, "dur": 0.083, + "args": { + "External id": 4059648,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11415 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831054.152, "dur": 0.158, + "args": { + "External id": 4059649,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11416 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831055.080, "dur": 0.051, + "args": { + "External id": 4059650,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11417 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831055.439, "dur": 0.058, + "args": { + "External id": 4059651,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11418 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831055.842, "dur": 0.068, + "args": { + "External id": 4059652,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11419 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831056.244, "dur": 0.069, + "args": { + "External id": 4059653,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11420 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831056.663, "dur": 0.055, + "args": { + "External id": 4059654,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11421 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831057.086, "dur": 0.068, + "args": { + "External id": 4059655,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11422 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831057.519, "dur": 0.056, + "args": { + "External id": 4059656,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11423 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831057.906, "dur": 0.057, + "args": { + "External id": 4059657,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11424 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831058.351, "dur": 0.060, + "args": { + "External id": 4059658,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11425 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831058.738, "dur": 0.059, + "args": { + "External id": 4059659,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11426 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831059.101, "dur": 0.055, + "args": { + "External id": 4059660,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11427 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831059.437, "dur": 0.065, + "args": { + "External id": 4059661,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11428 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831059.851, "dur": 0.060, + "args": { + "External id": 4059662,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11429 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831060.263, "dur": 0.059, + "args": { + "External id": 4059663,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11430 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831060.682, "dur": 0.056, + "args": { + "External id": 4059664,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11431 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831061.097, "dur": 0.064, + "args": { + "External id": 4059665,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11432 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831061.477, "dur": 0.066, + "args": { + "External id": 4059666,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11433 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831061.899, "dur": 0.059, + "args": { + "External id": 4059667,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11434 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831062.286, "dur": 0.055, + "args": { + "External id": 4059668,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11435 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831062.672, "dur": 0.060, + "args": { + "External id": 4059669,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11436 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831063.086, "dur": 0.053, + "args": { + "External id": 4059670,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11437 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831063.497, "dur": 0.054, + "args": { + "External id": 4059671,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11438 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831063.892, "dur": 0.058, + "args": { + "External id": 4059672,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11439 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831064.289, "dur": 0.066, + "args": { + "External id": 4059673,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11440 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831064.789, "dur": 0.054, + "args": { + "External id": 4059674,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11441 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831065.145, "dur": 0.068, + "args": { + "External id": 4059675,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11442 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831065.536, "dur": 0.064, + "args": { + "External id": 4059676,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11443 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831065.933, "dur": 0.067, + "args": { + "External id": 4059677,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11444 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831066.301, "dur": 0.057, + "args": { + "External id": 4059678,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11445 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831066.684, "dur": 0.059, + "args": { + "External id": 4059679,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11446 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831067.092, "dur": 0.053, + "args": { + "External id": 4059680,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11447 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831067.460, "dur": 0.057, + "args": { + "External id": 4059681,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11448 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831067.903, "dur": 0.068, + "args": { + "External id": 4059682,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11449 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831068.335, "dur": 0.067, + "args": { + "External id": 4059683,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11450 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831068.760, "dur": 0.067, + "args": { + "External id": 4059684,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11451 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831069.203, "dur": 0.048, + "args": { + "External id": 4059685,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11452 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831069.593, "dur": 0.056, + "args": { + "External id": 4059686,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11453 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831070.096, "dur": 0.047, + "args": { + "External id": 4059687,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11454 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831070.489, "dur": 0.056, + "args": { + "External id": 4059688,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11455 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831070.911, "dur": 0.056, + "args": { + "External id": 4059689,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11456 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831071.298, "dur": 0.056, + "args": { + "External id": 4059690,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11457 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831071.724, "dur": 0.054, + "args": { + "External id": 4059691,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11458 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831072.080, "dur": 0.057, + "args": { + "External id": 4059692,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11459 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831072.473, "dur": 0.056, + "args": { + "External id": 4059693,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11460 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831072.873, "dur": 0.059, + "args": { + "External id": 4059694,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11461 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831073.256, "dur": 0.060, + "args": { + "External id": 4059695,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11462 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831073.659, "dur": 0.059, + "args": { + "External id": 4059696,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11463 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831073.990, "dur": 0.059, + "args": { + "External id": 4059697,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11464 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831074.386, "dur": 0.058, + "args": { + "External id": 4059698,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11465 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831080.636, "dur": 0.068, + "args": { + "External id": 4059699,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11466 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831082.062, "dur": 0.056, + "args": { + "External id": 4059700,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11467 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831082.409, "dur": 0.058, + "args": { + "External id": 4059701,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11468 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831082.789, "dur": 0.053, + "args": { + "External id": 4059702,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11469 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831083.224, "dur": 0.051, + "args": { + "External id": 4059703,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11470 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831083.557, "dur": 0.056, + "args": { + "External id": 4059704,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11471 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831083.974, "dur": 0.057, + "args": { + "External id": 4059705,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11472 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831084.367, "dur": 0.053, + "args": { + "External id": 4059706,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11473 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831084.789, "dur": 0.057, + "args": { + "External id": 4059707,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11474 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831085.168, "dur": 0.056, + "args": { + "External id": 4059708,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11475 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831085.577, "dur": 0.056, + "args": { + "External id": 4059709,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11476 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831086.008, "dur": 0.053, + "args": { + "External id": 4059710,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11477 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831086.451, "dur": 0.058, + "args": { + "External id": 4059711,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11478 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831086.833, "dur": 0.060, + "args": { + "External id": 4059712,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11479 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831087.277, "dur": 0.058, + "args": { + "External id": 4059713,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11480 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831087.665, "dur": 0.057, + "args": { + "External id": 4059714,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11481 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831088.096, "dur": 0.057, + "args": { + "External id": 4059715,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11482 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831088.487, "dur": 0.056, + "args": { + "External id": 4059716,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11483 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831088.857, "dur": 0.055, + "args": { + "External id": 4059717,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11484 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831089.222, "dur": 0.067, + "args": { + "External id": 4059718,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11485 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831089.724, "dur": 0.047, + "args": { + "External id": 4059719,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11486 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831090.129, "dur": 0.060, + "args": { + "External id": 4059720,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11487 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831090.537, "dur": 0.060, + "args": { + "External id": 4059721,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11488 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831090.886, "dur": 0.057, + "args": { + "External id": 4059722,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11489 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831091.373, "dur": 0.050, + "args": { + "External id": 4059723,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11490 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831091.713, "dur": 0.070, + "args": { + "External id": 4059724,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11491 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831092.117, "dur": 0.065, + "args": { + "External id": 4059725,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11492 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831092.530, "dur": 0.061, + "args": { + "External id": 4059726,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11493 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831092.895, "dur": 0.045, + "args": { + "External id": 4059727,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11494 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831093.293, "dur": 0.069, + "args": { + "External id": 4059728,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11495 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831093.689, "dur": 0.067, + "args": { + "External id": 4059729,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11496 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831094.138, "dur": 0.058, + "args": { + "External id": 4059730,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11497 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831094.498, "dur": 0.056, + "args": { + "External id": 4059731,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11498 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831094.894, "dur": 0.055, + "args": { + "External id": 4059732,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11499 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831095.336, "dur": 0.059, + "args": { + "External id": 4059733,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11500 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831095.649, "dur": 0.056, + "args": { + "External id": 4059734,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11501 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831096.085, "dur": 0.061, + "args": { + "External id": 4059735,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11502 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831096.471, "dur": 0.057, + "args": { + "External id": 4059736,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11503 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831096.851, "dur": 0.060, + "args": { + "External id": 4059737,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11504 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831097.251, "dur": 0.059, + "args": { + "External id": 4059738,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11505 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831097.626, "dur": 0.057, + "args": { + "External id": 4059739,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11506 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831097.968, "dur": 0.060, + "args": { + "External id": 4059740,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11507 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831098.346, "dur": 0.057, + "args": { + "External id": 4059741,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11508 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831098.842, "dur": 0.056, + "args": { + "External id": 4059742,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11509 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831099.291, "dur": 0.061, + "args": { + "External id": 4059743,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11510 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831099.641, "dur": 0.083, + "args": { + "External id": 4059744,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11511 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831100.079, "dur": 0.054, + "args": { + "External id": 4059745,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11512 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831100.439, "dur": 0.057, + "args": { + "External id": 4059746,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11513 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831100.821, "dur": 0.071, + "args": { + "External id": 4059747,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11514 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831101.253, "dur": 0.057, + "args": { + "External id": 4059748,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11515 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831101.620, "dur": 0.060, + "args": { + "External id": 4059749,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11516 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831101.974, "dur": 0.051, + "args": { + "External id": 4059750,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11517 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831102.348, "dur": 0.059, + "args": { + "External id": 4059751,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11518 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831102.717, "dur": 0.058, + "args": { + "External id": 4059752,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11519 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831103.103, "dur": 0.058, + "args": { + "External id": 4059753,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11520 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831103.632, "dur": 0.058, + "args": { + "External id": 4059754,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11521 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831104.025, "dur": 0.059, + "args": { + "External id": 4059755,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11522 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831104.378, "dur": 0.059, + "args": { + "External id": 4059756,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11523 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831104.771, "dur": 0.058, + "args": { + "External id": 4059757,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11524 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831105.187, "dur": 0.059, + "args": { + "External id": 4059758,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11525 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831105.595, "dur": 0.058, + "args": { + "External id": 4059759,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11526 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831105.980, "dur": 0.056, + "args": { + "External id": 4059760,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11527 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831106.376, "dur": 0.058, + "args": { + "External id": 4059761,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11528 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831106.748, "dur": 0.058, + "args": { + "External id": 4059762,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11529 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831107.097, "dur": 0.054, + "args": { + "External id": 4059763,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11530 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831107.496, "dur": 0.059, + "args": { + "External id": 4059764,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11531 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831107.908, "dur": 0.065, + "args": { + "External id": 4059765,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11532 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831108.368, "dur": 0.052, + "args": { + "External id": 4059766,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11533 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831108.703, "dur": 0.065, + "args": { + "External id": 4059767,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11534 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831109.117, "dur": 0.056, + "args": { + "External id": 4059768,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11535 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831109.582, "dur": 0.058, + "args": { + "External id": 4059769,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11536 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831109.911, "dur": 0.057, + "args": { + "External id": 4059770,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11537 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831110.369, "dur": 0.056, + "args": { + "External id": 4059771,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11538 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831110.766, "dur": 0.063, + "args": { + "External id": 4059772,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11539 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831111.232, "dur": 0.065, + "args": { + "External id": 4059773,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11540 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831111.699, "dur": 0.056, + "args": { + "External id": 4059774,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11541 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831112.120, "dur": 0.063, + "args": { + "External id": 4059775,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11542 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831112.463, "dur": 0.068, + "args": { + "External id": 4059776,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11543 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831112.950, "dur": 0.049, + "args": { + "External id": 4059777,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11544 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831113.319, "dur": 0.058, + "args": { + "External id": 4059778,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11545 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831113.697, "dur": 0.057, + "args": { + "External id": 4059779,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11546 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831114.105, "dur": 0.080, + "args": { + "External id": 4059780,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11547 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831114.521, "dur": 0.055, + "args": { + "External id": 4059781,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11548 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831114.884, "dur": 0.066, + "args": { + "External id": 4059782,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11549 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831115.273, "dur": 0.067, + "args": { + "External id": 4059783,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11550 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831115.660, "dur": 0.065, + "args": { + "External id": 4059784,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11551 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831116.210, "dur": 0.058, + "args": { + "External id": 4059785,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11552 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831116.533, "dur": 0.056, + "args": { + "External id": 4059786,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11553 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831116.845, "dur": 0.058, + "args": { + "External id": 4059787,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11554 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831117.601, "dur": 0.060, + "args": { + "External id": 4059788,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11555 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831118.004, "dur": 0.051, + "args": { + "External id": 4059789,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11556 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831118.594, "dur": 0.062, + "args": { + "External id": 4059790,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11557 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831118.915, "dur": 0.051, + "args": { + "External id": 4059791,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11558 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831119.591, "dur": 0.060, + "args": { + "External id": 4059792,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11559 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831119.907, "dur": 0.049, + "args": { + "External id": 4059793,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11560 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831120.549, "dur": 0.059, + "args": { + "External id": 4059794,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11561 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831120.857, "dur": 0.050, + "args": { + "External id": 4059795,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11562 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831121.374, "dur": 0.057, + "args": { + "External id": 4059796,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11563 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831121.693, "dur": 0.048, + "args": { + "External id": 4059797,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11564 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831122.306, "dur": 0.055, + "args": { + "External id": 4059798,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11565 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831122.617, "dur": 0.044, + "args": { + "External id": 4059799,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11566 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831123.292, "dur": 0.059, + "args": { + "External id": 4059800,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11567 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831123.624, "dur": 0.051, + "args": { + "External id": 4059801,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11568 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831124.162, "dur": 0.057, + "args": { + "External id": 4059802,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11569 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831124.501, "dur": 0.052, + "args": { + "External id": 4059803,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11570 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831125.311, "dur": 0.095, + "args": { + "External id": 4059804,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11571 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831125.660, "dur": 0.053, + "args": { + "External id": 4059805,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11572 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831126.226, "dur": 0.059, + "args": { + "External id": 4059806,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11573 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831126.547, "dur": 0.050, + "args": { + "External id": 4059807,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11574 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831127.306, "dur": 0.069, + "args": { + "External id": 4059808,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11575 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831127.699, "dur": 0.056, + "args": { + "External id": 4059809,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11576 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831128.331, "dur": 0.069, + "args": { + "External id": 4059810,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11577 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831128.664, "dur": 0.049, + "args": { + "External id": 4059811,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11578 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831129.160, "dur": 0.067, + "args": { + "External id": 4059812,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11579 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831129.487, "dur": 0.050, + "args": { + "External id": 4059813,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11580 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831130.032, "dur": 0.059, + "args": { + "External id": 4059814,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11581 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831130.352, "dur": 0.047, + "args": { + "External id": 4059815,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11582 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831130.949, "dur": 0.065, + "args": { + "External id": 4059816,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11583 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831131.274, "dur": 0.052, + "args": { + "External id": 4059817,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11584 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831131.886, "dur": 0.060, + "args": { + "External id": 4059818,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11585 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831132.202, "dur": 0.054, + "args": { + "External id": 4059819,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11586 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831132.944, "dur": 0.061, + "args": { + "External id": 4059820,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11587 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831133.257, "dur": 0.051, + "args": { + "External id": 4059821,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11588 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831133.746, "dur": 0.069, + "args": { + "External id": 4059822,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11589 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831134.070, "dur": 0.053, + "args": { + "External id": 4059823,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11590 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831134.709, "dur": 0.068, + "args": { + "External id": 4059824,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11591 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831135.032, "dur": 0.067, + "args": { + "External id": 4059825,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11592 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831135.523, "dur": 0.059, + "args": { + "External id": 4059826,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11593 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831135.831, "dur": 0.050, + "args": { + "External id": 4059827,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11594 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831136.383, "dur": 0.071, + "args": { + "External id": 4059828,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11595 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831136.706, "dur": 0.054, + "args": { + "External id": 4059829,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11596 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831137.259, "dur": 0.067, + "args": { + "External id": 4059830,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11597 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831137.586, "dur": 0.053, + "args": { + "External id": 4059831,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11598 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831138.111, "dur": 0.060, + "args": { + "External id": 4059832,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11599 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831138.433, "dur": 0.050, + "args": { + "External id": 4059833,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11600 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831139.033, "dur": 0.067, + "args": { + "External id": 4059834,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11601 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831139.360, "dur": 0.053, + "args": { + "External id": 4059835,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11602 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831139.899, "dur": 0.068, + "args": { + "External id": 4059836,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11603 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831140.226, "dur": 0.051, + "args": { + "External id": 4059837,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11604 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831140.807, "dur": 0.067, + "args": { + "External id": 4059838,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11605 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831141.135, "dur": 0.053, + "args": { + "External id": 4059839,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11606 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831141.814, "dur": 0.068, + "args": { + "External id": 4059840,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11607 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831142.137, "dur": 0.054, + "args": { + "External id": 4059841,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11608 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831142.706, "dur": 0.060, + "args": { + "External id": 4059842,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11609 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831143.020, "dur": 0.053, + "args": { + "External id": 4059843,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11610 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831143.666, "dur": 0.064, + "args": { + "External id": 4059844,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11611 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831144.011, "dur": 0.055, + "args": { + "External id": 4059845,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11612 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831144.691, "dur": 0.064, + "args": { + "External id": 4059846,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11613 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831145.012, "dur": 0.049, + "args": { + "External id": 4059847,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11614 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831145.668, "dur": 0.057, + "args": { + "External id": 4059848,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11615 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831145.983, "dur": 0.049, + "args": { + "External id": 4059849,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11616 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831146.633, "dur": 0.059, + "args": { + "External id": 4059850,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11617 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831146.957, "dur": 0.052, + "args": { + "External id": 4059851,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11618 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831147.501, "dur": 0.071, + "args": { + "External id": 4059852,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11619 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831147.829, "dur": 0.048, + "args": { + "External id": 4059853,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11620 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831148.372, "dur": 0.067, + "args": { + "External id": 4059854,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11621 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831148.695, "dur": 0.054, + "args": { + "External id": 4059855,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11622 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831149.328, "dur": 0.069, + "args": { + "External id": 4059856,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11623 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831149.651, "dur": 0.053, + "args": { + "External id": 4059857,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11624 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831150.128, "dur": 0.057, + "args": { + "External id": 4059858,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11625 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::result_type", "pid": 1336756, "tid": 1336756, + "ts": 1655275831150.444, "dur": 0.051, + "args": { + "External id": 4059859,"Record function id": 0, "Concrete Inputs": ["", "1"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11626 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_fused_adamw_", "pid": 1336756, "tid": 1336756, + "ts": 1655275831706.190, "dur": 3222.282, + "args": { + "External id": 4059860,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "3.0696758680726497e-05", "0.90000000000000002", "0.94999999999999996", "0.10000000000000001", "1.0000000000000001e-15", "False", "False", "", ""], "Input type": ["TensorList", "TensorList", "TensorList", "TensorList", "TensorList", "TensorList", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 11627 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_fused_adamw_", "pid": 1336756, "tid": 1336756, + "ts": 1655275834460.881, "dur": 335.198, + "args": { + "External id": 4059861,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "3.0696758680726497e-05", "0.90000000000000002", "0.94999999999999996", "0.10000000000000001", "1.0000000000000001e-15", "False", "False", "", ""], "Input type": ["TensorList", "TensorList", "TensorList", "TensorList", "TensorList", "TensorList", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "Scalar", "", ""], "Input Strides": [[], [], [], [], [], [], [], [], [], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], [], [], [], [], [], [], [], [], []], "Ev Idx": 11628 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1336756, + "ts": 1655275835112.283, "dur": 26.165, + "args": { + "External id": 4059862,"Sequence number": 40618590, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[1]], "Ev Idx": 11629 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1336756, + "ts": 1655275835130.981, "dur": 7.253, + "args": { + "External id": 4059863,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[1]], "Ev Idx": 11630 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::permute", "pid": 1336756, "tid": 1336756, + "ts": 1655275835193.360, "dur": 10.618, + "args": { + "External id": 4059864,"Sequence number": 40618590, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[0]"], "Input type": ["int", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[8], []], "Ev Idx": 11631 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275835198.013, "dur": 4.254, + "args": { + "External id": 4059865,"Record function id": 0, "Concrete Inputs": ["", "[8]", "[1]", ""], "Input type": ["int", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[8], [], [], []], "Ev Idx": 11632 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1336756, + "ts": 1655275835208.863, "dur": 5.983, + "args": { + "External id": 4059866,"Sequence number": 40618590, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[-1, 8]"], "Input type": ["int", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[8], []], "Ev Idx": 11633 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655275835210.583, "dur": 4.004, + "args": { + "External id": 4059867,"Sequence number": 40618590, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[-1, 8]"], "Input type": ["int", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[8], []], "Ev Idx": 11634 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unbind", "pid": 1336756, "tid": 1336756, + "ts": 1655275835236.437, "dur": 13.652, + "args": { + "External id": 4059868,"Sequence number": 40618590, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["int", "Scalar"], "Input Strides": [[8, 1], []], "Input Dims": [[1, 8], []], "Ev Idx": 11635 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select", "pid": 1336756, "tid": 1336756, + "ts": 1655275835242.691, "dur": 6.192, + "args": { + "External id": 4059869,"Record function id": 0, "Concrete Inputs": ["", "0", "0"], "Input type": ["int", "Scalar", "Scalar"], "Input Strides": [[8, 1], [], []], "Input Dims": [[1, 8], [], []], "Ev Idx": 11636 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275835247.336, "dur": 0.701, + "args": { + "External id": 4059870,"Record function id": 0, "Concrete Inputs": ["", "[8]", "[1]", "0"], "Input type": ["int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[8, 1], [], [], []], "Input Dims": [[1, 8], [], [], []], "Ev Idx": 11637 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1336756, + "ts": 1655275835261.996, "dur": 2.115, + "args": { + "External id": 4059871,"Sequence number": 40618590, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["int"], "Input Strides": [[1]], "Input Dims": [[8]], "Ev Idx": 11638 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1336756, + "ts": 1655275835262.464, "dur": 1.546, + "args": { + "External id": 4059872,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["int"], "Input Strides": [[1]], "Input Dims": [[8]], "Ev Idx": 11639 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275835269.035, "dur": 0.527, + "args": { + "External id": 4059873,"Sequence number": 40618590, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "3", "False", "False", ""], "Input type": ["int", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], []], "Input Dims": [[8], [], [], [], []], "Ev Idx": 11640 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::flatten", "pid": 1336756, "tid": 1336756, + "ts": 1655275835275.659, "dur": 0.548, + "args": { + "External id": 4059874,"Sequence number": 40618590, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "0", "-1"], "Input type": ["int", "Scalar", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[8], [], []], "Ev Idx": 11641 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resolve_conj", "pid": 1336756, "tid": 1336756, + "ts": 1655275835279.902, "dur": 1.047, + "args": { + "External id": 4059875,"Sequence number": 40618590, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["int"], "Input Strides": [[1]], "Input Dims": [[8]], "Ev Idx": 11642 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resolve_neg", "pid": 1336756, "tid": 1336756, + "ts": 1655275835282.873, "dur": 0.364, + "args": { + "External id": 4059876,"Sequence number": 40618590, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["int"], "Input Strides": [[1]], "Input Dims": [[8]], "Ev Idx": 11643 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 1336756, "tid": 1336756, + "ts": 1655275835301.981, "dur": 39.480, + "args": { + "External id": 4059877,"Sequence number": 40618590, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "3"], "Input type": ["int", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[8], []], "Ev Idx": 11644 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275835312.702, "dur": 21.271, + "args": { + "External id": 4059878,"Record function id": 0, "Concrete Inputs": ["", "3", "False", "False", ""], "Input type": ["long int", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 11645 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336756, "tid": 1336756, + "ts": 1655275835315.825, "dur": 17.964, + "args": { + "External id": 4059879,"Record function id": 0, "Concrete Inputs": ["", "3", "", "", "", "False", ""], "Input type": ["long int", "Scalar", "", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], []], "Ev Idx": 11646 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275835319.873, "dur": 3.235, + "args": { + "External id": 4059880,"Record function id": 0, "Concrete Inputs": ["[]", "[]", "3", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 11647 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1336756, + "ts": 1655275835324.457, "dur": 9.049, + "args": { + "External id": 4059881,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["int", "long int", "Scalar"], "Input Strides": [[], [], []], "Input Dims": [[], [], []], "Ev Idx": 11648 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::nonzero", "pid": 1336756, "tid": 1336756, + "ts": 1655275835347.779, "dur": 25.309, + "args": { + "External id": 4059882,"Sequence number": 40618590, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["bool"], "Input Strides": [[1]], "Input Dims": [[8]], "Ev Idx": 11649 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655275835351.604, "dur": 1.042, + "args": { + "External id": 4059883,"Record function id": 0, "Concrete Inputs": ["[0]", "4", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 11650 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided_", "pid": 1336756, "tid": 1336756, + "ts": 1655275835364.195, "dur": 4.844, + "args": { + "External id": 4059884,"Record function id": 0, "Concrete Inputs": ["", "[1, 1]", "[1, 1]", ""], "Input type": ["long int", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[1, 1], [], [], []], "Ev Idx": 11651 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select", "pid": 1336756, "tid": 1336756, + "ts": 1655275835378.229, "dur": 6.043, + "args": { + "External id": 4059885,"Sequence number": 40618590, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "0", "0"], "Input type": ["long int", "Scalar", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[1, 1], [], []], "Ev Idx": 11652 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275835382.476, "dur": 0.588, + "args": { + "External id": 4059886,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", "0"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[1, 1], [], [], []], "Ev Idx": 11653 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resolve_conj", "pid": 1336756, "tid": 1336756, + "ts": 1655275835385.846, "dur": 0.203, + "args": { + "External id": 4059887,"Sequence number": 40618590, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["long int"], "Input Strides": [[1]], "Input Dims": [[1]], "Ev Idx": 11654 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resolve_neg", "pid": 1336756, "tid": 1336756, + "ts": 1655275835386.798, "dur": 0.089, + "args": { + "External id": 4059888,"Sequence number": 40618590, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["long int"], "Input Strides": [[1]], "Input Dims": [[1]], "Ev Idx": 11655 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 1336756, "tid": 1336756, + "ts": 1655275835399.122, "dur": 10.173, + "args": { + "External id": 4059889,"Sequence number": 40618590, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "3"], "Input type": ["int", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[8], []], "Ev Idx": 11656 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275835402.821, "dur": 4.602, + "args": { + "External id": 4059890,"Record function id": 0, "Concrete Inputs": ["", "3", "False", "False", ""], "Input type": ["long int", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 11657 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336756, "tid": 1336756, + "ts": 1655275835403.493, "dur": 3.775, + "args": { + "External id": 4059891,"Record function id": 0, "Concrete Inputs": ["", "3", "", "", "", "False", ""], "Input type": ["long int", "Scalar", "", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], []], "Ev Idx": 11658 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275835404.790, "dur": 0.863, + "args": { + "External id": 4059892,"Record function id": 0, "Concrete Inputs": ["[]", "[]", "3", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 11659 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1336756, + "ts": 1655275835406.294, "dur": 0.825, + "args": { + "External id": 4059893,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["int", "long int", "Scalar"], "Input Strides": [[], [], []], "Input Dims": [[], [], []], "Ev Idx": 11660 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::any", "pid": 1336756, "tid": 1336756, + "ts": 1655275835414.309, "dur": 32.800, + "args": { + "External id": 4059894,"Sequence number": 40618590, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["bool"], "Input Strides": [[1]], "Input Dims": [[8]], "Ev Idx": 11661 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275835438.069, "dur": 0.855, + "args": { + "External id": 4059895,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[0]", ""], "Input type": ["bool", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11662 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 1336756, "tid": 1336756, + "ts": 1655275835443.967, "dur": 1.189, + "args": { + "External id": 4059896,"Record function id": 0, "Concrete Inputs": ["", "0."], "Input type": ["bool", "Scalar"], "Input Strides": [[0], []], "Input Dims": [[1], []], "Ev Idx": 11663 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::item", "pid": 1336756, "tid": 1336756, + "ts": 1655275835450.310, "dur": 2.836, + "args": { + "External id": 4059897,"Sequence number": 40618590, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["bool"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 11664 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_local_scalar_dense", "pid": 1336756, "tid": 1336756, + "ts": 1655275835451.553, "dur": 1.484, + "args": { + "External id": 4059898,"Sequence number": 40618590, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["bool"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 11665 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "_c10d_functional::all_reduce", "pid": 1336756, "tid": 1336756, + "ts": 1655275835498.840, "dur": 532.499, + "args": { + "External id": 4059899,"Sequence number": 40618590, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["float", "", ""], "Input Strides": [[1], [], []], "Input Dims": [[1], [], []], "Ev Idx": 11666 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 1336756, "tid": 1336756, + "ts": 1655275835501.766, "dur": 67.614, + "args": { + "External id": 4059900,"Sequence number": 40618590, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[1], []], "Ev Idx": 11667 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336756, "tid": 1336756, + "ts": 1655275835504.202, "dur": 16.159, + "args": { + "External id": 4059901,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "0"], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[1], [], [], [], [], []], "Ev Idx": 11668 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655275835506.010, "dur": 13.816, + "args": { + "External id": 4059902,"Record function id": 0, "Concrete Inputs": ["[1]", "6", "0", "", "", "0"], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 11669 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1336756, + "ts": 1655275835521.281, "dur": 47.432, + "args": { + "External id": 4059903,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[1], [1], []], "Ev Idx": 11670 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::allreduce_", "pid": 1336756, "tid": 1336756, + "ts": 1655275835575.026, "dur": 453.244, + "args": { + "External id": 4059904,"Sequence number": 40618590, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "-1"], "Input type": ["TensorList", "", "", "", "Scalar"], "Input Strides": [[[1]], [], [], [], []], "Input Dims": [[[1]], [], [], [], []], "Ev Idx": 11671 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336756, "tid": 1336756, + "ts": 1655275835605.280, "dur": 416.032, + "args": { + "External id": 4059905,"Record function id": 0, "Collective name": "allreduce", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 3, "Input Strides": [[[1]], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "3", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 1, "Process Group Name": "0", "Input type": ["TensorList", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[[1]], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 11672, "In msg nelems": 1 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:all_reduce", "pid": 1336756, "tid": 1336756, + "ts": 1655275835622.342, "dur": 392.096, + "args": { + "External id": 4059906,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[1]], "Ev Idx": 11673 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::item", "pid": 1336756, "tid": 1336756, + "ts": 1655275836079.532, "dur": 3510.336, + "args": { + "External id": 4059907,"Sequence number": 40618590, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[1]], "Ev Idx": 11674 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_local_scalar_dense", "pid": 1336756, "tid": 1336756, + "ts": 1655275836082.739, "dur": 3506.316, + "args": { + "External id": 4059908,"Sequence number": 40618590, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[1]], "Ev Idx": 11675 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "_c10d_functional::wait_tensor", "pid": 1336756, "tid": 1336756, + "ts": 1655275836145.194, "dur": 34.728, + "args": { + "External id": 4059909,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[1]], "Ev Idx": 11676 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336756, "tid": 1336756, + "ts": 1655275836162.301, "dur": 9.198, + "args": { + "External id": 4059910,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "3", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 11677, "In msg nelems": 0, "Rank": 3, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_local_scalar_dense", "pid": 1336756, "tid": 1336756, + "ts": 1655275836206.975, "dur": 3370.207, + "args": { + "External id": 4059911,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[1]], "Ev Idx": 11678 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::permute", "pid": 1336756, "tid": 1336756, + "ts": 1655275839634.804, "dur": 8.286, + "args": { + "External id": 4059912,"Sequence number": 40618590, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[0]"], "Input type": ["int", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[8], []], "Ev Idx": 11679 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275839639.281, "dur": 1.918, + "args": { + "External id": 4059913,"Record function id": 0, "Concrete Inputs": ["", "[8]", "[1]", ""], "Input type": ["int", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[8], [], [], []], "Ev Idx": 11680 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1336756, + "ts": 1655275839647.199, "dur": 6.613, + "args": { + "External id": 4059914,"Sequence number": 40618590, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[-1, 8]"], "Input type": ["int", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[8], []], "Ev Idx": 11681 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655275839649.150, "dur": 4.448, + "args": { + "External id": 4059915,"Sequence number": 40618590, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[-1, 8]"], "Input type": ["int", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[8], []], "Ev Idx": 11682 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unbind", "pid": 1336756, "tid": 1336756, + "ts": 1655275839665.946, "dur": 9.178, + "args": { + "External id": 4059916,"Sequence number": 40618590, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["int", "Scalar"], "Input Strides": [[8, 1], []], "Input Dims": [[1, 8], []], "Ev Idx": 11683 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select", "pid": 1336756, "tid": 1336756, + "ts": 1655275839669.112, "dur": 5.048, + "args": { + "External id": 4059917,"Record function id": 0, "Concrete Inputs": ["", "0", "0"], "Input type": ["int", "Scalar", "Scalar"], "Input Strides": [[8, 1], [], []], "Input Dims": [[1, 8], [], []], "Ev Idx": 11684 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275839672.866, "dur": 0.601, + "args": { + "External id": 4059918,"Record function id": 0, "Concrete Inputs": ["", "[8]", "[1]", "0"], "Input type": ["int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[8, 1], [], [], []], "Input Dims": [[1, 8], [], [], []], "Ev Idx": 11685 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1336756, + "ts": 1655275839686.396, "dur": 4.574, + "args": { + "External id": 4059919,"Sequence number": 40618590, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["int"], "Input Strides": [[1]], "Input Dims": [[8]], "Ev Idx": 11686 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1336756, + "ts": 1655275839687.827, "dur": 2.946, + "args": { + "External id": 4059920,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["int"], "Input Strides": [[1]], "Input Dims": [[8]], "Ev Idx": 11687 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275839694.525, "dur": 0.536, + "args": { + "External id": 4059921,"Sequence number": 40618590, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "3", "False", "False", ""], "Input type": ["int", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], []], "Input Dims": [[8], [], [], [], []], "Ev Idx": 11688 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::flatten", "pid": 1336756, "tid": 1336756, + "ts": 1655275839698.407, "dur": 0.287, + "args": { + "External id": 4059922,"Sequence number": 40618590, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "0", "-1"], "Input type": ["int", "Scalar", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[8], [], []], "Ev Idx": 11689 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resolve_conj", "pid": 1336756, "tid": 1336756, + "ts": 1655275839700.843, "dur": 0.359, + "args": { + "External id": 4059923,"Sequence number": 40618590, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["int"], "Input Strides": [[1]], "Input Dims": [[8]], "Ev Idx": 11690 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resolve_neg", "pid": 1336756, "tid": 1336756, + "ts": 1655275839701.737, "dur": 0.137, + "args": { + "External id": 4059924,"Sequence number": 40618590, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["int"], "Input Strides": [[1]], "Input Dims": [[8]], "Ev Idx": 11691 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 1336756, "tid": 1336756, + "ts": 1655275839714.432, "dur": 28.911, + "args": { + "External id": 4059925,"Sequence number": 40618590, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "3"], "Input type": ["int", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[8], []], "Ev Idx": 11692 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275839724.068, "dur": 15.119, + "args": { + "External id": 4059926,"Record function id": 0, "Concrete Inputs": ["", "3", "False", "False", ""], "Input type": ["long int", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 11693 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336756, "tid": 1336756, + "ts": 1655275839725.076, "dur": 13.942, + "args": { + "External id": 4059927,"Record function id": 0, "Concrete Inputs": ["", "3", "", "", "", "False", ""], "Input type": ["long int", "Scalar", "", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], []], "Ev Idx": 11694 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275839729.056, "dur": 2.941, + "args": { + "External id": 4059928,"Record function id": 0, "Concrete Inputs": ["[]", "[]", "3", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 11695 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1336756, + "ts": 1655275839733.277, "dur": 5.442, + "args": { + "External id": 4059929,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["int", "long int", "Scalar"], "Input Strides": [[], [], []], "Input Dims": [[], [], []], "Ev Idx": 11696 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::nonzero", "pid": 1336756, "tid": 1336756, + "ts": 1655275839746.892, "dur": 12.307, + "args": { + "External id": 4059930,"Sequence number": 40618590, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["bool"], "Input Strides": [[1]], "Input Dims": [[8]], "Ev Idx": 11697 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655275839748.973, "dur": 0.880, + "args": { + "External id": 4059931,"Record function id": 0, "Concrete Inputs": ["[0]", "4", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 11698 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided_", "pid": 1336756, "tid": 1336756, + "ts": 1655275839755.450, "dur": 2.393, + "args": { + "External id": 4059932,"Record function id": 0, "Concrete Inputs": ["", "[1, 1]", "[1, 1]", ""], "Input type": ["long int", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[1, 1], [], [], []], "Ev Idx": 11699 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select", "pid": 1336756, "tid": 1336756, + "ts": 1655275839763.924, "dur": 4.302, + "args": { + "External id": 4059933,"Sequence number": 40618590, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "0", "0"], "Input type": ["long int", "Scalar", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[1, 1], [], []], "Ev Idx": 11700 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275839766.375, "dur": 0.580, + "args": { + "External id": 4059934,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", "0"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[1, 1], [], [], []], "Ev Idx": 11701 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resolve_conj", "pid": 1336756, "tid": 1336756, + "ts": 1655275839769.568, "dur": 0.081, + "args": { + "External id": 4059935,"Sequence number": 40618590, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["long int"], "Input Strides": [[1]], "Input Dims": [[1]], "Ev Idx": 11702 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resolve_neg", "pid": 1336756, "tid": 1336756, + "ts": 1655275839770.199, "dur": 0.205, + "args": { + "External id": 4059936,"Sequence number": 40618590, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["long int"], "Input Strides": [[1]], "Input Dims": [[1]], "Ev Idx": 11703 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 1336756, "tid": 1336756, + "ts": 1655275839780.210, "dur": 8.975, + "args": { + "External id": 4059937,"Sequence number": 40618590, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "3"], "Input type": ["int", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[8], []], "Ev Idx": 11704 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275839782.145, "dur": 5.511, + "args": { + "External id": 4059938,"Record function id": 0, "Concrete Inputs": ["", "3", "False", "False", ""], "Input type": ["long int", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 11705 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336756, "tid": 1336756, + "ts": 1655275839782.742, "dur": 4.731, + "args": { + "External id": 4059939,"Record function id": 0, "Concrete Inputs": ["", "3", "", "", "", "False", ""], "Input type": ["long int", "Scalar", "", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], []], "Ev Idx": 11706 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275839783.897, "dur": 1.728, + "args": { + "External id": 4059940,"Record function id": 0, "Concrete Inputs": ["[]", "[]", "3", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 11707 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1336756, + "ts": 1655275839786.375, "dur": 0.934, + "args": { + "External id": 4059941,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["int", "long int", "Scalar"], "Input Strides": [[], [], []], "Input Dims": [[], [], []], "Ev Idx": 11708 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::any", "pid": 1336756, "tid": 1336756, + "ts": 1655275839791.561, "dur": 9.008, + "args": { + "External id": 4059942,"Sequence number": 40618590, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["bool"], "Input Strides": [[1]], "Input Dims": [[8]], "Ev Idx": 11709 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275839795.882, "dur": 0.378, + "args": { + "External id": 4059943,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[0]", ""], "Input type": ["bool", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11710 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 1336756, "tid": 1336756, + "ts": 1655275839799.201, "dur": 0.583, + "args": { + "External id": 4059944,"Record function id": 0, "Concrete Inputs": ["", "0."], "Input type": ["bool", "Scalar"], "Input Strides": [[0], []], "Input Dims": [[1], []], "Ev Idx": 11711 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::item", "pid": 1336756, "tid": 1336756, + "ts": 1655275839802.250, "dur": 1.850, + "args": { + "External id": 4059945,"Sequence number": 40618590, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["bool"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 11712 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_local_scalar_dense", "pid": 1336756, "tid": 1336756, + "ts": 1655275839803.184, "dur": 0.827, + "args": { + "External id": 4059946,"Sequence number": 40618590, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["bool"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 11713 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "_c10d_functional::all_reduce", "pid": 1336756, "tid": 1336756, + "ts": 1655275839843.722, "dur": 435.146, + "args": { + "External id": 4059947,"Sequence number": 40618590, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["float", "", ""], "Input Strides": [[1], [], []], "Input Dims": [[1], [], []], "Ev Idx": 11714 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 1336756, "tid": 1336756, + "ts": 1655275839845.847, "dur": 45.548, + "args": { + "External id": 4059948,"Sequence number": 40618590, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[1], []], "Ev Idx": 11715 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336756, "tid": 1336756, + "ts": 1655275839848.713, "dur": 9.543, + "args": { + "External id": 4059949,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "0"], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[1], [], [], [], [], []], "Ev Idx": 11716 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655275839850.475, "dur": 7.346, + "args": { + "External id": 4059950,"Record function id": 0, "Concrete Inputs": ["[1]", "6", "0", "", "", "0"], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 11717 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1336756, + "ts": 1655275839858.953, "dur": 31.922, + "args": { + "External id": 4059951,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[1], [1], []], "Ev Idx": 11718 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::allreduce_", "pid": 1336756, "tid": 1336756, + "ts": 1655275839896.412, "dur": 380.042, + "args": { + "External id": 4059952,"Sequence number": 40618590, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "-1"], "Input type": ["TensorList", "", "", "", "Scalar"], "Input Strides": [[[1]], [], [], [], []], "Input Dims": [[[1]], [], [], [], []], "Ev Idx": 11719 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336756, "tid": 1336756, + "ts": 1655275839922.722, "dur": 347.642, + "args": { + "External id": 4059953,"Record function id": 0, "Collective name": "allreduce", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 3, "Input Strides": [[[1]], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "3", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 1, "Process Group Name": "0", "Input type": ["TensorList", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[[1]], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 11720, "In msg nelems": 1 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:all_reduce", "pid": 1336756, "tid": 1336756, + "ts": 1655275839935.094, "dur": 329.643, + "args": { + "External id": 4059954,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[1]], "Ev Idx": 11721 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::item", "pid": 1336756, "tid": 1336756, + "ts": 1655275840319.466, "dur": 1066.886, + "args": { + "External id": 4059955,"Sequence number": 40618590, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[1]], "Ev Idx": 11722 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_local_scalar_dense", "pid": 1336756, "tid": 1336756, + "ts": 1655275840321.432, "dur": 1064.174, + "args": { + "External id": 4059956,"Sequence number": 40618590, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[1]], "Ev Idx": 11723 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "_c10d_functional::wait_tensor", "pid": 1336756, "tid": 1336756, + "ts": 1655275840378.973, "dur": 27.129, + "args": { + "External id": 4059957,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[1]], "Ev Idx": 11724 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336756, "tid": 1336756, + "ts": 1655275840394.842, "dur": 3.675, + "args": { + "External id": 4059958,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "3", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 11725, "In msg nelems": 0, "Rank": 3, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_local_scalar_dense", "pid": 1336756, "tid": 1336756, + "ts": 1655275840449.327, "dur": 925.004, + "args": { + "External id": 4059959,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[1]], "Ev Idx": 11726 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::permute", "pid": 1336756, "tid": 1336756, + "ts": 1655275841445.918, "dur": 8.646, + "args": { + "External id": 4059960,"Sequence number": 40618590, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[0]"], "Input type": ["int", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[8], []], "Ev Idx": 11727 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275841450.548, "dur": 2.021, + "args": { + "External id": 4059961,"Record function id": 0, "Concrete Inputs": ["", "[8]", "[1]", ""], "Input type": ["int", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[8], [], [], []], "Ev Idx": 11728 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1336756, + "ts": 1655275841458.737, "dur": 6.191, + "args": { + "External id": 4059962,"Sequence number": 40618590, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[-1, 8]"], "Input type": ["int", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[8], []], "Ev Idx": 11729 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655275841460.582, "dur": 4.147, + "args": { + "External id": 4059963,"Sequence number": 40618590, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[-1, 8]"], "Input type": ["int", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[8], []], "Ev Idx": 11730 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unbind", "pid": 1336756, "tid": 1336756, + "ts": 1655275841476.322, "dur": 9.193, + "args": { + "External id": 4059964,"Sequence number": 40618590, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["int", "Scalar"], "Input Strides": [[8, 1], []], "Input Dims": [[1, 8], []], "Ev Idx": 11731 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select", "pid": 1336756, "tid": 1336756, + "ts": 1655275841479.408, "dur": 5.157, + "args": { + "External id": 4059965,"Record function id": 0, "Concrete Inputs": ["", "0", "0"], "Input type": ["int", "Scalar", "Scalar"], "Input Strides": [[8, 1], [], []], "Input Dims": [[1, 8], [], []], "Ev Idx": 11732 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275841483.438, "dur": 0.505, + "args": { + "External id": 4059966,"Record function id": 0, "Concrete Inputs": ["", "[8]", "[1]", "0"], "Input type": ["int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[8, 1], [], [], []], "Input Dims": [[1, 8], [], [], []], "Ev Idx": 11733 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1336756, + "ts": 1655275841496.723, "dur": 4.345, + "args": { + "External id": 4059967,"Sequence number": 40618590, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["int"], "Input Strides": [[1]], "Input Dims": [[8]], "Ev Idx": 11734 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1336756, + "ts": 1655275841498.176, "dur": 2.734, + "args": { + "External id": 4059968,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["int"], "Input Strides": [[1]], "Input Dims": [[8]], "Ev Idx": 11735 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275841504.465, "dur": 0.702, + "args": { + "External id": 4059969,"Sequence number": 40618590, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "3", "False", "False", ""], "Input type": ["int", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], []], "Input Dims": [[8], [], [], [], []], "Ev Idx": 11736 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::flatten", "pid": 1336756, "tid": 1336756, + "ts": 1655275841508.311, "dur": 0.316, + "args": { + "External id": 4059970,"Sequence number": 40618590, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "0", "-1"], "Input type": ["int", "Scalar", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[8], [], []], "Ev Idx": 11737 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resolve_conj", "pid": 1336756, "tid": 1336756, + "ts": 1655275841510.317, "dur": 0.389, + "args": { + "External id": 4059971,"Sequence number": 40618590, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["int"], "Input Strides": [[1]], "Input Dims": [[8]], "Ev Idx": 11738 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resolve_neg", "pid": 1336756, "tid": 1336756, + "ts": 1655275841511.502, "dur": 0.189, + "args": { + "External id": 4059972,"Sequence number": 40618590, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["int"], "Input Strides": [[1]], "Input Dims": [[8]], "Ev Idx": 11739 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 1336756, "tid": 1336756, + "ts": 1655275841525.543, "dur": 25.345, + "args": { + "External id": 4059973,"Sequence number": 40618590, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "3"], "Input type": ["int", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[8], []], "Ev Idx": 11740 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275841533.241, "dur": 13.429, + "args": { + "External id": 4059974,"Record function id": 0, "Concrete Inputs": ["", "3", "False", "False", ""], "Input type": ["long int", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 11741 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336756, "tid": 1336756, + "ts": 1655275841534.313, "dur": 12.139, + "args": { + "External id": 4059975,"Record function id": 0, "Concrete Inputs": ["", "3", "", "", "", "False", ""], "Input type": ["long int", "Scalar", "", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], []], "Ev Idx": 11742 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275841537.942, "dur": 2.132, + "args": { + "External id": 4059976,"Record function id": 0, "Concrete Inputs": ["[]", "[]", "3", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 11743 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1336756, + "ts": 1655275841541.079, "dur": 5.099, + "args": { + "External id": 4059977,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["int", "long int", "Scalar"], "Input Strides": [[], [], []], "Input Dims": [[], [], []], "Ev Idx": 11744 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::nonzero", "pid": 1336756, "tid": 1336756, + "ts": 1655275841554.105, "dur": 13.082, + "args": { + "External id": 4059978,"Sequence number": 40618590, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["bool"], "Input Strides": [[1]], "Input Dims": [[8]], "Ev Idx": 11745 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655275841556.343, "dur": 1.161, + "args": { + "External id": 4059979,"Record function id": 0, "Concrete Inputs": ["[0]", "4", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 11746 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided_", "pid": 1336756, "tid": 1336756, + "ts": 1655275841563.487, "dur": 2.420, + "args": { + "External id": 4059980,"Record function id": 0, "Concrete Inputs": ["", "[1, 1]", "[1, 1]", ""], "Input type": ["long int", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[1, 1], [], [], []], "Ev Idx": 11747 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select", "pid": 1336756, "tid": 1336756, + "ts": 1655275841573.319, "dur": 4.044, + "args": { + "External id": 4059981,"Sequence number": 40618590, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "0", "0"], "Input type": ["long int", "Scalar", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[1, 1], [], []], "Ev Idx": 11748 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275841575.527, "dur": 0.918, + "args": { + "External id": 4059982,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", "0"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[1, 1], [], [], []], "Ev Idx": 11749 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resolve_conj", "pid": 1336756, "tid": 1336756, + "ts": 1655275841578.875, "dur": 0.102, + "args": { + "External id": 4059983,"Sequence number": 40618590, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["long int"], "Input Strides": [[1]], "Input Dims": [[1]], "Ev Idx": 11750 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resolve_neg", "pid": 1336756, "tid": 1336756, + "ts": 1655275841579.497, "dur": 0.235, + "args": { + "External id": 4059984,"Sequence number": 40618590, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["long int"], "Input Strides": [[1]], "Input Dims": [[1]], "Ev Idx": 11751 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 1336756, "tid": 1336756, + "ts": 1655275841587.205, "dur": 8.445, + "args": { + "External id": 4059985,"Sequence number": 40618590, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "3"], "Input type": ["int", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[8], []], "Ev Idx": 11752 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275841589.004, "dur": 4.932, + "args": { + "External id": 4059986,"Record function id": 0, "Concrete Inputs": ["", "3", "False", "False", ""], "Input type": ["long int", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 11753 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336756, "tid": 1336756, + "ts": 1655275841589.648, "dur": 4.097, + "args": { + "External id": 4059987,"Record function id": 0, "Concrete Inputs": ["", "3", "", "", "", "False", ""], "Input type": ["long int", "Scalar", "", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], []], "Ev Idx": 11754 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275841591.374, "dur": 0.942, + "args": { + "External id": 4059988,"Record function id": 0, "Concrete Inputs": ["[]", "[]", "3", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 11755 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1336756, + "ts": 1655275841592.893, "dur": 0.705, + "args": { + "External id": 4059989,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["int", "long int", "Scalar"], "Input Strides": [[], [], []], "Input Dims": [[], [], []], "Ev Idx": 11756 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::any", "pid": 1336756, "tid": 1336756, + "ts": 1655275841597.803, "dur": 8.941, + "args": { + "External id": 4059990,"Sequence number": 40618590, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["bool"], "Input Strides": [[1]], "Input Dims": [[8]], "Ev Idx": 11757 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275841601.794, "dur": 0.590, + "args": { + "External id": 4059991,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[0]", ""], "Input type": ["bool", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11758 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 1336756, "tid": 1336756, + "ts": 1655275841605.322, "dur": 0.599, + "args": { + "External id": 4059992,"Record function id": 0, "Concrete Inputs": ["", "0."], "Input type": ["bool", "Scalar"], "Input Strides": [[0], []], "Input Dims": [[1], []], "Ev Idx": 11759 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::item", "pid": 1336756, "tid": 1336756, + "ts": 1655275841608.602, "dur": 1.536, + "args": { + "External id": 4059993,"Sequence number": 40618590, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["bool"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 11760 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_local_scalar_dense", "pid": 1336756, "tid": 1336756, + "ts": 1655275841609.181, "dur": 0.828, + "args": { + "External id": 4059994,"Sequence number": 40618590, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["bool"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 11761 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "_c10d_functional::all_reduce", "pid": 1336756, "tid": 1336756, + "ts": 1655275841642.625, "dur": 443.692, + "args": { + "External id": 4059995,"Sequence number": 40618590, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["float", "", ""], "Input Strides": [[], [], []], "Input Dims": [[], [], []], "Ev Idx": 11762 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 1336756, "tid": 1336756, + "ts": 1655275841648.383, "dur": 48.186, + "args": { + "External id": 4059996,"Sequence number": 40618591, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11763 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336756, "tid": 1336756, + "ts": 1655275841651.793, "dur": 10.471, + "args": { + "External id": 4059997,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "0"], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 11764 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655275841653.613, "dur": 8.158, + "args": { + "External id": 4059998,"Record function id": 0, "Concrete Inputs": ["[]", "6", "0", "", "", "0"], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 11765 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1336756, + "ts": 1655275841663.070, "dur": 31.010, + "args": { + "External id": 4059999,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[], [], []], "Input Dims": [[], [], []], "Ev Idx": 11766 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::allreduce_", "pid": 1336756, "tid": 1336756, + "ts": 1655275841703.114, "dur": 379.766, + "args": { + "External id": 4060000,"Sequence number": 40618592, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "-1"], "Input type": ["TensorList", "", "", "", "Scalar"], "Input Strides": [[[]], [], [], [], []], "Input Dims": [[[]], [], [], [], []], "Ev Idx": 11767 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336756, "tid": 1336756, + "ts": 1655275841729.482, "dur": 341.382, + "args": { + "External id": 4060001,"Record function id": 0, "Collective name": "allreduce", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 3, "Input Strides": [[[]], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "3", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 1, "Process Group Name": "0", "Input type": ["TensorList", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[[]], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 11768, "In msg nelems": 1 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:all_reduce", "pid": 1336756, "tid": 1336756, + "ts": 1655275841741.864, "dur": 323.527, + "args": { + "External id": 4060002,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 11769 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::item", "pid": 1336756, "tid": 1336756, + "ts": 1655275842126.782, "dur": 1074.895, + "args": { + "External id": 4060003,"Sequence number": 40618593, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 11770 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_local_scalar_dense", "pid": 1336756, "tid": 1336756, + "ts": 1655275842128.833, "dur": 1072.265, + "args": { + "External id": 4060004,"Sequence number": 40618593, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 11771 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "_c10d_functional::wait_tensor", "pid": 1336756, "tid": 1336756, + "ts": 1655275842183.342, "dur": 27.859, + "args": { + "External id": 4060005,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 11772 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336756, "tid": 1336756, + "ts": 1655275842199.486, "dur": 3.935, + "args": { + "External id": 4060006,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "3", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 11773, "In msg nelems": 0, "Rank": 3, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_local_scalar_dense", "pid": 1336756, "tid": 1336756, + "ts": 1655275842234.843, "dur": 955.023, + "args": { + "External id": 4060007,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 11774 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::permute", "pid": 1336756, "tid": 1336756, + "ts": 1655275843249.841, "dur": 7.792, + "args": { + "External id": 4060008,"Sequence number": 40618593, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[0]"], "Input type": ["int", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[8], []], "Ev Idx": 11775 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275843254.140, "dur": 1.865, + "args": { + "External id": 4060009,"Record function id": 0, "Concrete Inputs": ["", "[8]", "[1]", ""], "Input type": ["int", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[8], [], [], []], "Ev Idx": 11776 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1336756, + "ts": 1655275843261.615, "dur": 5.553, + "args": { + "External id": 4060010,"Sequence number": 40618593, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[-1, 8]"], "Input type": ["int", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[8], []], "Ev Idx": 11777 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655275843263.003, "dur": 3.965, + "args": { + "External id": 4060011,"Sequence number": 40618593, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[-1, 8]"], "Input type": ["int", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[8], []], "Ev Idx": 11778 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unbind", "pid": 1336756, "tid": 1336756, + "ts": 1655275843277.826, "dur": 9.025, + "args": { + "External id": 4060012,"Sequence number": 40618593, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["int", "Scalar"], "Input Strides": [[8, 1], []], "Input Dims": [[1, 8], []], "Ev Idx": 11779 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select", "pid": 1336756, "tid": 1336756, + "ts": 1655275843280.812, "dur": 5.136, + "args": { + "External id": 4060013,"Record function id": 0, "Concrete Inputs": ["", "0", "0"], "Input type": ["int", "Scalar", "Scalar"], "Input Strides": [[8, 1], [], []], "Input Dims": [[1, 8], [], []], "Ev Idx": 11780 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275843284.805, "dur": 0.469, + "args": { + "External id": 4060014,"Record function id": 0, "Concrete Inputs": ["", "[8]", "[1]", "0"], "Input type": ["int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[8, 1], [], [], []], "Input Dims": [[1, 8], [], [], []], "Ev Idx": 11781 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1336756, + "ts": 1655275843297.869, "dur": 3.981, + "args": { + "External id": 4060015,"Sequence number": 40618593, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["int"], "Input Strides": [[1]], "Input Dims": [[8]], "Ev Idx": 11782 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1336756, + "ts": 1655275843299.048, "dur": 2.669, + "args": { + "External id": 4060016,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["int"], "Input Strides": [[1]], "Input Dims": [[8]], "Ev Idx": 11783 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275843305.505, "dur": 0.542, + "args": { + "External id": 4060017,"Sequence number": 40618593, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "3", "False", "False", ""], "Input type": ["int", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], []], "Input Dims": [[8], [], [], [], []], "Ev Idx": 11784 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::flatten", "pid": 1336756, "tid": 1336756, + "ts": 1655275843308.988, "dur": 0.281, + "args": { + "External id": 4060018,"Sequence number": 40618593, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "0", "-1"], "Input type": ["int", "Scalar", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[8], [], []], "Ev Idx": 11785 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resolve_conj", "pid": 1336756, "tid": 1336756, + "ts": 1655275843311.213, "dur": 0.491, + "args": { + "External id": 4060019,"Sequence number": 40618593, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["int"], "Input Strides": [[1]], "Input Dims": [[8]], "Ev Idx": 11786 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resolve_neg", "pid": 1336756, "tid": 1336756, + "ts": 1655275843312.229, "dur": 0.144, + "args": { + "External id": 4060020,"Sequence number": 40618593, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["int"], "Input Strides": [[1]], "Input Dims": [[8]], "Ev Idx": 11787 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 1336756, "tid": 1336756, + "ts": 1655275843323.679, "dur": 26.561, + "args": { + "External id": 4060021,"Sequence number": 40618593, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "3"], "Input type": ["int", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[8], []], "Ev Idx": 11788 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275843331.312, "dur": 14.766, + "args": { + "External id": 4060022,"Record function id": 0, "Concrete Inputs": ["", "3", "False", "False", ""], "Input type": ["long int", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 11789 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336756, "tid": 1336756, + "ts": 1655275843332.500, "dur": 13.390, + "args": { + "External id": 4060023,"Record function id": 0, "Concrete Inputs": ["", "3", "", "", "", "False", ""], "Input type": ["long int", "Scalar", "", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], []], "Ev Idx": 11790 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275843336.235, "dur": 2.545, + "args": { + "External id": 4060024,"Record function id": 0, "Concrete Inputs": ["[]", "[]", "3", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 11791 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1336756, + "ts": 1655275843340.320, "dur": 5.270, + "args": { + "External id": 4060025,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["int", "long int", "Scalar"], "Input Strides": [[], [], []], "Input Dims": [[], [], []], "Ev Idx": 11792 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::nonzero", "pid": 1336756, "tid": 1336756, + "ts": 1655275843353.186, "dur": 14.034, + "args": { + "External id": 4060026,"Sequence number": 40618593, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["bool"], "Input Strides": [[1]], "Input Dims": [[8]], "Ev Idx": 11793 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655275843355.049, "dur": 0.944, + "args": { + "External id": 4060027,"Record function id": 0, "Concrete Inputs": ["[0]", "4", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 11794 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided_", "pid": 1336756, "tid": 1336756, + "ts": 1655275843363.363, "dur": 2.625, + "args": { + "External id": 4060028,"Record function id": 0, "Concrete Inputs": ["", "[1, 1]", "[1, 1]", ""], "Input type": ["long int", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[1, 1], [], [], []], "Ev Idx": 11795 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select", "pid": 1336756, "tid": 1336756, + "ts": 1655275843371.776, "dur": 4.070, + "args": { + "External id": 4060029,"Sequence number": 40618593, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "0", "0"], "Input type": ["long int", "Scalar", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[1, 1], [], []], "Ev Idx": 11796 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275843374.287, "dur": 0.610, + "args": { + "External id": 4060030,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", "0"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[1, 1], [], [], []], "Ev Idx": 11797 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resolve_conj", "pid": 1336756, "tid": 1336756, + "ts": 1655275843377.109, "dur": 0.110, + "args": { + "External id": 4060031,"Sequence number": 40618593, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["long int"], "Input Strides": [[1]], "Input Dims": [[1]], "Ev Idx": 11798 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resolve_neg", "pid": 1336756, "tid": 1336756, + "ts": 1655275843377.922, "dur": 0.185, + "args": { + "External id": 4060032,"Sequence number": 40618593, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["long int"], "Input Strides": [[1]], "Input Dims": [[1]], "Ev Idx": 11799 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 1336756, "tid": 1336756, + "ts": 1655275843385.250, "dur": 8.092, + "args": { + "External id": 4060033,"Sequence number": 40618593, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "3"], "Input type": ["int", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[8], []], "Ev Idx": 11800 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275843387.042, "dur": 4.791, + "args": { + "External id": 4060034,"Record function id": 0, "Concrete Inputs": ["", "3", "False", "False", ""], "Input type": ["long int", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 11801 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336756, "tid": 1336756, + "ts": 1655275843387.460, "dur": 4.178, + "args": { + "External id": 4060035,"Record function id": 0, "Concrete Inputs": ["", "3", "", "", "", "False", ""], "Input type": ["long int", "Scalar", "", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], []], "Ev Idx": 11802 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275843388.650, "dur": 1.507, + "args": { + "External id": 4060036,"Record function id": 0, "Concrete Inputs": ["[]", "[]", "3", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 11803 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1336756, + "ts": 1655275843390.771, "dur": 0.716, + "args": { + "External id": 4060037,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["int", "long int", "Scalar"], "Input Strides": [[], [], []], "Input Dims": [[], [], []], "Ev Idx": 11804 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::any", "pid": 1336756, "tid": 1336756, + "ts": 1655275843395.360, "dur": 9.119, + "args": { + "External id": 4060038,"Sequence number": 40618593, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["bool"], "Input Strides": [[1]], "Input Dims": [[8]], "Ev Idx": 11805 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275843399.444, "dur": 0.694, + "args": { + "External id": 4060039,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[0]", ""], "Input type": ["bool", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11806 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 1336756, "tid": 1336756, + "ts": 1655275843402.993, "dur": 0.681, + "args": { + "External id": 4060040,"Record function id": 0, "Concrete Inputs": ["", "0."], "Input type": ["bool", "Scalar"], "Input Strides": [[0], []], "Input Dims": [[1], []], "Ev Idx": 11807 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::item", "pid": 1336756, "tid": 1336756, + "ts": 1655275843408.621, "dur": 1.874, + "args": { + "External id": 4060041,"Sequence number": 40618593, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["bool"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 11808 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_local_scalar_dense", "pid": 1336756, "tid": 1336756, + "ts": 1655275843409.571, "dur": 0.828, + "args": { + "External id": 4060042,"Sequence number": 40618593, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["bool"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 11809 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "_c10d_functional::all_reduce", "pid": 1336756, "tid": 1336756, + "ts": 1655275843460.611, "dur": 390.701, + "args": { + "External id": 4060043,"Sequence number": 40618593, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["float", "", ""], "Input Strides": [[], [], []], "Input Dims": [[], [], []], "Ev Idx": 11810 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 1336756, "tid": 1336756, + "ts": 1655275843464.940, "dur": 49.810, + "args": { + "External id": 4060044,"Sequence number": 40618594, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[], []], "Input Dims": [[], []], "Ev Idx": 11811 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336756, "tid": 1336756, + "ts": 1655275843467.792, "dur": 10.585, + "args": { + "External id": 4060045,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "0"], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 11812 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655275843469.783, "dur": 7.974, + "args": { + "External id": 4060046,"Record function id": 0, "Concrete Inputs": ["[]", "6", "0", "", "", "0"], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 11813 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1336756, + "ts": 1655275843480.647, "dur": 31.664, + "args": { + "External id": 4060047,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[], [], []], "Input Dims": [[], [], []], "Ev Idx": 11814 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::allreduce_", "pid": 1336756, "tid": 1336756, + "ts": 1655275843519.701, "dur": 328.597, + "args": { + "External id": 4060048,"Sequence number": 40618595, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "-1"], "Input type": ["TensorList", "", "", "", "Scalar"], "Input Strides": [[[]], [], [], [], []], "Input Dims": [[[]], [], [], [], []], "Ev Idx": 11815 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336756, "tid": 1336756, + "ts": 1655275843543.479, "dur": 296.512, + "args": { + "External id": 4060049,"Record function id": 0, "Collective name": "allreduce", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 3, "Input Strides": [[[]], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "3", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 1, "Process Group Name": "0", "Input type": ["TensorList", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[[]], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 11816, "In msg nelems": 1 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:all_reduce", "pid": 1336756, "tid": 1336756, + "ts": 1655275843558.676, "dur": 274.894, + "args": { + "External id": 4060050,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 11817 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::item", "pid": 1336756, "tid": 1336756, + "ts": 1655275843886.003, "dur": 993.054, + "args": { + "External id": 4060051,"Sequence number": 40618596, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 11818 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_local_scalar_dense", "pid": 1336756, "tid": 1336756, + "ts": 1655275843888.062, "dur": 990.363, + "args": { + "External id": 4060052,"Sequence number": 40618596, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 11819 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "_c10d_functional::wait_tensor", "pid": 1336756, "tid": 1336756, + "ts": 1655275843940.477, "dur": 24.255, + "args": { + "External id": 4060053,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 11820 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336756, "tid": 1336756, + "ts": 1655275843953.966, "dur": 3.644, + "args": { + "External id": 4060054,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "3", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 11821, "In msg nelems": 0, "Rank": 3, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_local_scalar_dense", "pid": 1336756, "tid": 1336756, + "ts": 1655275844041.649, "dur": 825.708, + "args": { + "External id": 4060055,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 11822 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::permute", "pid": 1336756, "tid": 1336756, + "ts": 1655275844925.701, "dur": 7.744, + "args": { + "External id": 4060056,"Sequence number": 40618596, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[0]"], "Input type": ["int", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[8], []], "Ev Idx": 11823 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275844930.005, "dur": 1.926, + "args": { + "External id": 4060057,"Record function id": 0, "Concrete Inputs": ["", "[8]", "[1]", ""], "Input type": ["int", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[8], [], [], []], "Ev Idx": 11824 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1336756, + "ts": 1655275844937.745, "dur": 5.789, + "args": { + "External id": 4060058,"Sequence number": 40618596, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[-1, 8]"], "Input type": ["int", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[8], []], "Ev Idx": 11825 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655275844939.284, "dur": 4.054, + "args": { + "External id": 4060059,"Sequence number": 40618596, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[-1, 8]"], "Input type": ["int", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[8], []], "Ev Idx": 11826 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unbind", "pid": 1336756, "tid": 1336756, + "ts": 1655275844954.514, "dur": 9.692, + "args": { + "External id": 4060060,"Sequence number": 40618596, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["int", "Scalar"], "Input Strides": [[8, 1], []], "Input Dims": [[1, 8], []], "Ev Idx": 11827 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select", "pid": 1336756, "tid": 1336756, + "ts": 1655275844957.756, "dur": 5.521, + "args": { + "External id": 4060061,"Record function id": 0, "Concrete Inputs": ["", "0", "0"], "Input type": ["int", "Scalar", "Scalar"], "Input Strides": [[8, 1], [], []], "Input Dims": [[1, 8], [], []], "Ev Idx": 11828 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275844961.804, "dur": 0.787, + "args": { + "External id": 4060062,"Record function id": 0, "Concrete Inputs": ["", "[8]", "[1]", "0"], "Input type": ["int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[8, 1], [], [], []], "Input Dims": [[1, 8], [], [], []], "Ev Idx": 11829 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1336756, + "ts": 1655275844975.291, "dur": 4.127, + "args": { + "External id": 4060063,"Sequence number": 40618596, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["int"], "Input Strides": [[1]], "Input Dims": [[8]], "Ev Idx": 11830 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1336756, + "ts": 1655275844976.492, "dur": 2.810, + "args": { + "External id": 4060064,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["int"], "Input Strides": [[1]], "Input Dims": [[8]], "Ev Idx": 11831 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275845012.310, "dur": 0.603, + "args": { + "External id": 4060065,"Sequence number": 40618596, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "3", "False", "False", ""], "Input type": ["int", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], []], "Input Dims": [[8], [], [], [], []], "Ev Idx": 11832 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::flatten", "pid": 1336756, "tid": 1336756, + "ts": 1655275845017.040, "dur": 0.464, + "args": { + "External id": 4060066,"Sequence number": 40618596, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "0", "-1"], "Input type": ["int", "Scalar", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[8], [], []], "Ev Idx": 11833 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resolve_conj", "pid": 1336756, "tid": 1336756, + "ts": 1655275845019.386, "dur": 0.410, + "args": { + "External id": 4060067,"Sequence number": 40618596, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["int"], "Input Strides": [[1]], "Input Dims": [[8]], "Ev Idx": 11834 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resolve_neg", "pid": 1336756, "tid": 1336756, + "ts": 1655275845020.577, "dur": 0.143, + "args": { + "External id": 4060068,"Sequence number": 40618596, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["int"], "Input Strides": [[1]], "Input Dims": [[8]], "Ev Idx": 11835 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 1336756, "tid": 1336756, + "ts": 1655275845033.670, "dur": 27.863, + "args": { + "External id": 4060069,"Sequence number": 40618596, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "3"], "Input type": ["int", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[8], []], "Ev Idx": 11836 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275845041.798, "dur": 15.168, + "args": { + "External id": 4060070,"Record function id": 0, "Concrete Inputs": ["", "3", "False", "False", ""], "Input type": ["long int", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 11837 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336756, "tid": 1336756, + "ts": 1655275845042.973, "dur": 13.773, + "args": { + "External id": 4060071,"Record function id": 0, "Concrete Inputs": ["", "3", "", "", "", "False", ""], "Input type": ["long int", "Scalar", "", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], []], "Ev Idx": 11838 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275845046.697, "dur": 2.607, + "args": { + "External id": 4060072,"Record function id": 0, "Concrete Inputs": ["[]", "[]", "3", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 11839 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1336756, + "ts": 1655275845050.906, "dur": 5.531, + "args": { + "External id": 4060073,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["int", "long int", "Scalar"], "Input Strides": [[], [], []], "Input Dims": [[], [], []], "Ev Idx": 11840 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::nonzero", "pid": 1336756, "tid": 1336756, + "ts": 1655275845064.528, "dur": 14.476, + "args": { + "External id": 4060074,"Sequence number": 40618596, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["bool"], "Input Strides": [[1]], "Input Dims": [[8]], "Ev Idx": 11841 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655275845066.678, "dur": 0.970, + "args": { + "External id": 4060075,"Record function id": 0, "Concrete Inputs": ["[0]", "4", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 11842 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided_", "pid": 1336756, "tid": 1336756, + "ts": 1655275845075.059, "dur": 2.656, + "args": { + "External id": 4060076,"Record function id": 0, "Concrete Inputs": ["", "[1, 1]", "[1, 1]", ""], "Input type": ["long int", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[1, 1], [], [], []], "Ev Idx": 11843 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select", "pid": 1336756, "tid": 1336756, + "ts": 1655275845083.443, "dur": 4.794, + "args": { + "External id": 4060077,"Sequence number": 40618596, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "0", "0"], "Input type": ["long int", "Scalar", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[1, 1], [], []], "Ev Idx": 11844 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275845086.287, "dur": 0.923, + "args": { + "External id": 4060078,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", "0"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[1, 1], [], [], []], "Ev Idx": 11845 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resolve_conj", "pid": 1336756, "tid": 1336756, + "ts": 1655275845089.668, "dur": 0.096, + "args": { + "External id": 4060079,"Sequence number": 40618596, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["long int"], "Input Strides": [[1]], "Input Dims": [[1]], "Ev Idx": 11846 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resolve_neg", "pid": 1336756, "tid": 1336756, + "ts": 1655275845090.128, "dur": 0.189, + "args": { + "External id": 4060080,"Sequence number": 40618596, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["long int"], "Input Strides": [[1]], "Input Dims": [[1]], "Ev Idx": 11847 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 1336756, "tid": 1336756, + "ts": 1655275845098.202, "dur": 8.833, + "args": { + "External id": 4060081,"Sequence number": 40618596, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "3"], "Input type": ["int", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[8], []], "Ev Idx": 11848 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275845100.119, "dur": 5.289, + "args": { + "External id": 4060082,"Record function id": 0, "Concrete Inputs": ["", "3", "False", "False", ""], "Input type": ["long int", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 11849 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336756, "tid": 1336756, + "ts": 1655275845100.636, "dur": 4.602, + "args": { + "External id": 4060083,"Record function id": 0, "Concrete Inputs": ["", "3", "", "", "", "False", ""], "Input type": ["long int", "Scalar", "", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], []], "Ev Idx": 11850 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275845102.066, "dur": 1.529, + "args": { + "External id": 4060084,"Record function id": 0, "Concrete Inputs": ["[]", "[]", "3", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 11851 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1336756, + "ts": 1655275845104.306, "dur": 0.771, + "args": { + "External id": 4060085,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["int", "long int", "Scalar"], "Input Strides": [[], [], []], "Input Dims": [[], [], []], "Ev Idx": 11852 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::any", "pid": 1336756, "tid": 1336756, + "ts": 1655275845109.340, "dur": 10.699, + "args": { + "External id": 4060086,"Sequence number": 40618596, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["bool"], "Input Strides": [[1]], "Input Dims": [[8]], "Ev Idx": 11853 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275845113.364, "dur": 0.562, + "args": { + "External id": 4060087,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[0]", ""], "Input type": ["bool", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11854 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 1336756, "tid": 1336756, + "ts": 1655275845118.545, "dur": 0.687, + "args": { + "External id": 4060088,"Record function id": 0, "Concrete Inputs": ["", "0."], "Input type": ["bool", "Scalar"], "Input Strides": [[0], []], "Input Dims": [[1], []], "Ev Idx": 11855 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::item", "pid": 1336756, "tid": 1336756, + "ts": 1655275845121.739, "dur": 1.658, + "args": { + "External id": 4060089,"Sequence number": 40618596, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["bool"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 11856 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_local_scalar_dense", "pid": 1336756, "tid": 1336756, + "ts": 1655275845122.499, "dur": 0.818, + "args": { + "External id": 4060090,"Sequence number": 40618596, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["bool"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 11857 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "_c10d_functional::all_reduce", "pid": 1336756, "tid": 1336756, + "ts": 1655275845155.310, "dur": 429.468, + "args": { + "External id": 4060091,"Sequence number": 40618596, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["float", "", ""], "Input Strides": [[1], [], []], "Input Dims": [[1], [], []], "Ev Idx": 11858 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 1336756, "tid": 1336756, + "ts": 1655275845159.515, "dur": 52.932, + "args": { + "External id": 4060092,"Sequence number": 40618597, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[1], []], "Ev Idx": 11859 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336756, "tid": 1336756, + "ts": 1655275845162.662, "dur": 14.203, + "args": { + "External id": 4060093,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "0"], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[1], [], [], [], [], []], "Ev Idx": 11860 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655275845168.237, "dur": 8.037, + "args": { + "External id": 4060094,"Record function id": 0, "Concrete Inputs": ["[1]", "6", "0", "", "", "0"], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 11861 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1336756, + "ts": 1655275845177.760, "dur": 32.330, + "args": { + "External id": 4060095,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[1], [1], []], "Ev Idx": 11862 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::allreduce_", "pid": 1336756, "tid": 1336756, + "ts": 1655275845219.397, "dur": 361.950, + "args": { + "External id": 4060096,"Sequence number": 40618598, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "-1"], "Input type": ["TensorList", "", "", "", "Scalar"], "Input Strides": [[[1]], [], [], [], []], "Input Dims": [[[1]], [], [], [], []], "Ev Idx": 11863 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336756, "tid": 1336756, + "ts": 1655275845244.761, "dur": 327.279, + "args": { + "External id": 4060097,"Record function id": 0, "Collective name": "allreduce", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 3, "Input Strides": [[[1]], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "3", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 1, "Process Group Name": "0", "Input type": ["TensorList", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[[1]], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 11864, "In msg nelems": 1 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:all_reduce", "pid": 1336756, "tid": 1336756, + "ts": 1655275845261.047, "dur": 305.457, + "args": { + "External id": 4060098,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[1]], "Ev Idx": 11865 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::item", "pid": 1336756, "tid": 1336756, + "ts": 1655275845626.613, "dur": 996.658, + "args": { + "External id": 4060099,"Sequence number": 40618599, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[1]], "Ev Idx": 11866 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_local_scalar_dense", "pid": 1336756, "tid": 1336756, + "ts": 1655275845628.553, "dur": 994.059, + "args": { + "External id": 4060100,"Sequence number": 40618599, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[1]], "Ev Idx": 11867 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "_c10d_functional::wait_tensor", "pid": 1336756, "tid": 1336756, + "ts": 1655275845687.213, "dur": 27.102, + "args": { + "External id": 4060101,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[1]], "Ev Idx": 11868 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336756, "tid": 1336756, + "ts": 1655275845703.090, "dur": 3.670, + "args": { + "External id": 4060102,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "3", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 11869, "In msg nelems": 0, "Rank": 3, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_local_scalar_dense", "pid": 1336756, "tid": 1336756, + "ts": 1655275845740.272, "dur": 871.067, + "args": { + "External id": 4060103,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[1]], "Ev Idx": 11870 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::permute", "pid": 1336756, "tid": 1336756, + "ts": 1655275846670.430, "dur": 7.939, + "args": { + "External id": 4060104,"Sequence number": 40618599, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[0]"], "Input type": ["int", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[8], []], "Ev Idx": 11871 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275846674.843, "dur": 1.988, + "args": { + "External id": 4060105,"Record function id": 0, "Concrete Inputs": ["", "[8]", "[1]", ""], "Input type": ["int", "ScalarList", "ScalarList", ""], "Input Strides": [[1], [], [], []], "Input Dims": [[8], [], [], []], "Ev Idx": 11872 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1336756, + "ts": 1655275846682.529, "dur": 6.508, + "args": { + "External id": 4060106,"Sequence number": 40618599, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[-1, 8]"], "Input type": ["int", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[8], []], "Ev Idx": 11873 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1655275846684.235, "dur": 4.611, + "args": { + "External id": 4060107,"Sequence number": 40618599, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "[-1, 8]"], "Input type": ["int", "ScalarList"], "Input Strides": [[1], []], "Input Dims": [[8], []], "Ev Idx": 11874 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::unbind", "pid": 1336756, "tid": 1336756, + "ts": 1655275846699.670, "dur": 9.763, + "args": { + "External id": 4060108,"Sequence number": 40618599, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["int", "Scalar"], "Input Strides": [[8, 1], []], "Input Dims": [[1, 8], []], "Ev Idx": 11875 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select", "pid": 1336756, "tid": 1336756, + "ts": 1655275846702.795, "dur": 5.625, + "args": { + "External id": 4060109,"Record function id": 0, "Concrete Inputs": ["", "0", "0"], "Input type": ["int", "Scalar", "Scalar"], "Input Strides": [[8, 1], [], []], "Input Dims": [[1, 8], [], []], "Ev Idx": 11876 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275846706.881, "dur": 0.881, + "args": { + "External id": 4060110,"Record function id": 0, "Concrete Inputs": ["", "[8]", "[1]", "0"], "Input type": ["int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[8, 1], [], [], []], "Input Dims": [[1, 8], [], [], []], "Ev Idx": 11877 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::detach", "pid": 1336756, "tid": 1336756, + "ts": 1655275846720.476, "dur": 4.050, + "args": { + "External id": 4060111,"Sequence number": 40618599, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["int"], "Input Strides": [[1]], "Input Dims": [[8]], "Ev Idx": 11878 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "detach", "pid": 1336756, "tid": 1336756, + "ts": 1655275846721.750, "dur": 2.607, + "args": { + "External id": 4060112,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["int"], "Input Strides": [[1]], "Input Dims": [[8]], "Ev Idx": 11879 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275846727.674, "dur": 0.611, + "args": { + "External id": 4060113,"Sequence number": 40618599, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "3", "False", "False", ""], "Input type": ["int", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[1], [], [], [], []], "Input Dims": [[8], [], [], [], []], "Ev Idx": 11880 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::flatten", "pid": 1336756, "tid": 1336756, + "ts": 1655275846730.973, "dur": 0.384, + "args": { + "External id": 4060114,"Sequence number": 40618599, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "0", "-1"], "Input type": ["int", "Scalar", "Scalar"], "Input Strides": [[1], [], []], "Input Dims": [[8], [], []], "Ev Idx": 11881 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resolve_conj", "pid": 1336756, "tid": 1336756, + "ts": 1655275846733.353, "dur": 0.348, + "args": { + "External id": 4060115,"Sequence number": 40618599, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["int"], "Input Strides": [[1]], "Input Dims": [[8]], "Ev Idx": 11882 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resolve_neg", "pid": 1336756, "tid": 1336756, + "ts": 1655275846734.246, "dur": 0.208, + "args": { + "External id": 4060116,"Sequence number": 40618599, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["int"], "Input Strides": [[1]], "Input Dims": [[8]], "Ev Idx": 11883 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 1336756, "tid": 1336756, + "ts": 1655275846746.125, "dur": 27.075, + "args": { + "External id": 4060117,"Sequence number": 40618599, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "3"], "Input type": ["int", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[8], []], "Ev Idx": 11884 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275846753.792, "dur": 14.825, + "args": { + "External id": 4060118,"Record function id": 0, "Concrete Inputs": ["", "3", "False", "False", ""], "Input type": ["long int", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 11885 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336756, "tid": 1336756, + "ts": 1655275846755.016, "dur": 13.423, + "args": { + "External id": 4060119,"Record function id": 0, "Concrete Inputs": ["", "3", "", "", "", "False", ""], "Input type": ["long int", "Scalar", "", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], []], "Ev Idx": 11886 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275846758.600, "dur": 2.680, + "args": { + "External id": 4060120,"Record function id": 0, "Concrete Inputs": ["[]", "[]", "3", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 11887 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1336756, + "ts": 1655275846762.608, "dur": 5.563, + "args": { + "External id": 4060121,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["int", "long int", "Scalar"], "Input Strides": [[], [], []], "Input Dims": [[], [], []], "Ev Idx": 11888 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::nonzero", "pid": 1336756, "tid": 1336756, + "ts": 1655275846776.081, "dur": 13.894, + "args": { + "External id": 4060122,"Sequence number": 40618599, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["bool"], "Input Strides": [[1]], "Input Dims": [[8]], "Ev Idx": 11889 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655275846780.179, "dur": 0.931, + "args": { + "External id": 4060123,"Record function id": 0, "Concrete Inputs": ["[0]", "4", "0", "", "", ""], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", ""], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 11890 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided_", "pid": 1336756, "tid": 1336756, + "ts": 1655275846786.357, "dur": 2.311, + "args": { + "External id": 4060124,"Record function id": 0, "Concrete Inputs": ["", "[1, 1]", "[1, 1]", ""], "Input type": ["long int", "ScalarList", "ScalarList", ""], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[1, 1], [], [], []], "Ev Idx": 11891 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select", "pid": 1336756, "tid": 1336756, + "ts": 1655275846794.177, "dur": 4.026, + "args": { + "External id": 4060125,"Sequence number": 40618599, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "0", "0"], "Input type": ["long int", "Scalar", "Scalar"], "Input Strides": [[1, 1], [], []], "Input Dims": [[1, 1], [], []], "Ev Idx": 11892 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275846796.700, "dur": 0.589, + "args": { + "External id": 4060126,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[1]", "0"], "Input type": ["long int", "ScalarList", "ScalarList", "Scalar"], "Input Strides": [[1, 1], [], [], []], "Input Dims": [[1, 1], [], [], []], "Ev Idx": 11893 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resolve_conj", "pid": 1336756, "tid": 1336756, + "ts": 1655275846799.755, "dur": 0.220, + "args": { + "External id": 4060127,"Sequence number": 40618599, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["long int"], "Input Strides": [[1]], "Input Dims": [[1]], "Ev Idx": 11894 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::resolve_neg", "pid": 1336756, "tid": 1336756, + "ts": 1655275846800.385, "dur": 0.164, + "args": { + "External id": 4060128,"Sequence number": 40618599, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["long int"], "Input Strides": [[1]], "Input Dims": [[1]], "Ev Idx": 11895 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::eq", "pid": 1336756, "tid": 1336756, + "ts": 1655275846807.730, "dur": 8.100, + "args": { + "External id": 4060129,"Sequence number": 40618599, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "3"], "Input type": ["int", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[8], []], "Ev Idx": 11896 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::to", "pid": 1336756, "tid": 1336756, + "ts": 1655275846809.570, "dur": 4.708, + "args": { + "External id": 4060130,"Record function id": 0, "Concrete Inputs": ["", "3", "False", "False", ""], "Input type": ["long int", "Scalar", "Scalar", "Scalar", ""], "Input Strides": [[], [], [], [], []], "Input Dims": [[], [], [], [], []], "Ev Idx": 11897 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_to_copy", "pid": 1336756, "tid": 1336756, + "ts": 1655275846810.143, "dur": 3.978, + "args": { + "External id": 4060131,"Record function id": 0, "Concrete Inputs": ["", "3", "", "", "", "False", ""], "Input type": ["long int", "Scalar", "", "", "", "Scalar", ""], "Input Strides": [[], [], [], [], [], [], []], "Input Dims": [[], [], [], [], [], [], []], "Ev Idx": 11898 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275846811.492, "dur": 1.026, + "args": { + "External id": 4060132,"Record function id": 0, "Concrete Inputs": ["[]", "[]", "3", "0", "", "False"], "Input type": ["ScalarList", "ScalarList", "Scalar", "Scalar", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 11899 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1336756, + "ts": 1655275846813.194, "dur": 0.781, + "args": { + "External id": 4060133,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["int", "long int", "Scalar"], "Input Strides": [[], [], []], "Input Dims": [[], [], []], "Ev Idx": 11900 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::any", "pid": 1336756, "tid": 1336756, + "ts": 1655275846819.591, "dur": 9.251, + "args": { + "External id": 4060134,"Sequence number": 40618599, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["bool"], "Input Strides": [[1]], "Input Dims": [[8]], "Ev Idx": 11901 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1655275846823.834, "dur": 0.423, + "args": { + "External id": 4060135,"Record function id": 0, "Concrete Inputs": ["", "[1]", "[0]", ""], "Input type": ["bool", "ScalarList", "ScalarList", ""], "Input Strides": [[], [], [], []], "Input Dims": [[], [], [], []], "Ev Idx": 11902 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::fill_", "pid": 1336756, "tid": 1336756, + "ts": 1655275846827.391, "dur": 0.619, + "args": { + "External id": 4060136,"Record function id": 0, "Concrete Inputs": ["", "0."], "Input type": ["bool", "Scalar"], "Input Strides": [[0], []], "Input Dims": [[1], []], "Ev Idx": 11903 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::item", "pid": 1336756, "tid": 1336756, + "ts": 1655275846830.853, "dur": 1.668, + "args": { + "External id": 4060137,"Sequence number": 40618599, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["bool"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 11904 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_local_scalar_dense", "pid": 1336756, "tid": 1336756, + "ts": 1655275846831.480, "dur": 0.968, + "args": { + "External id": 4060138,"Sequence number": 40618599, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["bool"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 11905 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "_c10d_functional::all_reduce", "pid": 1336756, "tid": 1336756, + "ts": 1655275846865.066, "dur": 448.676, + "args": { + "External id": 4060139,"Sequence number": 40618599, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", ""], "Input type": ["float", "", ""], "Input Strides": [[1], [], []], "Input Dims": [[1], [], []], "Ev Idx": 11906 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 1336756, "tid": 1336756, + "ts": 1655275846868.776, "dur": 48.853, + "args": { + "External id": 4060140,"Sequence number": 40618600, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "0"], "Input type": ["float", "Scalar"], "Input Strides": [[1], []], "Input Dims": [[1], []], "Ev Idx": 11907 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336756, "tid": 1336756, + "ts": 1655275846873.477, "dur": 9.433, + "args": { + "External id": 4060141,"Record function id": 0, "Concrete Inputs": ["", "6", "0", "", "", "0"], "Input type": ["float", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[1], [], [], [], [], []], "Input Dims": [[1], [], [], [], [], []], "Ev Idx": 11908 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1655275846875.241, "dur": 7.115, + "args": { + "External id": 4060142,"Record function id": 0, "Concrete Inputs": ["[1]", "6", "0", "", "", "0"], "Input type": ["ScalarList", "Scalar", "Scalar", "", "", "Scalar"], "Input Strides": [[], [], [], [], [], []], "Input Dims": [[], [], [], [], [], []], "Ev Idx": 11909 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::copy_", "pid": 1336756, "tid": 1336756, + "ts": 1655275846883.877, "dur": 31.473, + "args": { + "External id": 4060143,"Record function id": 0, "Concrete Inputs": ["", "", "False"], "Input type": ["float", "float", "Scalar"], "Input Strides": [[1], [1], []], "Input Dims": [[1], [1], []], "Ev Idx": 11910 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "c10d::allreduce_", "pid": 1336756, "tid": 1336756, + "ts": 1655275846922.899, "dur": 387.770, + "args": { + "External id": 4060144,"Sequence number": 40618601, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": ["", "", "", "", "-1"], "Input type": ["TensorList", "", "", "", "Scalar"], "Input Strides": [[[1]], [], [], [], []], "Input Dims": [[[1]], [], [], [], []], "Ev Idx": 11911 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336756, "tid": 1336756, + "ts": 1655275846948.011, "dur": 353.301, + "args": { + "External id": 4060145,"Record function id": 0, "Collective name": "allreduce", "Process Group Description": "default_pg", "dtype": "Float", "Rank": 3, "Input Strides": [[[1]], [], [], [], [], [], [], [], [], []], "Concrete Inputs": ["", "", "", "3", "", "[]", "[]", "0", "1", "8"], "Out msg nelems": 1, "Process Group Name": "0", "Input type": ["TensorList", "", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Global rank stride": 1, "Out split size": "[]", "In split size": "[]", "Process Group Ranks": "[0, 1, 2, 3, 4, 5, 6, 7]", "Group size": 8, "Input Dims": [[[1]], [], [], [], [], [], [], [], [], []], "Global rank start": 0, "Ev Idx": 11912, "In msg nelems": 1 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "nccl:all_reduce", "pid": 1336756, "tid": 1336756, + "ts": 1655275846960.673, "dur": 335.573, + "args": { + "External id": 4060146,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[1]], "Ev Idx": 11913 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::item", "pid": 1336756, "tid": 1336756, + "ts": 1655275847354.234, "dur": 1273.806, + "args": { + "External id": 4060147,"Sequence number": 40618602, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[1]], "Ev Idx": 11914 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_local_scalar_dense", "pid": 1336756, "tid": 1336756, + "ts": 1655275847356.074, "dur": 1271.448, + "args": { + "External id": 4060148,"Sequence number": 40618602, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[1]], "Ev Idx": 11915 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "_c10d_functional::wait_tensor", "pid": 1336756, "tid": 1336756, + "ts": 1655275847412.394, "dur": 50.038, + "args": { + "External id": 4060149,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[1]], "Ev Idx": 11916 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "record_param_comms", "pid": 1336756, "tid": 1336756, + "ts": 1655275847448.949, "dur": 5.005, + "args": { + "External id": 4060150,"Record function id": 0, "Collective name": "wait", "Process Group Description": "default_pg", "dtype": "Byte", "Input Dims": [[], [], [], [], [], [], [], [], []], "Input Strides": [[], [], [], [], [], [], [], [], []], "Input type": ["", "", "Scalar", "", "ScalarList", "ScalarList", "Scalar", "Scalar", "Scalar"], "Concrete Inputs": ["", "", "3", "", "[]", "[]", "-1", "-1", "1"], "Out msg nelems": 0, "Process Group Name": "0", "Process Group Ranks": "[]", "Group size": 1, "Ev Idx": 11917, "In msg nelems": 0, "Rank": 3, "In split size": "[]", "Out split size": "[]" + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_local_scalar_dense", "pid": 1336756, "tid": 1336756, + "ts": 1655275847489.756, "dur": 1126.275, + "args": { + "External id": 4060151,"Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[1]], "Input Dims": [[1]], "Ev Idx": 11918 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::item", "pid": 1336756, "tid": 1336756, + "ts": 1655275848671.001, "dur": 35.001, + "args": { + "External id": 4060152,"Sequence number": 40618602, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 11919 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_local_scalar_dense", "pid": 1336756, "tid": 1336756, + "ts": 1655275848672.209, "dur": 33.513, + "args": { + "External id": 4060153,"Sequence number": 40618602, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 11920 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::item", "pid": 1336756, "tid": 1336756, + "ts": 1655275849149.443, "dur": 44.404, + "args": { + "External id": 4060154,"Sequence number": 40618602, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 11921 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_local_scalar_dense", "pid": 1336756, "tid": 1336756, + "ts": 1655275849150.526, "dur": 42.641, + "args": { + "External id": 4060155,"Sequence number": 40618602, "Fwd thread id": 0, "Record function id": 0, "Concrete Inputs": [""], "Input type": ["float"], "Input Strides": [[]], "Input Dims": [[]], "Ev Idx": 11922 + } + }, + { + "name": "process_name", "ph": "M", "ts": 1655273725348.487, "pid": 1336756, "tid": 0, + "args": { + "name": "python3.12" + } + }, + { + "name": "process_labels", "ph": "M", "ts": 1655273725348.487, "pid": 1336756, "tid": 0, + "args": { + "labels": "CPU" + } + }, + { + "name": "process_sort_index", "ph": "M", "ts": 1655273725348.487, "pid": 1336756, "tid": 0, + "args": { + "sort_index": 1336756 + } + }, + { + "name": "thread_name", "ph": "M", "ts": 1655273725348.487, "pid": 1336756, "tid": 1381189, + "args": { + "name": "thread 1381189 (pt_autograd_3)" + } + }, + { + "name": "thread_sort_index", "ph": "M", "ts": 1655273725348.487, "pid": 1336756, "tid": 1381189, + "args": { + "sort_index": 1381189 + } + }, + { + "name": "thread_name", "ph": "M", "ts": 1655273725348.487, "pid": 1336756, "tid": 1381189, + "args": { + "name": "thread 1381189 (python3.12)" + } + }, + { + "name": "thread_sort_index", "ph": "M", "ts": 1655273725348.487, "pid": 1336756, "tid": 1381189, + "args": { + "sort_index": 1381189 + } + }, + { + "name": "thread_name", "ph": "M", "ts": 1655273725348.487, "pid": 1336756, "tid": 1336756, + "args": { + "name": "thread 1336756 (python3.12)" + } + }, + { + "name": "thread_sort_index", "ph": "M", "ts": 1655273725348.487, "pid": 1336756, "tid": 1336756, + "args": { + "sort_index": 1336756 + } + }, + { + "ph": "X", "cat": "Trace", "ts": 1655273725279.835, "dur": 2124183.664, + "pid": "Spans", "tid": "PyTorch Profiler", + "name": "PyTorch Profiler (0)", + "args": { + "Op count": 0 + } + }, + { + "name": "process_sort_index", "ph": "M", "ts": 1655273725279.835, + "pid": "Spans", "tid": 0, + "args": { + "sort_index": 536870912 + } + }, + { + "name": "Iteration Start: PyTorch Profiler", "ph": "i", "s": "g", + "pid": "Traces", "tid": "Trace PyTorch Profiler", "ts": 1655273725279.835 + }, + { + "name": "Record Window End", "ph": "i", "s": "g", + "pid": "", "tid": "", "ts": 1655275910138.246 + } + ], + "traceName": "exp/mtp.1B.batch16.seqlen4096.context4096.warmup2000.update1.steps200000.lr2e-4.cosine/profile_trace/iteration_168960/rank3_trace.json", + "displayTimeUnit": "ms", + "baseTimeNanoseconds": 1751410836000000000 +} \ No newline at end of file