diff --git "a/profile_trace/iteration_155136/rank3_trace.json" "b/profile_trace/iteration_155136/rank3_trace.json" new file mode 100644--- /dev/null +++ "b/profile_trace/iteration_155136/rank3_trace.json" @@ -0,0 +1,83385 @@ + +{ + "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": "B26BC4AE063A406D91A388BAB107F421", + "traceEvents": [ + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: DivBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1625851779322.118, "dur": 122.209, + "args": { + "External id": 3720193,"Record function id": 0, "Sequence number": 37295302, "Fwd thread id": 1, "Ev Idx": 0 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "DivBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1625851779343.996, "dur": 90.523, + "args": { + "External id": 3720194,"Sequence number": 37295302, "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": 1625851779343.996, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::div", "pid": 1336756, "tid": 1381189, + "ts": 1625851779351.873, "dur": 80.451, + "args": { + "External id": 3720195,"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": 1625851779457.597, "dur": 213.157, + "args": { + "External id": 3720196,"Record function id": 0, "Ev Idx": 3 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward", "pid": 1336756, "tid": 1381189, + "ts": 1625851779512.190, "dur": 86.405, + "args": { + "External id": 3720197,"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": 1625851779542.349, "dur": 45.023, + "args": { + "External id": 3720198,"Record function id": 0, "Ev Idx": 5 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "AddBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1625851779603.231, "dur": 1.381, + "args": { + "External id": 3720199,"Sequence number": 37295301, "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": 1625851779603.231, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 1336756, "tid": 1381189, + "ts": 1625851779608.708, "dur": 57.407, + "args": { + "External id": 3720200,"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": 1625851779619.309, "dur": 46.298, + "args": { + "External id": 3720201,"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": 1625851779628.978, "dur": 3.775, + "args": { + "External id": 3720202,"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": 1625851779698.266, "dur": 36120.576, + "args": { + "External id": 3720203,"Record function id": 0, "Sequence number": 37295299, "Fwd thread id": 1, "Ev Idx": 10 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "FusedLinearCrossEntropyFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1625851779701.031, "dur": 36108.544, + "args": { + "External id": 3720204,"Sequence number": 37295299, "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": 1625851779701.031, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1625851779742.510, "dur": 6.438, + "args": { + "External id": 3720205,"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": 1625851779754.682, "dur": 35945.868, + "args": { + "External id": 3720206,"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": 1625851779756.654, "dur": 35943.544, + "args": { + "External id": 3720207,"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": 1625851779762.451, "dur": 7.065, + "args": { + "External id": 3720208,"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": 1625851779771.035, "dur": 35928.066, + "args": { + "External id": 3720209,"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": 1625851815705.088, "dur": 0.454, + "args": { + "External id": 3720210,"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": 1625851815708.097, "dur": 2.988, + "args": { + "External id": 3720211,"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": 1625851815709.865, "dur": 0.949, + "args": { + "External id": 3720212,"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": 1625851815717.435, "dur": 31.697, + "args": { + "External id": 3720213,"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": 1625851815757.405, "dur": 43.377, + "args": { + "External id": 3720214,"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": 1625851815759.186, "dur": 41.398, + "args": { + "External id": 3720215,"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": 1625851815760.571, "dur": 39.736, + "args": { + "External id": 3720216,"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": 1625851815831.407, "dur": 19.181, + "args": { + "External id": 3720217,"Record function id": 0, "Sequence number": 37295298, "Fwd thread id": 1, "Ev Idx": 24 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1625851815833.115, "dur": 15.125, + "args": { + "External id": 3720218,"Sequence number": 37295298, "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": 1625851815833.115, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1381189, + "ts": 1625851815836.276, "dur": 11.735, + "args": { + "External id": 3720219,"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": 1625851815840.524, "dur": 7.323, + "args": { + "External id": 3720220,"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": 1625851815856.751, "dur": 95.448, + "args": { + "External id": 3720221,"Record function id": 0, "Sequence number": 37295297, "Fwd thread id": 1, "Ev Idx": 28 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SliceBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1625851815857.691, "dur": 87.231, + "args": { + "External id": 3720222,"Sequence number": 37295297, "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": 1625851815857.691, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 1336756, "tid": 1381189, + "ts": 1625851815861.047, "dur": 83.418, + "args": { + "External id": 3720223,"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": 1625851815866.429, "dur": 32.034, + "args": { + "External id": 3720224,"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": 1625851815870.619, "dur": 4.466, + "args": { + "External id": 3720225,"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": 1625851815876.668, "dur": 21.470, + "args": { + "External id": 3720226,"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": 1625851815879.306, "dur": 18.471, + "args": { + "External id": 3720227,"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": 1625851815903.755, "dur": 4.524, + "args": { + "External id": 3720228,"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": 1625851815906.268, "dur": 1.653, + "args": { + "External id": 3720229,"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": 1625851815909.435, "dur": 34.073, + "args": { + "External id": 3720230,"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": 1625851815956.598, "dur": 97.955, + "args": { + "External id": 3720231,"Record function id": 0, "Sequence number": 37295296, "Fwd thread id": 1, "Ev Idx": 38 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SelectBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1625851815957.930, "dur": 92.215, + "args": { + "External id": 3720232,"Sequence number": 37295296, "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": 1625851815957.930, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select_backward", "pid": 1336756, "tid": 1381189, + "ts": 1625851815961.407, "dur": 88.406, + "args": { + "External id": 3720233,"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": 1625851815966.186, "dur": 48.455, + "args": { + "External id": 3720234,"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": 1625851815967.774, "dur": 2.876, + "args": { + "External id": 3720235,"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": 1625851815971.243, "dur": 43.107, + "args": { + "External id": 3720236,"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": 1625851815975.254, "dur": 38.356, + "args": { + "External id": 3720237,"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": 1625851816019.365, "dur": 6.266, + "args": { + "External id": 3720238,"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": 1625851816023.431, "dur": 1.478, + "args": { + "External id": 3720239,"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": 1625851816026.531, "dur": 22.589, + "args": { + "External id": 3720240,"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": 1625851816059.880, "dur": 135.195, + "args": { + "External id": 3720241,"Record function id": 0, "Sequence number": 37295295, "Fwd thread id": 1, "Ev Idx": 48 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SliceBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1625851816060.976, "dur": 130.521, + "args": { + "External id": 3720242,"Sequence number": 37295295, "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": 1625851816060.976, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 1336756, "tid": 1381189, + "ts": 1625851816065.185, "dur": 125.964, + "args": { + "External id": 3720243,"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": 1625851816069.734, "dur": 18.220, + "args": { + "External id": 3720244,"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": 1625851816070.698, "dur": 2.904, + "args": { + "External id": 3720245,"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": 1625851816074.229, "dur": 13.463, + "args": { + "External id": 3720246,"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": 1625851816075.432, "dur": 11.898, + "args": { + "External id": 3720247,"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": 1625851816092.203, "dur": 2.616, + "args": { + "External id": 3720248,"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": 1625851816093.809, "dur": 0.751, + "args": { + "External id": 3720249,"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": 1625851816095.896, "dur": 94.707, + "args": { + "External id": 3720250,"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": 1625851816199.009, "dur": 103.303, + "args": { + "External id": 3720251,"Record function id": 0, "Sequence number": 37295294, "Fwd thread id": 1, "Ev Idx": 58 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SliceBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1625851816199.996, "dur": 99.430, + "args": { + "External id": 3720252,"Sequence number": 37295294, "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": 1625851816199.996, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 1336756, "tid": 1381189, + "ts": 1625851816201.407, "dur": 97.778, + "args": { + "External id": 3720253,"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": 1625851816204.917, "dur": 18.958, + "args": { + "External id": 3720254,"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": 1625851816206.037, "dur": 4.799, + "args": { + "External id": 3720255,"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": 1625851816211.454, "dur": 12.174, + "args": { + "External id": 3720256,"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": 1625851816212.300, "dur": 11.012, + "args": { + "External id": 3720257,"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": 1625851816224.931, "dur": 3.850, + "args": { + "External id": 3720258,"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": 1625851816227.989, "dur": 0.652, + "args": { + "External id": 3720259,"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": 1625851816231.703, "dur": 66.803, + "args": { + "External id": 3720260,"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": 1625851816306.614, "dur": 39.234, + "args": { + "External id": 3720261,"Record function id": 0, "Sequence number": 37295293, "Fwd thread id": 1, "Ev Idx": 68 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "AddBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1625851816307.974, "dur": 1.038, + "args": { + "External id": 3720262,"Sequence number": 37295293, "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": 1625851816307.974, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 1336756, "tid": 1381189, + "ts": 1625851816311.403, "dur": 31.153, + "args": { + "External id": 3720263,"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": 1625851816313.303, "dur": 28.872, + "args": { + "External id": 3720264,"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": 1625851816320.755, "dur": 3.356, + "args": { + "External id": 3720265,"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": 1625851816351.083, "dur": 2220.953, + "args": { + "External id": 3720266,"Record function id": 0, "Sequence number": 37295291, "Fwd thread id": 1, "Ev Idx": 73 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "FusedLinearCrossEntropyFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1625851816352.495, "dur": 2187.854, + "args": { + "External id": 3720267,"Sequence number": 37295291, "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": 1625851816352.495, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1625851816388.198, "dur": 2.408, + "args": { + "External id": 3720268,"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": 1625851816392.925, "dur": 2055.201, + "args": { + "External id": 3720269,"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": 1625851816394.967, "dur": 2052.881, + "args": { + "External id": 3720270,"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": 1625851816397.960, "dur": 4.925, + "args": { + "External id": 3720271,"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": 1625851816403.662, "dur": 2043.000, + "args": { + "External id": 3720272,"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": 1625851818451.381, "dur": 0.290, + "args": { + "External id": 3720273,"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": 1625851818455.417, "dur": 2.842, + "args": { + "External id": 3720274,"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": 1625851818456.929, "dur": 1.089, + "args": { + "External id": 3720275,"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": 1625851818462.386, "dur": 23.251, + "args": { + "External id": 3720276,"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": 1625851818491.293, "dur": 40.933, + "args": { + "External id": 3720277,"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": 1625851818492.846, "dur": 39.143, + "args": { + "External id": 3720278,"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": 1625851818494.185, "dur": 37.471, + "args": { + "External id": 3720279,"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": 1625851818548.817, "dur": 19.481, + "args": { + "External id": 3720280,"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": 1625851818579.946, "dur": 14.632, + "args": { + "External id": 3720281,"Record function id": 0, "Sequence number": 37295290, "Fwd thread id": 1, "Ev Idx": 88 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1625851818580.983, "dur": 11.498, + "args": { + "External id": 3720282,"Sequence number": 37295290, "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": 1625851818580.983, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1381189, + "ts": 1625851818587.059, "dur": 5.230, + "args": { + "External id": 3720283,"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": 1625851818588.475, "dur": 3.694, + "args": { + "External id": 3720284,"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": 1625851818597.919, "dur": 65.114, + "args": { + "External id": 3720285,"Record function id": 0, "Sequence number": 37295289, "Fwd thread id": 1, "Ev Idx": 92 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SliceBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1625851818599.148, "dur": 58.970, + "args": { + "External id": 3720286,"Sequence number": 37295289, "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": 1625851818599.148, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 1336756, "tid": 1381189, + "ts": 1625851818600.803, "dur": 56.962, + "args": { + "External id": 3720287,"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": 1625851818605.352, "dur": 20.094, + "args": { + "External id": 3720288,"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": 1625851818606.943, "dur": 2.771, + "args": { + "External id": 3720289,"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": 1625851818610.541, "dur": 14.660, + "args": { + "External id": 3720290,"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": 1625851818611.939, "dur": 12.756, + "args": { + "External id": 3720291,"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": 1625851818626.753, "dur": 5.701, + "args": { + "External id": 3720292,"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": 1625851818628.692, "dur": 3.517, + "args": { + "External id": 3720293,"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": 1625851818633.178, "dur": 23.876, + "args": { + "External id": 3720294,"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": 1625851818669.654, "dur": 72.852, + "args": { + "External id": 3720295,"Record function id": 0, "Sequence number": 37295288, "Fwd thread id": 1, "Ev Idx": 102 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SelectBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1625851818670.843, "dur": 68.228, + "args": { + "External id": 3720296,"Sequence number": 37295288, "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": 1625851818670.843, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select_backward", "pid": 1336756, "tid": 1381189, + "ts": 1625851818675.278, "dur": 63.568, + "args": { + "External id": 3720297,"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": 1625851818687.911, "dur": 25.340, + "args": { + "External id": 3720298,"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": 1625851818689.043, "dur": 3.755, + "args": { + "External id": 3720299,"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": 1625851818693.635, "dur": 19.366, + "args": { + "External id": 3720300,"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": 1625851818694.838, "dur": 17.777, + "args": { + "External id": 3720301,"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": 1625851818714.352, "dur": 6.752, + "args": { + "External id": 3720302,"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": 1625851818719.368, "dur": 1.175, + "args": { + "External id": 3720303,"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": 1625851818721.995, "dur": 16.224, + "args": { + "External id": 3720304,"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": 1625851818749.861, "dur": 105.807, + "args": { + "External id": 3720305,"Record function id": 0, "Sequence number": 37295287, "Fwd thread id": 1, "Ev Idx": 112 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SliceBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1625851818752.703, "dur": 100.074, + "args": { + "External id": 3720306,"Sequence number": 37295287, "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": 1625851818752.703, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 1336756, "tid": 1381189, + "ts": 1625851818754.349, "dur": 98.109, + "args": { + "External id": 3720307,"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": 1625851818755.470, "dur": 23.629, + "args": { + "External id": 3720308,"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": 1625851818756.646, "dur": 2.100, + "args": { + "External id": 3720309,"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": 1625851818759.261, "dur": 19.568, + "args": { + "External id": 3720310,"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": 1625851818759.949, "dur": 18.563, + "args": { + "External id": 3720311,"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": 1625851818780.169, "dur": 4.786, + "args": { + "External id": 3720312,"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": 1625851818784.164, "dur": 0.607, + "args": { + "External id": 3720313,"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": 1625851818785.782, "dur": 65.939, + "args": { + "External id": 3720314,"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": 1625851818859.510, "dur": 93.116, + "args": { + "External id": 3720315,"Record function id": 0, "Sequence number": 37295286, "Fwd thread id": 1, "Ev Idx": 122 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SliceBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1625851818862.458, "dur": 71.744, + "args": { + "External id": 3720316,"Sequence number": 37295286, "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": 1625851818862.458, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 1336756, "tid": 1381189, + "ts": 1625851818865.994, "dur": 67.889, + "args": { + "External id": 3720317,"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": 1625851818867.027, "dur": 15.424, + "args": { + "External id": 3720318,"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": 1625851818868.057, "dur": 1.674, + "args": { + "External id": 3720319,"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": 1625851818870.523, "dur": 11.684, + "args": { + "External id": 3720320,"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": 1625851818871.750, "dur": 10.150, + "args": { + "External id": 3720321,"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": 1625851818883.725, "dur": 1.739, + "args": { + "External id": 3720322,"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": 1625851818884.579, "dur": 0.719, + "args": { + "External id": 3720323,"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": 1625851818886.354, "dur": 46.926, + "args": { + "External id": 3720324,"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": 1625851818937.877, "dur": 13.606, + "args": { + "External id": 3720325,"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": 1625851818956.766, "dur": 66.093, + "args": { + "External id": 3720326,"Record function id": 0, "Sequence number": 37295285, "Fwd thread id": 1, "Ev Idx": 133 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "AddBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1625851818960.482, "dur": 0.814, + "args": { + "External id": 3720327,"Sequence number": 37295285, "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": 1625851818960.482, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 1336756, "tid": 1381189, + "ts": 1625851818963.024, "dur": 56.549, + "args": { + "External id": 3720328,"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": 1625851818964.578, "dur": 54.250, + "args": { + "External id": 3720329,"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": 1625851818972.223, "dur": 2.578, + "args": { + "External id": 3720330,"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": 1625851819029.535, "dur": 3070.705, + "args": { + "External id": 3720331,"Record function id": 0, "Sequence number": 37295283, "Fwd thread id": 1, "Ev Idx": 138 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "FusedLinearCrossEntropyFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1625851819032.946, "dur": 3041.217, + "args": { + "External id": 3720332,"Sequence number": 37295283, "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": 1625851819032.946, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1625851819062.191, "dur": 2.399, + "args": { + "External id": 3720333,"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": 1625851819066.638, "dur": 2897.177, + "args": { + "External id": 3720334,"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": 1625851819068.222, "dur": 2895.341, + "args": { + "External id": 3720335,"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": 1625851819070.177, "dur": 3.686, + "args": { + "External id": 3720336,"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": 1625851819074.634, "dur": 2887.658, + "args": { + "External id": 3720337,"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": 1625851821966.852, "dur": 0.316, + "args": { + "External id": 3720338,"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": 1625851821968.488, "dur": 2.242, + "args": { + "External id": 3720339,"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": 1625851821969.700, "dur": 0.902, + "args": { + "External id": 3720340,"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": 1625851821974.317, "dur": 43.274, + "args": { + "External id": 3720341,"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": 1625851822028.209, "dur": 38.889, + "args": { + "External id": 3720342,"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": 1625851822029.469, "dur": 37.366, + "args": { + "External id": 3720343,"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": 1625851822030.498, "dur": 36.044, + "args": { + "External id": 3720344,"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": 1625851822081.576, "dur": 15.424, + "args": { + "External id": 3720345,"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": 1625851822107.467, "dur": 9.933, + "args": { + "External id": 3720346,"Record function id": 0, "Sequence number": 37295282, "Fwd thread id": 1, "Ev Idx": 153 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1625851822108.826, "dur": 6.908, + "args": { + "External id": 3720347,"Sequence number": 37295282, "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": 1625851822108.826, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1381189, + "ts": 1625851822111.193, "dur": 4.336, + "args": { + "External id": 3720348,"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": 1625851822112.452, "dur": 2.965, + "args": { + "External id": 3720349,"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": 1625851822120.662, "dur": 66.881, + "args": { + "External id": 3720350,"Record function id": 0, "Sequence number": 37295281, "Fwd thread id": 1, "Ev Idx": 157 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SliceBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1625851822121.782, "dur": 61.648, + "args": { + "External id": 3720351,"Sequence number": 37295281, "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": 1625851822121.782, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 1336756, "tid": 1381189, + "ts": 1625851822126.332, "dur": 56.753, + "args": { + "External id": 3720352,"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": 1625851822130.682, "dur": 20.603, + "args": { + "External id": 3720353,"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": 1625851822131.608, "dur": 2.714, + "args": { + "External id": 3720354,"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": 1625851822135.238, "dur": 15.751, + "args": { + "External id": 3720355,"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": 1625851822136.555, "dur": 13.993, + "args": { + "External id": 3720356,"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": 1625851822152.639, "dur": 5.495, + "args": { + "External id": 3720357,"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": 1625851822156.695, "dur": 1.210, + "args": { + "External id": 3720358,"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": 1625851822159.132, "dur": 23.223, + "args": { + "External id": 3720359,"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": 1625851822191.299, "dur": 50.965, + "args": { + "External id": 3720360,"Record function id": 0, "Sequence number": 37295280, "Fwd thread id": 1, "Ev Idx": 167 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SelectBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1625851822192.518, "dur": 46.876, + "args": { + "External id": 3720361,"Sequence number": 37295280, "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": 1625851822192.518, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select_backward", "pid": 1336756, "tid": 1381189, + "ts": 1625851822193.729, "dur": 45.380, + "args": { + "External id": 3720362,"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": 1625851822195.202, "dur": 18.720, + "args": { + "External id": 3720363,"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": 1625851822197.889, "dur": 2.052, + "args": { + "External id": 3720364,"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": 1625851822200.425, "dur": 13.244, + "args": { + "External id": 3720365,"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": 1625851822201.009, "dur": 12.297, + "args": { + "External id": 3720366,"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": 1625851822214.788, "dur": 8.330, + "args": { + "External id": 3720367,"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": 1625851822219.164, "dur": 3.501, + "args": { + "External id": 3720368,"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": 1625851822223.691, "dur": 14.945, + "args": { + "External id": 3720369,"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": 1625851822245.901, "dur": 95.790, + "args": { + "External id": 3720370,"Record function id": 0, "Sequence number": 37295279, "Fwd thread id": 1, "Ev Idx": 177 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SliceBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1625851822246.676, "dur": 92.106, + "args": { + "External id": 3720371,"Sequence number": 37295279, "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": 1625851822246.676, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 1336756, "tid": 1381189, + "ts": 1625851822248.216, "dur": 90.097, + "args": { + "External id": 3720372,"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": 1625851822249.277, "dur": 21.313, + "args": { + "External id": 3720373,"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": 1625851822250.475, "dur": 2.163, + "args": { + "External id": 3720374,"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": 1625851822255.538, "dur": 14.792, + "args": { + "External id": 3720375,"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": 1625851822256.478, "dur": 13.490, + "args": { + "External id": 3720376,"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": 1625851822271.884, "dur": 4.216, + "args": { + "External id": 3720377,"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": 1625851822275.259, "dur": 0.692, + "args": { + "External id": 3720378,"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": 1625851822277.133, "dur": 60.561, + "args": { + "External id": 3720379,"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": 1625851822345.313, "dur": 99.280, + "args": { + "External id": 3720380,"Record function id": 0, "Sequence number": 37295278, "Fwd thread id": 1, "Ev Idx": 187 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SliceBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1625851822346.285, "dur": 79.880, + "args": { + "External id": 3720381,"Sequence number": 37295278, "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": 1625851822346.285, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 1336756, "tid": 1381189, + "ts": 1625851822349.510, "dur": 76.362, + "args": { + "External id": 3720382,"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": 1625851822350.179, "dur": 18.979, + "args": { + "External id": 3720383,"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": 1625851822350.739, "dur": 1.502, + "args": { + "External id": 3720384,"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": 1625851822352.817, "dur": 16.070, + "args": { + "External id": 3720385,"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": 1625851822356.309, "dur": 12.273, + "args": { + "External id": 3720386,"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": 1625851822370.134, "dur": 5.602, + "args": { + "External id": 3720387,"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": 1625851822375.070, "dur": 0.466, + "args": { + "External id": 3720388,"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": 1625851822376.504, "dur": 48.734, + "args": { + "External id": 3720389,"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": 1625851822429.352, "dur": 14.201, + "args": { + "External id": 3720390,"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": 1625851822450.700, "dur": 30.030, + "args": { + "External id": 3720391,"Record function id": 0, "Sequence number": 37295277, "Fwd thread id": 1, "Ev Idx": 198 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "AddBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1625851822452.130, "dur": 1.072, + "args": { + "External id": 3720392,"Sequence number": 37295277, "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": 1625851822452.130, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::sum", "pid": 1336756, "tid": 1381189, + "ts": 1625851822454.739, "dur": 22.002, + "args": { + "External id": 3720393,"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": 1625851822456.413, "dur": 19.948, + "args": { + "External id": 3720394,"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": 1625851822460.845, "dur": 0.692, + "args": { + "External id": 3720395,"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": 1625851822484.414, "dur": 3112.720, + "args": { + "External id": 3720396,"Record function id": 0, "Sequence number": 37295276, "Fwd thread id": 1, "Ev Idx": 203 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "FusedLinearCrossEntropyFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1625851822495.313, "dur": 3072.922, + "args": { + "External id": 3720397,"Sequence number": 37295276, "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": 1625851822495.313, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1625851822521.122, "dur": 2.276, + "args": { + "External id": 3720398,"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": 1625851822525.263, "dur": 2960.916, + "args": { + "External id": 3720399,"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": 1625851822526.708, "dur": 2959.199, + "args": { + "External id": 3720400,"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": 1625851822530.902, "dur": 2.656, + "args": { + "External id": 3720401,"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": 1625851822534.412, "dur": 2950.499, + "args": { + "External id": 3720402,"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": 1625851825489.544, "dur": 0.258, + "args": { + "External id": 3720403,"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": 1625851825490.674, "dur": 2.247, + "args": { + "External id": 3720404,"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": 1625851825492.010, "dur": 0.753, + "args": { + "External id": 3720405,"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": 1625851825496.345, "dur": 22.928, + "args": { + "External id": 3720406,"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": 1625851825523.704, "dur": 38.768, + "args": { + "External id": 3720407,"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": 1625851825524.665, "dur": 37.597, + "args": { + "External id": 3720408,"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": 1625851825525.972, "dur": 35.936, + "args": { + "External id": 3720409,"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": 1625851825578.511, "dur": 14.596, + "args": { + "External id": 3720410,"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": 1625851825609.155, "dur": 12.603, + "args": { + "External id": 3720411,"Record function id": 0, "Ev Idx": 218 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625851825611.524, "dur": 8.356, + "args": { + "External id": 3720412,"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": 1625851825614.712, "dur": 4.100, + "args": { + "External id": 3720413,"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": 1625851825615.945, "dur": 2.762, + "args": { + "External id": 3720414,"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": 1625851825625.343, "dur": 10.598, + "args": { + "External id": 3720415,"Record function id": 0, "Sequence number": 37295275, "Fwd thread id": 1, "Ev Idx": 222 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1625851825626.337, "dur": 7.584, + "args": { + "External id": 3720416,"Sequence number": 37295275, "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": 1625851825626.337, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1381189, + "ts": 1625851825628.214, "dur": 5.510, + "args": { + "External id": 3720417,"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": 1625851825631.132, "dur": 2.473, + "args": { + "External id": 3720418,"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": 1625851825639.191, "dur": 84.708, + "args": { + "External id": 3720419,"Record function id": 0, "Sequence number": 37295274, "Fwd thread id": 1, "Ev Idx": 226 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SliceBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1625851825640.293, "dur": 78.114, + "args": { + "External id": 3720420,"Sequence number": 37295274, "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": 1625851825640.293, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 1336756, "tid": 1381189, + "ts": 1625851825641.844, "dur": 76.207, + "args": { + "External id": 3720421,"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": 1625851825646.797, "dur": 23.800, + "args": { + "External id": 3720422,"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": 1625851825648.185, "dur": 2.614, + "args": { + "External id": 3720423,"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": 1625851825651.626, "dur": 18.677, + "args": { + "External id": 3720424,"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": 1625851825652.896, "dur": 16.926, + "args": { + "External id": 3720425,"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": 1625851825671.929, "dur": 17.094, + "args": { + "External id": 3720426,"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": 1625851825687.129, "dur": 1.219, + "args": { + "External id": 3720427,"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": 1625851825690.308, "dur": 26.989, + "args": { + "External id": 3720428,"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": 1625851825729.036, "dur": 53.947, + "args": { + "External id": 3720429,"Record function id": 0, "Sequence number": 37295273, "Fwd thread id": 1, "Ev Idx": 236 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SelectBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1625851825730.518, "dur": 50.052, + "args": { + "External id": 3720430,"Sequence number": 37295273, "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": 1625851825730.518, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select_backward", "pid": 1336756, "tid": 1381189, + "ts": 1625851825732.432, "dur": 47.785, + "args": { + "External id": 3720431,"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": 1625851825734.234, "dur": 24.115, + "args": { + "External id": 3720432,"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": 1625851825741.967, "dur": 2.505, + "args": { + "External id": 3720433,"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": 1625851825745.150, "dur": 12.925, + "args": { + "External id": 3720434,"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": 1625851825746.114, "dur": 11.578, + "args": { + "External id": 3720435,"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": 1625851825759.332, "dur": 4.586, + "args": { + "External id": 3720436,"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": 1625851825762.496, "dur": 0.988, + "args": { + "External id": 3720437,"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": 1625851825764.348, "dur": 15.428, + "args": { + "External id": 3720438,"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": 1625851825786.622, "dur": 96.790, + "args": { + "External id": 3720439,"Record function id": 0, "Sequence number": 37295272, "Fwd thread id": 1, "Ev Idx": 246 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SliceBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1625851825787.547, "dur": 93.367, + "args": { + "External id": 3720440,"Sequence number": 37295272, "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": 1625851825787.547, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 1336756, "tid": 1381189, + "ts": 1625851825788.834, "dur": 91.811, + "args": { + "External id": 3720441,"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": 1625851825792.415, "dur": 19.257, + "args": { + "External id": 3720442,"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": 1625851825793.209, "dur": 1.921, + "args": { + "External id": 3720443,"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": 1625851825797.974, "dur": 13.431, + "args": { + "External id": 3720444,"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": 1625851825799.011, "dur": 12.048, + "args": { + "External id": 3720445,"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": 1625851825812.772, "dur": 3.750, + "args": { + "External id": 3720446,"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": 1625851825813.771, "dur": 2.620, + "args": { + "External id": 3720447,"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": 1625851825817.185, "dur": 62.736, + "args": { + "External id": 3720448,"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": 1625851825887.218, "dur": 135.679, + "args": { + "External id": 3720449,"Record function id": 0, "Sequence number": 37295271, "Fwd thread id": 1, "Ev Idx": 256 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SliceBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1625851825888.175, "dur": 85.846, + "args": { + "External id": 3720450,"Sequence number": 37295271, "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": 1625851825888.175, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice_backward", "pid": 1336756, "tid": 1381189, + "ts": 1625851825889.658, "dur": 84.139, + "args": { + "External id": 3720451,"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": 1625851825890.863, "dur": 32.749, + "args": { + "External id": 3720452,"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": 1625851825895.798, "dur": 1.501, + "args": { + "External id": 3720453,"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": 1625851825902.091, "dur": 21.280, + "args": { + "External id": 3720454,"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": 1625851825906.699, "dur": 16.233, + "args": { + "External id": 3720455,"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": 1625851825924.535, "dur": 1.665, + "args": { + "External id": 3720456,"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": 1625851825925.402, "dur": 0.601, + "args": { + "External id": 3720457,"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": 1625851825926.966, "dur": 46.308, + "args": { + "External id": 3720458,"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": 1625851825977.541, "dur": 42.478, + "args": { + "External id": 3720459,"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": 1625851826030.238, "dur": 351.323, + "args": { + "External id": 3720460,"Record function id": 0, "Sequence number": 37295270, "Fwd thread id": 1, "Ev Idx": 267 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1625851826031.693, "dur": 342.524, + "args": { + "External id": 3720461,"Sequence number": 37295270, "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": 1625851826031.693, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_bwd_kernel_0", "pid": 1336756, "tid": 1381189, + "ts": 1625851826204.481, "dur": 44.659, + "args": { + "External id": 3720462,"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": 1625851826285.831, "dur": 28.183, + "args": { + "External id": 3720463,"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": 1625851826330.417, "dur": 19.573, + "args": { + "External id": 3720464,"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": 1625851826389.952, "dur": 13.365, + "args": { + "External id": 3720465,"Record function id": 0, "Ev Idx": 272 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625851826392.071, "dur": 10.361, + "args": { + "External id": 3720466,"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": 1625851826395.426, "dur": 6.132, + "args": { + "External id": 3720467,"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": 1625851826398.671, "dur": 2.772, + "args": { + "External id": 3720468,"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": 1625851826406.740, "dur": 36.887, + "args": { + "External id": 3720469,"Record function id": 0, "Sequence number": 37295269, "Fwd thread id": 1, "Ev Idx": 276 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "StackBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1625851826407.799, "dur": 28.404, + "args": { + "External id": 3720470,"Sequence number": 37295269, "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": 1625851826407.799, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::select", "pid": 1336756, "tid": 1381189, + "ts": 1625851826410.190, "dur": 7.599, + "args": { + "External id": 3720471,"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": 1625851826414.823, "dur": 1.142, + "args": { + "External id": 3720472,"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": 1625851826418.411, "dur": 8.218, + "args": { + "External id": 3720473,"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": 1625851826425.047, "dur": 0.694, + "args": { + "External id": 3720474,"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": 1625851826427.075, "dur": 2.584, + "args": { + "External id": 3720475,"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": 1625851826428.297, "dur": 0.504, + "args": { + "External id": 3720476,"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": 1625851826430.171, "dur": 5.415, + "args": { + "External id": 3720477,"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": 1625851826434.077, "dur": 0.666, + "args": { + "External id": 3720478,"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": 1625851826447.247, "dur": 5.668, + "args": { + "External id": 3720479,"Record function id": 0, "Sequence number": 37295268, "Fwd thread id": 1, "Ev Idx": 286 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "AddBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1625851826448.330, "dur": 1.264, + "args": { + "External id": 3720480,"Sequence number": 37295268, "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": 1625851826448.330, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: SwiGLULinearFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1625851826456.773, "dur": 571.188, + "args": { + "External id": 3720481,"Record function id": 0, "Sequence number": 37295267, "Fwd thread id": 1, "Ev Idx": 288 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SwiGLULinearFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1625851826457.802, "dur": 518.897, + "args": { + "External id": 3720482,"Sequence number": 37295267, "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": 1625851826457.802, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1381189, + "ts": 1625851826496.652, "dur": 11.832, + "args": { + "External id": 3720483,"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": 1625851826503.895, "dur": 4.218, + "args": { + "External id": 3720484,"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": 1625851826512.895, "dur": 6.658, + "args": { + "External id": 3720485,"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": 1625851826515.490, "dur": 2.730, + "args": { + "External id": 3720486,"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": 1625851826517.058, "dur": 0.927, + "args": { + "External id": 3720487,"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": 1625851826525.515, "dur": 123.720, + "args": { + "External id": 3720488,"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": 1625851826526.800, "dur": 7.445, + "args": { + "External id": 3720489,"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": 1625851826527.416, "dur": 5.882, + "args": { + "External id": 3720490,"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": 1625851826530.672, "dur": 2.493, + "args": { + "External id": 3720491,"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": 1625851826535.599, "dur": 113.002, + "args": { + "External id": 3720492,"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": 1625851826537.436, "dur": 110.054, + "args": { + "External id": 3720493,"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": 1625851826653.700, "dur": 6.509, + "args": { + "External id": 3720494,"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": 1625851826657.519, "dur": 2.562, + "args": { + "External id": 3720495,"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": 1625851826708.888, "dur": 5.614, + "args": { + "External id": 3720496,"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": 1625851826715.856, "dur": 3.423, + "args": { + "External id": 3720497,"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": 1625851826722.539, "dur": 1.836, + "args": { + "External id": 3720498,"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": 1625851826763.968, "dur": 3.177, + "args": { + "External id": 3720499,"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": 1625851826764.877, "dur": 2.073, + "args": { + "External id": 3720500,"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": 1625851826798.014, "dur": 155.272, + "args": { + "External id": 3720501,"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": 1625851826804.463, "dur": 9.466, + "args": { + "External id": 3720502,"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": 1625851826810.005, "dur": 1.085, + "args": { + "External id": 3720503,"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": 1625851826815.911, "dur": 8.556, + "args": { + "External id": 3720504,"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": 1625851826821.067, "dur": 2.631, + "args": { + "External id": 3720505,"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": 1625851826826.498, "dur": 4.131, + "args": { + "External id": 3720506,"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": 1625851826829.485, "dur": 0.798, + "args": { + "External id": 3720507,"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": 1625851826831.084, "dur": 4.469, + "args": { + "External id": 3720508,"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": 1625851826834.145, "dur": 0.680, + "args": { + "External id": 3720509,"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": 1625851826839.800, "dur": 4.263, + "args": { + "External id": 3720510,"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": 1625851826843.130, "dur": 0.666, + "args": { + "External id": 3720511,"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": 1625851826846.827, "dur": 8.222, + "args": { + "External id": 3720512,"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": 1625851826852.798, "dur": 2.053, + "args": { + "External id": 3720513,"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": 1625851826855.700, "dur": 3.596, + "args": { + "External id": 3720514,"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": 1625851826858.516, "dur": 0.523, + "args": { + "External id": 3720515,"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": 1625851826859.774, "dur": 2.457, + "args": { + "External id": 3720516,"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": 1625851826860.460, "dur": 1.695, + "args": { + "External id": 3720517,"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": 1625851826864.256, "dur": 74.976, + "args": { + "External id": 3720518,"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": 1625851826940.805, "dur": 3.453, + "args": { + "External id": 3720519,"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": 1625851826946.695, "dur": 2.620, + "args": { + "External id": 3720520,"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": 1625851826948.211, "dur": 0.436, + "args": { + "External id": 3720521,"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": 1625851826951.164, "dur": 0.938, + "args": { + "External id": 3720522,"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": 1625851827043.374, "dur": 11.926, + "args": { + "External id": 3720523,"Record function id": 0, "Ev Idx": 330 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625851827045.826, "dur": 8.648, + "args": { + "External id": 3720524,"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": 1625851827048.774, "dur": 4.763, + "args": { + "External id": 3720525,"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": 1625851827050.358, "dur": 3.041, + "args": { + "External id": 3720526,"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": 1625851827059.779, "dur": 9.707, + "args": { + "External id": 3720527,"Record function id": 0, "Sequence number": 37295266, "Fwd thread id": 1, "Ev Idx": 334 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1625851827060.887, "dur": 6.715, + "args": { + "External id": 3720528,"Sequence number": 37295266, "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": 1625851827060.887, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1381189, + "ts": 1625851827064.968, "dur": 2.377, + "args": { + "External id": 3720529,"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": 1625851827065.771, "dur": 1.446, + "args": { + "External id": 3720530,"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": 1625851827073.281, "dur": 181.361, + "args": { + "External id": 3720531,"Record function id": 0, "Sequence number": 37295265, "Fwd thread id": 1, "Ev Idx": 338 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1625851827074.246, "dur": 172.989, + "args": { + "External id": 3720532,"Sequence number": 37295265, "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": 1625851827074.246, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1381189, + "ts": 1625851827080.512, "dur": 4.350, + "args": { + "External id": 3720533,"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": 1625851827082.048, "dur": 2.245, + "args": { + "External id": 3720534,"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": 1625851827083.485, "dur": 0.556, + "args": { + "External id": 3720535,"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": 1625851827086.279, "dur": 65.942, + "args": { + "External id": 3720536,"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": 1625851827153.761, "dur": 6.080, + "args": { + "External id": 3720537,"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": 1625851827154.614, "dur": 4.639, + "args": { + "External id": 3720538,"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": 1625851827157.978, "dur": 1.089, + "args": { + "External id": 3720539,"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": 1625851827161.241, "dur": 6.151, + "args": { + "External id": 3720540,"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": 1625851827162.392, "dur": 4.538, + "args": { + "External id": 3720541,"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": 1625851827166.142, "dur": 0.703, + "args": { + "External id": 3720542,"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": 1625851827168.125, "dur": 78.144, + "args": { + "External id": 3720543,"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": 1625851827259.510, "dur": 6.328, + "args": { + "External id": 3720544,"Record function id": 0, "Sequence number": 37295264, "Fwd thread id": 1, "Ev Idx": 351 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1625851827260.690, "dur": 3.618, + "args": { + "External id": 3720545,"Sequence number": 37295264, "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": 1625851827260.690, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1381189, + "ts": 1625851827262.028, "dur": 2.130, + "args": { + "External id": 3720546,"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": 1625851827262.865, "dur": 1.166, + "args": { + "External id": 3720547,"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": 1625851827269.174, "dur": 12.425, + "args": { + "External id": 3720548,"Record function id": 0, "Sequence number": 37295263, "Fwd thread id": 1, "Ev Idx": 355 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1625851827272.482, "dur": 6.674, + "args": { + "External id": 3720549,"Sequence number": 37295263, "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": 1625851827272.482, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1381189, + "ts": 1625851827273.557, "dur": 5.378, + "args": { + "External id": 3720550,"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": 1625851827274.570, "dur": 3.885, + "args": { + "External id": 3720551,"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": 1625851827277.876, "dur": 0.440, + "args": { + "External id": 3720552,"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": 1625851827285.553, "dur": 5.340, + "args": { + "External id": 3720553,"Record function id": 0, "Ev Idx": 360 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625851827286.856, "dur": 3.534, + "args": { + "External id": 3720554,"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": 1625851827287.944, "dur": 2.142, + "args": { + "External id": 3720555,"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": 1625851827288.838, "dur": 1.159, + "args": { + "External id": 3720556,"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": 1625851827295.899, "dur": 7.527, + "args": { + "External id": 3720557,"Record function id": 0, "Sequence number": 37295262, "Fwd thread id": 1, "Ev Idx": 364 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1625851827296.595, "dur": 4.589, + "args": { + "External id": 3720558,"Sequence number": 37295262, "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": 1625851827296.595, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1381189, + "ts": 1625851827297.884, "dur": 3.157, + "args": { + "External id": 3720559,"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": 1625851827300.200, "dur": 0.701, + "args": { + "External id": 3720560,"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": 1625851827306.451, "dur": 126.339, + "args": { + "External id": 3720561,"Record function id": 0, "Sequence number": 37295261, "Fwd thread id": 1, "Ev Idx": 368 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1625851827307.090, "dur": 118.453, + "args": { + "External id": 3720562,"Sequence number": 37295261, "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": 1625851827307.090, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1381189, + "ts": 1625851827309.118, "dur": 2.930, + "args": { + "External id": 3720563,"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": 1625851827309.934, "dur": 1.701, + "args": { + "External id": 3720564,"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": 1625851827310.908, "dur": 0.588, + "args": { + "External id": 3720565,"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": 1625851827314.539, "dur": 43.373, + "args": { + "External id": 3720566,"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": 1625851827358.874, "dur": 5.736, + "args": { + "External id": 3720567,"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": 1625851827359.671, "dur": 4.437, + "args": { + "External id": 3720568,"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": 1625851827363.160, "dur": 0.826, + "args": { + "External id": 3720569,"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": 1625851827365.821, "dur": 7.182, + "args": { + "External id": 3720570,"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": 1625851827366.959, "dur": 5.664, + "args": { + "External id": 3720571,"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": 1625851827369.957, "dur": 2.588, + "args": { + "External id": 3720572,"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": 1625851827373.666, "dur": 51.227, + "args": { + "External id": 3720573,"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": 1625851827437.239, "dur": 36.630, + "args": { + "External id": 3720574,"Record function id": 0, "Sequence number": 37295260, "Fwd thread id": 1, "Ev Idx": 381 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1625851827438.090, "dur": 5.154, + "args": { + "External id": 3720575,"Sequence number": 37295260, "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": 1625851827438.090, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1381189, + "ts": 1625851827439.489, "dur": 3.616, + "args": { + "External id": 3720576,"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": 1625851827442.013, "dur": 0.979, + "args": { + "External id": 3720577,"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": 1625851827446.539, "dur": 24.693, + "args": { + "External id": 3720578,"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": 1625851827477.644, "dur": 9.240, + "args": { + "External id": 3720579,"Record function id": 0, "Sequence number": 37295259, "Fwd thread id": 1, "Ev Idx": 386 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1625851827478.530, "dur": 6.719, + "args": { + "External id": 3720580,"Sequence number": 37295259, "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": 1625851827478.530, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1381189, + "ts": 1625851827479.398, "dur": 5.645, + "args": { + "External id": 3720581,"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": 1625851827482.607, "dur": 1.979, + "args": { + "External id": 3720582,"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": 1625851827483.967, "dur": 0.496, + "args": { + "External id": 3720583,"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": 1625851827490.610, "dur": 4.690, + "args": { + "External id": 3720584,"Record function id": 0, "Ev Idx": 391 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625851827491.881, "dur": 2.963, + "args": { + "External id": 3720585,"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": 1625851827492.641, "dur": 1.918, + "args": { + "External id": 3720586,"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": 1625851827493.285, "dur": 1.187, + "args": { + "External id": 3720587,"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": 1625851827499.428, "dur": 457.797, + "args": { + "External id": 3720588,"Record function id": 0, "Sequence number": 37295258, "Fwd thread id": 1, "Ev Idx": 395 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1625851827500.915, "dur": 440.769, + "args": { + "External id": 3720589,"Sequence number": 37295258, "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": 1625851827500.915, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::contiguous", "pid": 1336756, "tid": 1381189, + "ts": 1625851827527.807, "dur": 32.604, + "args": { + "External id": 3720590,"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": 1625851827529.492, "dur": 30.675, + "args": { + "External id": 3720591,"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": 1625851827532.014, "dur": 5.516, + "args": { + "External id": 3720592,"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": 1625851827534.546, "dur": 2.449, + "args": { + "External id": 3720593,"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": 1625851827538.738, "dur": 20.849, + "args": { + "External id": 3720594,"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": 1625851827572.126, "dur": 4.445, + "args": { + "External id": 3720595,"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": 1625851827575.433, "dur": 1.018, + "args": { + "External id": 3720596,"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": 1625851827580.605, "dur": 3.546, + "args": { + "External id": 3720597,"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": 1625851827581.206, "dur": 2.845, + "args": { + "External id": 3720598,"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": 1625851827599.118, "dur": 2.127, + "args": { + "External id": 3720599,"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": 1625851827615.018, "dur": 3.885, + "args": { + "External id": 3720600,"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": 1625851827824.660, "dur": 3.730, + "args": { + "External id": 3720601,"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": 1625851827833.243, "dur": 38.339, + "args": { + "External id": 3720602,"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": 1625851827845.943, "dur": 1.053, + "args": { + "External id": 3720603,"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": 1625851827877.375, "dur": 29.362, + "args": { + "External id": 3720604,"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": 1625851827879.444, "dur": 27.101, + "args": { + "External id": 3720605,"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": 1625851827883.312, "dur": 4.038, + "args": { + "External id": 3720606,"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": 1625851827889.229, "dur": 16.842, + "args": { + "External id": 3720607,"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": 1625851827913.893, "dur": 2.234, + "args": { + "External id": 3720608,"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": 1625851827915.088, "dur": 0.940, + "args": { + "External id": 3720609,"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": 1625851827922.115, "dur": 4.507, + "args": { + "External id": 3720610,"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": 1625851827925.269, "dur": 1.238, + "args": { + "External id": 3720611,"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": 1625851827928.757, "dur": 4.145, + "args": { + "External id": 3720612,"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": 1625851827929.955, "dur": 2.856, + "args": { + "External id": 3720613,"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": 1625851827969.606, "dur": 8.720, + "args": { + "External id": 3720614,"Record function id": 0, "Ev Idx": 421 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625851827971.277, "dur": 6.382, + "args": { + "External id": 3720615,"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": 1625851827973.598, "dur": 3.168, + "args": { + "External id": 3720616,"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": 1625851827974.766, "dur": 1.886, + "args": { + "External id": 3720617,"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": 1625851828031.942, "dur": 15.188, + "args": { + "External id": 3720618,"Record function id": 0, "Sequence number": 37295257, "Fwd thread id": 1, "Ev Idx": 425 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1625851828034.521, "dur": 8.195, + "args": { + "External id": 3720619,"Sequence number": 37295257, "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": 1625851828034.521, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1381189, + "ts": 1625851828038.613, "dur": 3.897, + "args": { + "External id": 3720620,"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": 1625851828039.487, "dur": 2.703, + "args": { + "External id": 3720621,"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": 1625851828054.387, "dur": 153.580, + "args": { + "External id": 3720622,"Record function id": 0, "Sequence number": 37295256, "Fwd thread id": 1, "Ev Idx": 429 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1625851828055.555, "dur": 147.869, + "args": { + "External id": 3720623,"Sequence number": 37295256, "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": 1625851828055.555, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1381189, + "ts": 1625851828059.201, "dur": 5.291, + "args": { + "External id": 3720624,"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": 1625851828060.893, "dur": 2.911, + "args": { + "External id": 3720625,"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": 1625851828062.390, "dur": 1.198, + "args": { + "External id": 3720626,"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": 1625851828066.227, "dur": 66.926, + "args": { + "External id": 3720627,"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": 1625851828134.508, "dur": 8.049, + "args": { + "External id": 3720628,"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": 1625851828138.117, "dur": 3.847, + "args": { + "External id": 3720629,"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": 1625851828139.260, "dur": 2.520, + "args": { + "External id": 3720630,"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": 1625851828144.360, "dur": 5.469, + "args": { + "External id": 3720631,"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": 1625851828145.608, "dur": 3.549, + "args": { + "External id": 3720632,"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": 1625851828148.780, "dur": 0.311, + "args": { + "External id": 3720633,"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": 1625851828150.286, "dur": 52.314, + "args": { + "External id": 3720634,"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": 1625851828212.899, "dur": 10.900, + "args": { + "External id": 3720635,"Record function id": 0, "Sequence number": 37295255, "Fwd thread id": 1, "Ev Idx": 442 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1625851828214.214, "dur": 7.386, + "args": { + "External id": 3720636,"Sequence number": 37295255, "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": 1625851828214.214, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1381189, + "ts": 1625851828217.409, "dur": 4.040, + "args": { + "External id": 3720637,"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": 1625851828218.060, "dur": 3.243, + "args": { + "External id": 3720638,"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": 1625851828227.183, "dur": 8.527, + "args": { + "External id": 3720639,"Record function id": 0, "Sequence number": 37295254, "Fwd thread id": 1, "Ev Idx": 446 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1625851828228.206, "dur": 5.831, + "args": { + "External id": 3720640,"Sequence number": 37295254, "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": 1625851828228.206, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1381189, + "ts": 1625851828229.200, "dur": 4.619, + "args": { + "External id": 3720641,"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": 1625851828229.889, "dur": 3.422, + "args": { + "External id": 3720642,"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": 1625851828232.826, "dur": 0.382, + "args": { + "External id": 3720643,"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": 1625851828240.151, "dur": 8.000, + "args": { + "External id": 3720644,"Record function id": 0, "Ev Idx": 451 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625851828241.165, "dur": 6.455, + "args": { + "External id": 3720645,"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": 1625851828242.700, "dur": 4.626, + "args": { + "External id": 3720646,"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": 1625851828245.792, "dur": 1.436, + "args": { + "External id": 3720647,"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": 1625851828251.042, "dur": 6.865, + "args": { + "External id": 3720648,"Record function id": 0, "Sequence number": 37295253, "Fwd thread id": 1, "Ev Idx": 455 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1625851828252.040, "dur": 3.401, + "args": { + "External id": 3720649,"Sequence number": 37295253, "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": 1625851828252.040, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1381189, + "ts": 1625851828253.173, "dur": 2.123, + "args": { + "External id": 3720650,"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": 1625851828253.973, "dur": 1.193, + "args": { + "External id": 3720651,"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": 1625851828264.802, "dur": 313.212, + "args": { + "External id": 3720652,"Record function id": 0, "Sequence number": 37295252, "Fwd thread id": 1, "Ev Idx": 459 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "FlashAttnFuncBackward", "pid": 1336756, "tid": 1381189, + "ts": 1625851828265.947, "dur": 291.800, + "args": { + "External id": 3720653,"Sequence number": 37295252, "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": 1625851828265.947, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336756, "tid": 1381189, + "ts": 1625851828282.999, "dur": 11.367, + "args": { + "External id": 3720654,"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": 1625851828290.044, "dur": 3.879, + "args": { + "External id": 3720655,"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": 1625851828296.356, "dur": 3.216, + "args": { + "External id": 3720656,"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": 1625851828297.416, "dur": 1.926, + "args": { + "External id": 3720657,"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": 1625851828301.170, "dur": 6.201, + "args": { + "External id": 3720658,"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": 1625851828304.302, "dur": 2.907, + "args": { + "External id": 3720659,"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": 1625851828337.184, "dur": 195.605, + "args": { + "External id": 3720660,"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": 1625851828427.253, "dur": 3.799, + "args": { + "External id": 3720661,"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": 1625851828432.716, "dur": 4.028, + "args": { + "External id": 3720662,"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": 1625851828545.299, "dur": 3.401, + "args": { + "External id": 3720663,"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": 1625851828551.439, "dur": 1.000, + "args": { + "External id": 3720664,"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": 1625851828554.523, "dur": 0.613, + "args": { + "External id": 3720665,"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": 1625851828585.344, "dur": 257.854, + "args": { + "External id": 3720666,"Record function id": 0, "Sequence number": 37295251, "Fwd thread id": 1, "Ev Idx": 473 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1625851828586.657, "dur": 247.719, + "args": { + "External id": 3720667,"Sequence number": 37295251, "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": 1625851828586.657, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 1336756, "tid": 1381189, + "ts": 1625851828606.597, "dur": 50.605, + "args": { + "External id": 3720668,"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": 1625851828613.217, "dur": 2.504, + "args": { + "External id": 3720669,"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": 1625851828617.054, "dur": 39.335, + "args": { + "External id": 3720670,"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": 1625851828666.743, "dur": 4.021, + "args": { + "External id": 3720671,"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": 1625851828668.194, "dur": 2.260, + "args": { + "External id": 3720672,"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": 1625851828852.438, "dur": 205.582, + "args": { + "External id": 3720673,"Record function id": 0, "Sequence number": 37295250, "Fwd thread id": 1, "Ev Idx": 480 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1625851828854.479, "dur": 195.686, + "args": { + "External id": 3720674,"Sequence number": 37295250, "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": 1625851828854.479, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 1336756, "tid": 1381189, + "ts": 1625851828868.045, "dur": 38.943, + "args": { + "External id": 3720675,"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": 1625851828872.731, "dur": 3.742, + "args": { + "External id": 3720676,"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": 1625851828877.498, "dur": 28.780, + "args": { + "External id": 3720677,"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": 1625851828914.245, "dur": 4.477, + "args": { + "External id": 3720678,"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": 1625851828916.098, "dur": 2.284, + "args": { + "External id": 3720679,"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": 1625851829068.686, "dur": 16.040, + "args": { + "External id": 3720680,"Record function id": 0, "Sequence number": 37295249, "Fwd thread id": 1, "Ev Idx": 487 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1625851829070.410, "dur": 11.381, + "args": { + "External id": 3720681,"Sequence number": 37295249, "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": 1625851829070.410, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1381189, + "ts": 1625851829072.973, "dur": 8.501, + "args": { + "External id": 3720682,"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": 1625851829074.366, "dur": 6.946, + "args": { + "External id": 3720683,"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": 1625851829088.216, "dur": 9.470, + "args": { + "External id": 3720684,"Record function id": 0, "Sequence number": 37295248, "Fwd thread id": 1, "Ev Idx": 491 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1625851829089.318, "dur": 6.212, + "args": { + "External id": 3720685,"Sequence number": 37295248, "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": 1625851829089.318, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1381189, + "ts": 1625851829093.424, "dur": 1.954, + "args": { + "External id": 3720686,"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": 1625851829094.226, "dur": 1.008, + "args": { + "External id": 3720687,"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": 1625851829100.796, "dur": 8.345, + "args": { + "External id": 3720688,"Record function id": 0, "Sequence number": 37295247, "Fwd thread id": 1, "Ev Idx": 495 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1625851829102.078, "dur": 5.216, + "args": { + "External id": 3720689,"Sequence number": 37295247, "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": 1625851829102.078, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1381189, + "ts": 1625851829105.732, "dur": 1.404, + "args": { + "External id": 3720690,"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": 1625851829106.270, "dur": 0.784, + "args": { + "External id": 3720691,"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": 1625851829114.968, "dur": 5.543, + "args": { + "External id": 3720692,"Record function id": 0, "Sequence number": 37295246, "Fwd thread id": 1, "Ev Idx": 499 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1625851829115.842, "dur": 2.657, + "args": { + "External id": 3720693,"Sequence number": 37295246, "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": 1625851829115.842, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1381189, + "ts": 1625851829116.832, "dur": 1.513, + "args": { + "External id": 3720694,"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": 1625851829117.428, "dur": 0.824, + "args": { + "External id": 3720695,"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": 1625851829123.827, "dur": 180.879, + "args": { + "External id": 3720696,"Record function id": 0, "Sequence number": 37295245, "Fwd thread id": 1, "Ev Idx": 503 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1625851829124.934, "dur": 172.656, + "args": { + "External id": 3720697,"Sequence number": 37295245, "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": 1625851829124.934, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1381189, + "ts": 1625851829128.648, "dur": 8.549, + "args": { + "External id": 3720698,"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": 1625851829132.687, "dur": 3.847, + "args": { + "External id": 3720699,"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": 1625851829134.664, "dur": 1.631, + "args": { + "External id": 3720700,"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": 1625851829138.692, "dur": 68.227, + "args": { + "External id": 3720701,"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": 1625851829208.431, "dur": 7.779, + "args": { + "External id": 3720702,"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": 1625851829209.254, "dur": 6.021, + "args": { + "External id": 3720703,"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": 1625851829213.690, "dur": 1.408, + "args": { + "External id": 3720704,"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": 1625851829244.640, "dur": 5.468, + "args": { + "External id": 3720705,"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": 1625851829248.061, "dur": 1.120, + "args": { + "External id": 3720706,"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": 1625851829248.652, "dur": 0.410, + "args": { + "External id": 3720707,"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": 1625851829250.658, "dur": 46.078, + "args": { + "External id": 3720708,"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": 1625851829309.418, "dur": 5.604, + "args": { + "External id": 3720709,"Record function id": 0, "Sequence number": 37295244, "Fwd thread id": 1, "Ev Idx": 516 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1625851829310.252, "dur": 3.200, + "args": { + "External id": 3720710,"Sequence number": 37295244, "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": 1625851829310.252, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1381189, + "ts": 1625851829311.395, "dur": 1.918, + "args": { + "External id": 3720711,"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": 1625851829312.095, "dur": 1.083, + "args": { + "External id": 3720712,"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": 1625851829318.155, "dur": 10.362, + "args": { + "External id": 3720713,"Record function id": 0, "Sequence number": 37295243, "Fwd thread id": 1, "Ev Idx": 520 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1625851829321.375, "dur": 5.257, + "args": { + "External id": 3720714,"Sequence number": 37295243, "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": 1625851829321.375, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1381189, + "ts": 1625851829322.110, "dur": 4.337, + "args": { + "External id": 3720715,"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": 1625851829322.638, "dur": 3.354, + "args": { + "External id": 3720716,"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": 1625851829325.491, "dur": 0.392, + "args": { + "External id": 3720717,"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": 1625851829334.659, "dur": 8.198, + "args": { + "External id": 3720718,"Record function id": 0, "Ev Idx": 525 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625851829336.033, "dur": 6.131, + "args": { + "External id": 3720719,"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": 1625851829338.336, "dur": 3.408, + "args": { + "External id": 3720720,"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": 1625851829339.356, "dur": 2.292, + "args": { + "External id": 3720721,"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": 1625851829348.345, "dur": 7.348, + "args": { + "External id": 3720722,"Record function id": 0, "Sequence number": 37295242, "Fwd thread id": 1, "Ev Idx": 529 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1625851829349.186, "dur": 4.432, + "args": { + "External id": 3720723,"Sequence number": 37295242, "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": 1625851829349.186, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1381189, + "ts": 1625851829349.955, "dur": 3.520, + "args": { + "External id": 3720724,"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": 1625851829352.662, "dur": 0.674, + "args": { + "External id": 3720725,"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": 1625851829359.169, "dur": 92.903, + "args": { + "External id": 3720726,"Record function id": 0, "Sequence number": 37295241, "Fwd thread id": 1, "Ev Idx": 533 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1625851829359.924, "dur": 85.473, + "args": { + "External id": 3720727,"Sequence number": 37295241, "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": 1625851829359.924, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1381189, + "ts": 1625851829362.160, "dur": 4.582, + "args": { + "External id": 3720728,"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": 1625851829362.617, "dur": 3.693, + "args": { + "External id": 3720729,"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": 1625851829365.819, "dur": 0.377, + "args": { + "External id": 3720730,"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": 1625851829370.392, "dur": 29.699, + "args": { + "External id": 3720731,"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": 1625851829401.104, "dur": 2.569, + "args": { + "External id": 3720732,"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": 1625851829401.611, "dur": 1.619, + "args": { + "External id": 3720733,"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": 1625851829402.330, "dur": 0.793, + "args": { + "External id": 3720734,"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": 1625851829404.903, "dur": 7.063, + "args": { + "External id": 3720735,"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": 1625851829405.875, "dur": 5.684, + "args": { + "External id": 3720736,"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": 1625851829409.086, "dur": 2.403, + "args": { + "External id": 3720737,"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": 1625851829412.396, "dur": 32.344, + "args": { + "External id": 3720738,"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": 1625851829456.338, "dur": 34.769, + "args": { + "External id": 3720739,"Record function id": 0, "Sequence number": 37295240, "Fwd thread id": 1, "Ev Idx": 546 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1625851829457.435, "dur": 5.305, + "args": { + "External id": 3720740,"Sequence number": 37295240, "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": 1625851829457.435, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1381189, + "ts": 1625851829460.698, "dur": 1.894, + "args": { + "External id": 3720741,"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": 1625851829461.301, "dur": 1.157, + "args": { + "External id": 3720742,"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": 1625851829465.541, "dur": 23.401, + "args": { + "External id": 3720743,"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": 1625851829494.767, "dur": 8.594, + "args": { + "External id": 3720744,"Record function id": 0, "Sequence number": 37295239, "Fwd thread id": 1, "Ev Idx": 551 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1625851829495.668, "dur": 6.006, + "args": { + "External id": 3720745,"Sequence number": 37295239, "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": 1625851829495.668, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1381189, + "ts": 1625851829496.248, "dur": 5.210, + "args": { + "External id": 3720746,"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": 1625851829497.069, "dur": 3.887, + "args": { + "External id": 3720747,"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": 1625851829500.453, "dur": 0.387, + "args": { + "External id": 3720748,"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": 1625851829507.151, "dur": 6.870, + "args": { + "External id": 3720749,"Record function id": 0, "Ev Idx": 556 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625851829510.267, "dur": 3.267, + "args": { + "External id": 3720750,"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": 1625851829511.335, "dur": 1.871, + "args": { + "External id": 3720751,"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": 1625851829511.794, "dur": 1.304, + "args": { + "External id": 3720752,"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": 1625851829517.172, "dur": 5.406, + "args": { + "External id": 3720753,"Record function id": 0, "Sequence number": 37295238, "Fwd thread id": 1, "Ev Idx": 560 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1625851829517.992, "dur": 2.562, + "args": { + "External id": 3720754,"Sequence number": 37295238, "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": 1625851829517.992, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1381189, + "ts": 1625851829518.994, "dur": 1.417, + "args": { + "External id": 3720755,"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": 1625851829519.589, "dur": 0.729, + "args": { + "External id": 3720756,"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": 1625851829525.678, "dur": 89.685, + "args": { + "External id": 3720757,"Record function id": 0, "Sequence number": 37295237, "Fwd thread id": 1, "Ev Idx": 564 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1625851829528.965, "dur": 77.849, + "args": { + "External id": 3720758,"Sequence number": 37295237, "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": 1625851829528.965, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1381189, + "ts": 1625851829530.936, "dur": 2.188, + "args": { + "External id": 3720759,"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": 1625851829531.360, "dur": 1.332, + "args": { + "External id": 3720760,"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": 1625851829532.210, "dur": 0.370, + "args": { + "External id": 3720761,"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": 1625851829533.705, "dur": 28.021, + "args": { + "External id": 3720762,"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": 1625851829562.624, "dur": 6.756, + "args": { + "External id": 3720763,"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": 1625851829563.113, "dur": 5.743, + "args": { + "External id": 3720764,"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": 1625851829568.276, "dur": 0.471, + "args": { + "External id": 3720765,"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": 1625851829570.618, "dur": 2.760, + "args": { + "External id": 3720766,"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": 1625851829571.471, "dur": 1.346, + "args": { + "External id": 3720767,"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": 1625851829572.300, "dur": 0.445, + "args": { + "External id": 3720768,"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": 1625851829573.776, "dur": 32.217, + "args": { + "External id": 3720769,"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": 1625851829619.499, "dur": 25.806, + "args": { + "External id": 3720770,"Record function id": 0, "Sequence number": 37295236, "Fwd thread id": 1, "Ev Idx": 577 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1625851829620.440, "dur": 4.646, + "args": { + "External id": 3720771,"Sequence number": 37295236, "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": 1625851829620.440, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1381189, + "ts": 1625851829623.516, "dur": 1.417, + "args": { + "External id": 3720772,"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": 1625851829623.969, "dur": 0.828, + "args": { + "External id": 3720773,"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": 1625851829627.161, "dur": 16.264, + "args": { + "External id": 3720774,"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": 1625851829648.715, "dur": 10.141, + "args": { + "External id": 3720775,"Record function id": 0, "Sequence number": 37295235, "Fwd thread id": 1, "Ev Idx": 582 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1625851829649.893, "dur": 7.169, + "args": { + "External id": 3720776,"Sequence number": 37295235, "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": 1625851829649.893, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1381189, + "ts": 1625851829650.658, "dur": 6.197, + "args": { + "External id": 3720777,"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": 1625851829653.270, "dur": 3.123, + "args": { + "External id": 3720778,"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": 1625851829655.726, "dur": 0.556, + "args": { + "External id": 3720779,"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": 1625851829662.534, "dur": 5.962, + "args": { + "External id": 3720780,"Record function id": 0, "Ev Idx": 587 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625851829663.558, "dur": 4.488, + "args": { + "External id": 3720781,"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": 1625851829664.296, "dur": 3.465, + "args": { + "External id": 3720782,"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": 1625851829666.695, "dur": 0.969, + "args": { + "External id": 3720783,"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": 1625851829672.282, "dur": 428.361, + "args": { + "External id": 3720784,"Record function id": 0, "Sequence number": 37295234, "Fwd thread id": 1, "Ev Idx": 591 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1625851829673.313, "dur": 389.745, + "args": { + "External id": 3720785,"Sequence number": 37295234, "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": 1625851829673.313, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1381189, + "ts": 1625851829720.917, "dur": 2.589, + "args": { + "External id": 3720786,"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": 1625851829721.450, "dur": 1.768, + "args": { + "External id": 3720787,"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": 1625851829740.173, "dur": 6.753, + "args": { + "External id": 3720788,"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": 1625851829756.236, "dur": 2.369, + "args": { + "External id": 3720789,"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": 1625851829913.806, "dur": 1.734, + "args": { + "External id": 3720790,"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": 1625851829919.850, "dur": 39.009, + "args": { + "External id": 3720791,"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": 1625851829931.897, "dur": 0.910, + "args": { + "External id": 3720792,"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": 1625851829964.371, "dur": 68.715, + "args": { + "External id": 3720793,"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": 1625851829966.248, "dur": 66.531, + "args": { + "External id": 3720794,"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": 1625851829969.798, "dur": 4.996, + "args": { + "External id": 3720795,"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": 1625851829976.482, "dur": 55.213, + "args": { + "External id": 3720796,"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": 1625851830039.608, "dur": 3.427, + "args": { + "External id": 3720797,"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": 1625851830041.149, "dur": 1.782, + "args": { + "External id": 3720798,"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": 1625851830052.057, "dur": 3.537, + "args": { + "External id": 3720799,"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": 1625851830054.451, "dur": 1.052, + "args": { + "External id": 3720800,"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": 1625851830074.510, "dur": 19.583, + "args": { + "External id": 3720801,"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": 1625851830113.380, "dur": 8.096, + "args": { + "External id": 3720802,"Record function id": 0, "Ev Idx": 609 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625851830115.487, "dur": 5.262, + "args": { + "External id": 3720803,"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": 1625851830117.530, "dur": 2.317, + "args": { + "External id": 3720804,"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": 1625851830118.267, "dur": 1.444, + "args": { + "External id": 3720805,"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": 1625851830127.603, "dur": 5.560, + "args": { + "External id": 3720806,"Record function id": 0, "Sequence number": 37295233, "Fwd thread id": 1, "Ev Idx": 613 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "AddBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1625851830129.183, "dur": 1.196, + "args": { + "External id": 3720807,"Sequence number": 37295233, "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": 1625851830129.183, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: SwiGLULinearFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1625851830136.913, "dur": 414.798, + "args": { + "External id": 3720808,"Record function id": 0, "Sequence number": 37295232, "Fwd thread id": 1, "Ev Idx": 615 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SwiGLULinearFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1625851830138.047, "dur": 402.755, + "args": { + "External id": 3720809,"Sequence number": 37295232, "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": 1625851830138.047, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1381189, + "ts": 1625851830170.256, "dur": 8.256, + "args": { + "External id": 3720810,"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": 1625851830175.127, "dur": 3.134, + "args": { + "External id": 3720811,"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": 1625851830181.669, "dur": 6.891, + "args": { + "External id": 3720812,"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": 1625851830183.255, "dur": 4.553, + "args": { + "External id": 3720813,"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": 1625851830186.664, "dur": 0.983, + "args": { + "External id": 3720814,"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": 1625851830194.051, "dur": 92.080, + "args": { + "External id": 3720815,"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": 1625851830195.400, "dur": 5.151, + "args": { + "External id": 3720816,"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": 1625851830196.090, "dur": 4.034, + "args": { + "External id": 3720817,"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": 1625851830197.072, "dur": 2.976, + "args": { + "External id": 3720818,"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": 1625851830201.835, "dur": 83.849, + "args": { + "External id": 3720819,"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": 1625851830203.589, "dur": 81.227, + "args": { + "External id": 3720820,"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": 1625851830289.599, "dur": 5.333, + "args": { + "External id": 3720821,"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": 1625851830293.507, "dur": 1.318, + "args": { + "External id": 3720822,"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": 1625851830327.567, "dur": 4.725, + "args": { + "External id": 3720823,"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": 1625851830333.847, "dur": 1.953, + "args": { + "External id": 3720824,"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": 1625851830336.770, "dur": 1.735, + "args": { + "External id": 3720825,"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": 1625851830371.285, "dur": 2.187, + "args": { + "External id": 3720826,"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": 1625851830371.941, "dur": 1.383, + "args": { + "External id": 3720827,"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": 1625851830398.973, "dur": 123.971, + "args": { + "External id": 3720828,"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": 1625851830404.183, "dur": 4.993, + "args": { + "External id": 3720829,"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": 1625851830407.464, "dur": 0.849, + "args": { + "External id": 3720830,"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": 1625851830410.537, "dur": 10.993, + "args": { + "External id": 3720831,"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": 1625851830417.113, "dur": 3.696, + "args": { + "External id": 3720832,"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": 1625851830422.956, "dur": 3.932, + "args": { + "External id": 3720833,"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": 1625851830426.008, "dur": 0.463, + "args": { + "External id": 3720834,"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": 1625851830427.572, "dur": 3.760, + "args": { + "External id": 3720835,"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": 1625851830430.472, "dur": 0.465, + "args": { + "External id": 3720836,"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": 1625851830434.682, "dur": 1.913, + "args": { + "External id": 3720837,"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": 1625851830435.852, "dur": 0.471, + "args": { + "External id": 3720838,"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": 1625851830441.496, "dur": 4.525, + "args": { + "External id": 3720839,"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": 1625851830443.887, "dur": 1.974, + "args": { + "External id": 3720840,"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": 1625851830448.421, "dur": 1.619, + "args": { + "External id": 3720841,"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": 1625851830449.392, "dur": 0.335, + "args": { + "External id": 3720842,"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": 1625851830450.572, "dur": 5.803, + "args": { + "External id": 3720843,"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": 1625851830453.245, "dur": 3.031, + "args": { + "External id": 3720844,"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": 1625851830457.750, "dur": 51.136, + "args": { + "External id": 3720845,"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": 1625851830510.438, "dur": 3.227, + "args": { + "External id": 3720846,"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": 1625851830514.344, "dur": 4.230, + "args": { + "External id": 3720847,"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": 1625851830517.601, "dur": 0.449, + "args": { + "External id": 3720848,"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": 1625851830520.768, "dur": 0.896, + "args": { + "External id": 3720849,"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": 1625851830560.277, "dur": 7.927, + "args": { + "External id": 3720850,"Record function id": 0, "Ev Idx": 657 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625851830561.995, "dur": 5.613, + "args": { + "External id": 3720851,"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": 1625851830563.639, "dur": 3.063, + "args": { + "External id": 3720852,"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": 1625851830564.634, "dur": 1.986, + "args": { + "External id": 3720853,"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": 1625851830571.765, "dur": 6.604, + "args": { + "External id": 3720854,"Record function id": 0, "Sequence number": 37295231, "Fwd thread id": 1, "Ev Idx": 661 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1625851830572.775, "dur": 3.205, + "args": { + "External id": 3720855,"Sequence number": 37295231, "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": 1625851830572.775, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1381189, + "ts": 1625851830574.212, "dur": 1.592, + "args": { + "External id": 3720856,"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": 1625851830574.849, "dur": 0.845, + "args": { + "External id": 3720857,"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": 1625851830581.969, "dur": 139.005, + "args": { + "External id": 3720858,"Record function id": 0, "Sequence number": 37295230, "Fwd thread id": 1, "Ev Idx": 665 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1625851830582.802, "dur": 129.592, + "args": { + "External id": 3720859,"Sequence number": 37295230, "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": 1625851830582.802, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1381189, + "ts": 1625851830587.752, "dur": 5.861, + "args": { + "External id": 3720860,"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": 1625851830588.687, "dur": 4.395, + "args": { + "External id": 3720861,"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": 1625851830592.442, "dur": 0.502, + "args": { + "External id": 3720862,"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": 1625851830594.733, "dur": 40.552, + "args": { + "External id": 3720863,"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": 1625851830636.399, "dur": 5.747, + "args": { + "External id": 3720864,"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": 1625851830637.053, "dur": 4.258, + "args": { + "External id": 3720865,"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": 1625851830640.077, "dur": 1.066, + "args": { + "External id": 3720866,"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": 1625851830643.680, "dur": 3.974, + "args": { + "External id": 3720867,"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": 1625851830645.209, "dur": 1.860, + "args": { + "External id": 3720868,"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": 1625851830646.637, "dur": 0.368, + "args": { + "External id": 3720869,"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": 1625851830648.302, "dur": 62.588, + "args": { + "External id": 3720870,"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": 1625851830727.777, "dur": 9.782, + "args": { + "External id": 3720871,"Record function id": 0, "Sequence number": 37295229, "Fwd thread id": 1, "Ev Idx": 678 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1625851830728.828, "dur": 7.378, + "args": { + "External id": 3720872,"Sequence number": 37295229, "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": 1625851830728.828, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1381189, + "ts": 1625851830733.176, "dur": 2.881, + "args": { + "External id": 3720873,"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": 1625851830734.131, "dur": 1.826, + "args": { + "External id": 3720874,"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": 1625851830741.176, "dur": 10.063, + "args": { + "External id": 3720875,"Record function id": 0, "Sequence number": 37295228, "Fwd thread id": 1, "Ev Idx": 682 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1625851830744.510, "dur": 4.582, + "args": { + "External id": 3720876,"Sequence number": 37295228, "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": 1625851830744.510, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1381189, + "ts": 1625851830745.727, "dur": 3.151, + "args": { + "External id": 3720877,"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": 1625851830746.606, "dur": 1.777, + "args": { + "External id": 3720878,"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": 1625851830747.699, "dur": 0.573, + "args": { + "External id": 3720879,"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": 1625851830755.467, "dur": 5.580, + "args": { + "External id": 3720880,"Record function id": 0, "Ev Idx": 687 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625851830756.631, "dur": 3.887, + "args": { + "External id": 3720881,"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": 1625851830758.025, "dur": 2.200, + "args": { + "External id": 3720882,"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": 1625851830758.681, "dur": 1.451, + "args": { + "External id": 3720883,"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": 1625851830764.205, "dur": 8.650, + "args": { + "External id": 3720884,"Record function id": 0, "Sequence number": 37295227, "Fwd thread id": 1, "Ev Idx": 691 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1625851830766.846, "dur": 4.184, + "args": { + "External id": 3720885,"Sequence number": 37295227, "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": 1625851830766.846, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1381189, + "ts": 1625851830767.774, "dur": 3.103, + "args": { + "External id": 3720886,"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": 1625851830770.053, "dur": 0.730, + "args": { + "External id": 3720887,"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": 1625851830775.823, "dur": 122.620, + "args": { + "External id": 3720888,"Record function id": 0, "Sequence number": 37295226, "Fwd thread id": 1, "Ev Idx": 695 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1625851830776.463, "dur": 113.056, + "args": { + "External id": 3720889,"Sequence number": 37295226, "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": 1625851830776.463, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1381189, + "ts": 1625851830778.831, "dur": 6.202, + "args": { + "External id": 3720890,"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": 1625851830779.511, "dur": 5.039, + "args": { + "External id": 3720891,"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": 1625851830783.890, "dur": 0.550, + "args": { + "External id": 3720892,"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": 1625851830788.427, "dur": 38.658, + "args": { + "External id": 3720893,"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": 1625851830828.061, "dur": 5.427, + "args": { + "External id": 3720894,"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": 1625851830828.701, "dur": 4.228, + "args": { + "External id": 3720895,"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": 1625851830829.887, "dur": 2.879, + "args": { + "External id": 3720896,"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": 1625851830834.708, "dur": 9.361, + "args": { + "External id": 3720897,"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": 1625851830835.794, "dur": 7.870, + "args": { + "External id": 3720898,"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": 1625851830841.501, "dur": 2.086, + "args": { + "External id": 3720899,"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": 1625851830844.576, "dur": 44.283, + "args": { + "External id": 3720900,"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": 1625851830902.784, "dur": 30.280, + "args": { + "External id": 3720901,"Record function id": 0, "Sequence number": 37295225, "Fwd thread id": 1, "Ev Idx": 708 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1625851830904.300, "dur": 3.487, + "args": { + "External id": 3720902,"Sequence number": 37295225, "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": 1625851830904.300, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1381189, + "ts": 1625851830905.631, "dur": 2.016, + "args": { + "External id": 3720903,"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": 1625851830906.580, "dur": 0.942, + "args": { + "External id": 3720904,"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": 1625851830910.362, "dur": 19.837, + "args": { + "External id": 3720905,"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": 1625851830936.668, "dur": 11.465, + "args": { + "External id": 3720906,"Record function id": 0, "Sequence number": 37295224, "Fwd thread id": 1, "Ev Idx": 713 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1625851830938.062, "dur": 8.093, + "args": { + "External id": 3720907,"Sequence number": 37295224, "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": 1625851830938.062, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1381189, + "ts": 1625851830939.412, "dur": 6.550, + "args": { + "External id": 3720908,"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": 1625851830940.462, "dur": 4.995, + "args": { + "External id": 3720909,"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": 1625851830944.937, "dur": 0.441, + "args": { + "External id": 3720910,"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": 1625851830951.862, "dur": 5.406, + "args": { + "External id": 3720911,"Record function id": 0, "Ev Idx": 718 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625851830953.490, "dur": 3.223, + "args": { + "External id": 3720912,"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": 1625851830954.450, "dur": 1.941, + "args": { + "External id": 3720913,"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": 1625851830955.121, "dur": 1.189, + "args": { + "External id": 3720914,"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": 1625851830963.306, "dur": 463.066, + "args": { + "External id": 3720915,"Record function id": 0, "Sequence number": 37295223, "Fwd thread id": 1, "Ev Idx": 722 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1625851830965.103, "dur": 427.952, + "args": { + "External id": 3720916,"Sequence number": 37295223, "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": 1625851830965.103, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::contiguous", "pid": 1336756, "tid": 1381189, + "ts": 1625851831023.901, "dur": 42.515, + "args": { + "External id": 3720917,"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": 1625851831025.658, "dur": 40.553, + "args": { + "External id": 3720918,"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": 1625851831028.977, "dur": 9.322, + "args": { + "External id": 3720919,"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": 1625851831033.697, "dur": 3.849, + "args": { + "External id": 3720920,"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": 1625851831039.852, "dur": 25.885, + "args": { + "External id": 3720921,"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": 1625851831078.506, "dur": 4.460, + "args": { + "External id": 3720922,"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": 1625851831081.164, "dur": 1.705, + "args": { + "External id": 3720923,"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": 1625851831087.039, "dur": 3.469, + "args": { + "External id": 3720924,"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": 1625851831087.662, "dur": 2.750, + "args": { + "External id": 3720925,"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": 1625851831102.385, "dur": 2.489, + "args": { + "External id": 3720926,"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": 1625851831115.259, "dur": 2.518, + "args": { + "External id": 3720927,"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": 1625851831286.664, "dur": 1.971, + "args": { + "External id": 3720928,"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": 1625851831292.744, "dur": 31.616, + "args": { + "External id": 3720929,"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": 1625851831301.059, "dur": 1.054, + "args": { + "External id": 3720930,"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": 1625851831329.424, "dur": 28.660, + "args": { + "External id": 3720931,"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": 1625851831331.425, "dur": 26.443, + "args": { + "External id": 3720932,"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": 1625851831336.622, "dur": 3.885, + "args": { + "External id": 3720933,"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": 1625851831341.871, "dur": 15.475, + "args": { + "External id": 3720934,"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": 1625851831362.208, "dur": 5.192, + "args": { + "External id": 3720935,"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": 1625851831366.027, "dur": 1.233, + "args": { + "External id": 3720936,"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": 1625851831373.196, "dur": 2.473, + "args": { + "External id": 3720937,"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": 1625851831374.005, "dur": 1.559, + "args": { + "External id": 3720938,"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": 1625851831379.783, "dur": 4.578, + "args": { + "External id": 3720939,"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": 1625851831380.764, "dur": 3.506, + "args": { + "External id": 3720940,"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": 1625851831406.965, "dur": 18.023, + "args": { + "External id": 3720941,"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": 1625851831438.871, "dur": 10.919, + "args": { + "External id": 3720942,"Record function id": 0, "Ev Idx": 749 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625851831440.739, "dur": 8.445, + "args": { + "External id": 3720943,"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": 1625851831442.971, "dur": 5.394, + "args": { + "External id": 3720944,"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": 1625851831446.399, "dur": 1.855, + "args": { + "External id": 3720945,"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": 1625851831453.163, "dur": 7.622, + "args": { + "External id": 3720946,"Record function id": 0, "Sequence number": 37295222, "Fwd thread id": 1, "Ev Idx": 753 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1625851831453.985, "dur": 4.005, + "args": { + "External id": 3720947,"Sequence number": 37295222, "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": 1625851831453.985, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1381189, + "ts": 1625851831455.805, "dur": 2.013, + "args": { + "External id": 3720948,"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": 1625851831456.584, "dur": 1.099, + "args": { + "External id": 3720949,"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": 1625851831464.184, "dur": 127.159, + "args": { + "External id": 3720950,"Record function id": 0, "Sequence number": 37295221, "Fwd thread id": 1, "Ev Idx": 757 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1625851831464.876, "dur": 120.895, + "args": { + "External id": 3720951,"Sequence number": 37295221, "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": 1625851831464.876, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1381189, + "ts": 1625851831468.413, "dur": 8.771, + "args": { + "External id": 3720952,"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": 1625851831471.556, "dur": 5.007, + "args": { + "External id": 3720953,"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": 1625851831475.583, "dur": 0.826, + "args": { + "External id": 3720954,"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": 1625851831478.325, "dur": 55.856, + "args": { + "External id": 3720955,"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": 1625851831535.312, "dur": 4.509, + "args": { + "External id": 3720956,"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": 1625851831536.065, "dur": 3.209, + "args": { + "External id": 3720957,"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": 1625851831537.107, "dur": 2.029, + "args": { + "External id": 3720958,"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": 1625851831542.988, "dur": 2.948, + "args": { + "External id": 3720959,"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": 1625851831544.225, "dur": 1.272, + "args": { + "External id": 3720960,"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": 1625851831544.974, "dur": 0.406, + "args": { + "External id": 3720961,"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": 1625851831546.375, "dur": 38.710, + "args": { + "External id": 3720962,"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": 1625851831596.058, "dur": 10.671, + "args": { + "External id": 3720963,"Record function id": 0, "Sequence number": 37295220, "Fwd thread id": 1, "Ev Idx": 770 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1625851831597.124, "dur": 7.687, + "args": { + "External id": 3720964,"Sequence number": 37295220, "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": 1625851831597.124, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1381189, + "ts": 1625851831600.422, "dur": 4.240, + "args": { + "External id": 3720965,"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": 1625851831601.107, "dur": 3.422, + "args": { + "External id": 3720966,"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": 1625851831611.858, "dur": 8.600, + "args": { + "External id": 3720967,"Record function id": 0, "Sequence number": 37295219, "Fwd thread id": 1, "Ev Idx": 774 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1625851831614.918, "dur": 3.949, + "args": { + "External id": 3720968,"Sequence number": 37295219, "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": 1625851831614.918, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1381189, + "ts": 1625851831615.851, "dur": 2.813, + "args": { + "External id": 3720969,"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": 1625851831616.448, "dur": 1.773, + "args": { + "External id": 3720970,"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": 1625851831617.725, "dur": 0.410, + "args": { + "External id": 3720971,"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": 1625851831624.178, "dur": 4.834, + "args": { + "External id": 3720972,"Record function id": 0, "Ev Idx": 779 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625851831625.468, "dur": 3.039, + "args": { + "External id": 3720973,"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": 1625851831626.385, "dur": 1.856, + "args": { + "External id": 3720974,"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": 1625851831626.841, "dur": 1.316, + "args": { + "External id": 3720975,"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": 1625851831632.185, "dur": 10.123, + "args": { + "External id": 3720976,"Record function id": 0, "Sequence number": 37295218, "Fwd thread id": 1, "Ev Idx": 783 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1625851831633.107, "dur": 6.890, + "args": { + "External id": 3720977,"Sequence number": 37295218, "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": 1625851831633.107, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1381189, + "ts": 1625851831636.341, "dur": 3.504, + "args": { + "External id": 3720978,"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": 1625851831638.582, "dur": 1.150, + "args": { + "External id": 3720979,"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": 1625851831646.016, "dur": 300.757, + "args": { + "External id": 3720980,"Record function id": 0, "Sequence number": 37295217, "Fwd thread id": 1, "Ev Idx": 787 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "FlashAttnFuncBackward", "pid": 1336756, "tid": 1381189, + "ts": 1625851831647.148, "dur": 281.405, + "args": { + "External id": 3720981,"Sequence number": 37295217, "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": 1625851831647.148, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336756, "tid": 1381189, + "ts": 1625851831660.106, "dur": 5.103, + "args": { + "External id": 3720982,"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": 1625851831661.880, "dur": 2.887, + "args": { + "External id": 3720983,"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": 1625851831667.181, "dur": 5.428, + "args": { + "External id": 3720984,"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": 1625851831670.469, "dur": 1.938, + "args": { + "External id": 3720985,"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": 1625851831674.164, "dur": 23.984, + "args": { + "External id": 3720986,"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": 1625851831675.081, "dur": 22.534, + "args": { + "External id": 3720987,"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": 1625851831727.022, "dur": 176.720, + "args": { + "External id": 3720988,"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": 1625851831810.034, "dur": 3.664, + "args": { + "External id": 3720989,"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": 1625851831815.476, "dur": 4.190, + "args": { + "External id": 3720990,"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": 1625851831915.504, "dur": 4.142, + "args": { + "External id": 3720991,"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": 1625851831922.533, "dur": 0.816, + "args": { + "External id": 3720992,"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": 1625851831925.246, "dur": 0.832, + "args": { + "External id": 3720993,"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": 1625851831955.666, "dur": 271.738, + "args": { + "External id": 3720994,"Record function id": 0, "Sequence number": 37295216, "Fwd thread id": 1, "Ev Idx": 801 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1625851831957.405, "dur": 263.533, + "args": { + "External id": 3720995,"Sequence number": 37295216, "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": 1625851831957.405, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 1336756, "tid": 1381189, + "ts": 1625851831978.089, "dur": 84.942, + "args": { + "External id": 3720996,"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": 1625851831980.553, "dur": 2.734, + "args": { + "External id": 3720997,"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": 1625851832019.808, "dur": 42.403, + "args": { + "External id": 3720998,"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": 1625851832074.734, "dur": 7.355, + "args": { + "External id": 3720999,"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": 1625851832078.781, "dur": 2.990, + "args": { + "External id": 3721000,"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": 1625851832235.798, "dur": 150.394, + "args": { + "External id": 3721001,"Record function id": 0, "Sequence number": 37295215, "Fwd thread id": 1, "Ev Idx": 808 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1625851832237.699, "dur": 143.027, + "args": { + "External id": 3721002,"Sequence number": 37295215, "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": 1625851832237.699, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 1336756, "tid": 1381189, + "ts": 1625851832250.283, "dur": 31.447, + "args": { + "External id": 3721003,"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": 1625851832252.658, "dur": 2.687, + "args": { + "External id": 3721004,"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": 1625851832256.554, "dur": 24.721, + "args": { + "External id": 3721005,"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": 1625851832288.655, "dur": 7.423, + "args": { + "External id": 3721006,"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": 1625851832293.640, "dur": 2.178, + "args": { + "External id": 3721007,"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": 1625851832392.079, "dur": 13.813, + "args": { + "External id": 3721008,"Record function id": 0, "Sequence number": 37295214, "Fwd thread id": 1, "Ev Idx": 815 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1625851832393.217, "dur": 10.487, + "args": { + "External id": 3721009,"Sequence number": 37295214, "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": 1625851832393.217, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1381189, + "ts": 1625851832395.762, "dur": 7.613, + "args": { + "External id": 3721010,"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": 1625851832397.011, "dur": 6.161, + "args": { + "External id": 3721011,"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": 1625851832409.652, "dur": 10.362, + "args": { + "External id": 3721012,"Record function id": 0, "Sequence number": 37295213, "Fwd thread id": 1, "Ev Idx": 819 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1625851832413.522, "dur": 4.815, + "args": { + "External id": 3721013,"Sequence number": 37295213, "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": 1625851832413.522, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1381189, + "ts": 1625851832414.728, "dur": 3.465, + "args": { + "External id": 3721014,"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": 1625851832417.148, "dur": 0.939, + "args": { + "External id": 3721015,"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": 1625851832425.012, "dur": 5.079, + "args": { + "External id": 3721016,"Record function id": 0, "Sequence number": 37295212, "Fwd thread id": 1, "Ev Idx": 823 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1625851832425.664, "dur": 2.117, + "args": { + "External id": 3721017,"Sequence number": 37295212, "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": 1625851832425.664, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1381189, + "ts": 1625851832426.529, "dur": 1.103, + "args": { + "External id": 3721018,"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": 1625851832426.926, "dur": 0.618, + "args": { + "External id": 3721019,"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": 1625851832433.292, "dur": 9.839, + "args": { + "External id": 3721020,"Record function id": 0, "Sequence number": 37295211, "Fwd thread id": 1, "Ev Idx": 827 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1625851832434.272, "dur": 6.826, + "args": { + "External id": 3721021,"Sequence number": 37295211, "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": 1625851832434.272, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1381189, + "ts": 1625851832435.320, "dur": 5.613, + "args": { + "External id": 3721022,"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": 1625851832439.527, "dur": 1.294, + "args": { + "External id": 3721023,"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": 1625851832446.574, "dur": 142.179, + "args": { + "External id": 3721024,"Record function id": 0, "Sequence number": 37295210, "Fwd thread id": 1, "Ev Idx": 831 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1625851832447.343, "dur": 134.496, + "args": { + "External id": 3721025,"Sequence number": 37295210, "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": 1625851832447.343, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1381189, + "ts": 1625851832450.477, "dur": 6.099, + "args": { + "External id": 3721026,"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": 1625851832452.631, "dur": 3.318, + "args": { + "External id": 3721027,"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": 1625851832454.418, "dur": 1.302, + "args": { + "External id": 3721028,"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": 1625851832457.824, "dur": 64.909, + "args": { + "External id": 3721029,"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": 1625851832523.869, "dur": 6.299, + "args": { + "External id": 3721030,"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": 1625851832526.915, "dur": 2.561, + "args": { + "External id": 3721031,"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": 1625851832528.291, "dur": 1.041, + "args": { + "External id": 3721032,"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": 1625851832531.654, "dur": 5.288, + "args": { + "External id": 3721033,"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": 1625851832532.618, "dur": 3.484, + "args": { + "External id": 3721034,"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": 1625851832535.503, "dur": 0.519, + "args": { + "External id": 3721035,"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": 1625851832537.581, "dur": 43.414, + "args": { + "External id": 3721036,"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": 1625851832593.524, "dur": 8.381, + "args": { + "External id": 3721037,"Record function id": 0, "Sequence number": 37295209, "Fwd thread id": 1, "Ev Idx": 844 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1625851832594.313, "dur": 6.124, + "args": { + "External id": 3721038,"Sequence number": 37295209, "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": 1625851832594.313, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1381189, + "ts": 1625851832597.979, "dur": 2.310, + "args": { + "External id": 3721039,"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": 1625851832598.785, "dur": 1.353, + "args": { + "External id": 3721040,"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": 1625851832605.233, "dur": 6.509, + "args": { + "External id": 3721041,"Record function id": 0, "Sequence number": 37295208, "Fwd thread id": 1, "Ev Idx": 848 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1625851832605.939, "dur": 3.654, + "args": { + "External id": 3721042,"Sequence number": 37295208, "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": 1625851832605.939, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1381189, + "ts": 1625851832606.955, "dur": 2.439, + "args": { + "External id": 3721043,"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": 1625851832607.462, "dur": 1.475, + "args": { + "External id": 3721044,"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": 1625851832608.431, "dur": 0.377, + "args": { + "External id": 3721045,"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": 1625851832619.766, "dur": 10.806, + "args": { + "External id": 3721046,"Record function id": 0, "Ev Idx": 853 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625851832621.447, "dur": 8.477, + "args": { + "External id": 3721047,"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": 1625851832623.726, "dur": 5.719, + "args": { + "External id": 3721048,"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": 1625851832627.003, "dur": 2.339, + "args": { + "External id": 3721049,"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": 1625851832633.613, "dur": 5.809, + "args": { + "External id": 3721050,"Record function id": 0, "Sequence number": 37295207, "Fwd thread id": 1, "Ev Idx": 857 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1625851832634.403, "dur": 3.385, + "args": { + "External id": 3721051,"Sequence number": 37295207, "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": 1625851832634.403, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1381189, + "ts": 1625851832635.842, "dur": 1.778, + "args": { + "External id": 3721052,"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": 1625851832636.456, "dur": 1.054, + "args": { + "External id": 3721053,"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": 1625851832642.570, "dur": 117.679, + "args": { + "External id": 3721054,"Record function id": 0, "Sequence number": 37295206, "Fwd thread id": 1, "Ev Idx": 861 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1625851832643.338, "dur": 109.785, + "args": { + "External id": 3721055,"Sequence number": 37295206, "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": 1625851832643.338, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1381189, + "ts": 1625851832645.448, "dur": 4.478, + "args": { + "External id": 3721056,"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": 1625851832648.281, "dur": 1.249, + "args": { + "External id": 3721057,"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": 1625851832648.862, "dur": 0.554, + "args": { + "External id": 3721058,"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": 1625851832650.600, "dur": 45.654, + "args": { + "External id": 3721059,"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": 1625851832698.395, "dur": 6.601, + "args": { + "External id": 3721060,"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": 1625851832699.187, "dur": 5.058, + "args": { + "External id": 3721061,"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": 1625851832702.876, "dur": 1.241, + "args": { + "External id": 3721062,"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": 1625851832708.100, "dur": 5.053, + "args": { + "External id": 3721063,"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": 1625851832709.574, "dur": 3.159, + "args": { + "External id": 3721064,"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": 1625851832710.244, "dur": 2.362, + "args": { + "External id": 3721065,"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": 1625851832713.933, "dur": 38.381, + "args": { + "External id": 3721066,"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": 1625851832766.461, "dur": 35.894, + "args": { + "External id": 3721067,"Record function id": 0, "Sequence number": 37295205, "Fwd thread id": 1, "Ev Idx": 874 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1625851832767.508, "dur": 5.414, + "args": { + "External id": 3721068,"Sequence number": 37295205, "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": 1625851832767.508, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1381189, + "ts": 1625851832768.552, "dur": 4.223, + "args": { + "External id": 3721069,"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": 1625851832771.418, "dur": 1.261, + "args": { + "External id": 3721070,"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": 1625851832776.348, "dur": 21.762, + "args": { + "External id": 3721071,"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": 1625851832805.910, "dur": 7.308, + "args": { + "External id": 3721072,"Record function id": 0, "Sequence number": 37295204, "Fwd thread id": 1, "Ev Idx": 879 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1625851832807.011, "dur": 4.219, + "args": { + "External id": 3721073,"Sequence number": 37295204, "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": 1625851832807.011, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1381189, + "ts": 1625851832807.741, "dur": 3.252, + "args": { + "External id": 3721074,"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": 1625851832808.650, "dur": 1.864, + "args": { + "External id": 3721075,"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": 1625851832809.599, "dur": 0.756, + "args": { + "External id": 3721076,"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": 1625851832817.248, "dur": 8.163, + "args": { + "External id": 3721077,"Record function id": 0, "Ev Idx": 884 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625851832818.617, "dur": 6.279, + "args": { + "External id": 3721078,"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": 1625851832819.936, "dur": 4.643, + "args": { + "External id": 3721079,"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": 1625851832822.865, "dur": 1.604, + "args": { + "External id": 3721080,"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": 1625851832828.478, "dur": 7.497, + "args": { + "External id": 3721081,"Record function id": 0, "Sequence number": 37295203, "Fwd thread id": 1, "Ev Idx": 888 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1625851832829.203, "dur": 4.807, + "args": { + "External id": 3721082,"Sequence number": 37295203, "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": 1625851832829.203, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1381189, + "ts": 1625851832830.210, "dur": 3.657, + "args": { + "External id": 3721083,"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": 1625851832832.740, "dur": 1.037, + "args": { + "External id": 3721084,"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": 1625851832841.139, "dur": 97.992, + "args": { + "External id": 3721085,"Record function id": 0, "Sequence number": 37295202, "Fwd thread id": 1, "Ev Idx": 892 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1625851832842.571, "dur": 89.391, + "args": { + "External id": 3721086,"Sequence number": 37295202, "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": 1625851832842.571, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1381189, + "ts": 1625851832844.667, "dur": 4.696, + "args": { + "External id": 3721087,"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": 1625851832845.387, "dur": 3.563, + "args": { + "External id": 3721088,"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": 1625851832848.400, "dur": 0.420, + "args": { + "External id": 3721089,"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": 1625851832850.039, "dur": 28.717, + "args": { + "External id": 3721090,"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": 1625851832879.716, "dur": 3.124, + "args": { + "External id": 3721091,"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": 1625851832880.322, "dur": 2.017, + "args": { + "External id": 3721092,"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": 1625851832881.435, "dur": 0.787, + "args": { + "External id": 3721093,"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": 1625851832884.218, "dur": 11.372, + "args": { + "External id": 3721094,"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": 1625851832891.130, "dur": 4.101, + "args": { + "External id": 3721095,"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": 1625851832894.512, "dur": 0.654, + "args": { + "External id": 3721096,"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": 1625851832896.133, "dur": 35.161, + "args": { + "External id": 3721097,"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": 1625851832943.351, "dur": 23.880, + "args": { + "External id": 3721098,"Record function id": 0, "Sequence number": 37295201, "Fwd thread id": 1, "Ev Idx": 905 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1625851832944.448, "dur": 3.558, + "args": { + "External id": 3721099,"Sequence number": 37295201, "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": 1625851832944.448, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1381189, + "ts": 1625851832945.728, "dur": 2.133, + "args": { + "External id": 3721100,"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": 1625851832946.561, "dur": 1.203, + "args": { + "External id": 3721101,"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": 1625851832950.112, "dur": 14.861, + "args": { + "External id": 3721102,"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": 1625851832970.726, "dur": 11.360, + "args": { + "External id": 3721103,"Record function id": 0, "Sequence number": 37295200, "Fwd thread id": 1, "Ev Idx": 910 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1625851832973.995, "dur": 5.977, + "args": { + "External id": 3721104,"Sequence number": 37295200, "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": 1625851832973.995, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1381189, + "ts": 1625851832974.999, "dur": 4.776, + "args": { + "External id": 3721105,"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": 1625851832975.686, "dur": 3.629, + "args": { + "External id": 3721106,"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": 1625851832978.541, "dur": 0.656, + "args": { + "External id": 3721107,"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": 1625851833033.195, "dur": 7.982, + "args": { + "External id": 3721108,"Record function id": 0, "Ev Idx": 915 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625851833035.457, "dur": 4.976, + "args": { + "External id": 3721109,"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": 1625851833037.585, "dur": 2.461, + "args": { + "External id": 3721110,"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": 1625851833038.171, "dur": 1.655, + "args": { + "External id": 3721111,"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": 1625851833046.760, "dur": 372.922, + "args": { + "External id": 3721112,"Record function id": 0, "Sequence number": 37295199, "Fwd thread id": 1, "Ev Idx": 919 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1625851833047.939, "dur": 338.813, + "args": { + "External id": 3721113,"Sequence number": 37295199, "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": 1625851833047.939, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1381189, + "ts": 1625851833080.946, "dur": 4.396, + "args": { + "External id": 3721114,"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": 1625851833083.417, "dur": 1.770, + "args": { + "External id": 3721115,"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": 1625851833099.281, "dur": 6.633, + "args": { + "External id": 3721116,"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": 1625851833115.199, "dur": 1.827, + "args": { + "External id": 3721117,"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": 1625851833274.198, "dur": 1.871, + "args": { + "External id": 3721118,"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": 1625851833280.339, "dur": 37.225, + "args": { + "External id": 3721119,"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": 1625851833291.188, "dur": 0.955, + "args": { + "External id": 3721120,"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": 1625851833327.415, "dur": 36.816, + "args": { + "External id": 3721121,"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": 1625851833329.348, "dur": 34.669, + "args": { + "External id": 3721122,"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": 1625851833337.285, "dur": 5.656, + "args": { + "External id": 3721123,"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": 1625851833344.795, "dur": 18.628, + "args": { + "External id": 3721124,"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": 1625851833369.396, "dur": 2.413, + "args": { + "External id": 3721125,"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": 1625851833370.506, "dur": 1.104, + "args": { + "External id": 3721126,"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": 1625851833377.231, "dur": 2.557, + "args": { + "External id": 3721127,"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": 1625851833378.439, "dur": 1.246, + "args": { + "External id": 3721128,"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": 1625851833398.022, "dur": 17.444, + "args": { + "External id": 3721129,"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": 1625851833429.347, "dur": 11.399, + "args": { + "External id": 3721130,"Record function id": 0, "Ev Idx": 937 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625851833434.145, "dur": 5.916, + "args": { + "External id": 3721131,"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": 1625851833436.018, "dur": 3.161, + "args": { + "External id": 3721132,"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": 1625851833436.970, "dur": 2.122, + "args": { + "External id": 3721133,"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": 1625851833444.456, "dur": 6.425, + "args": { + "External id": 3721134,"Record function id": 0, "Sequence number": 37295198, "Fwd thread id": 1, "Ev Idx": 941 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "AddBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1625851833446.029, "dur": 1.161, + "args": { + "External id": 3721135,"Sequence number": 37295198, "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": 1625851833446.029, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: SwiGLULinearFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1625851833454.410, "dur": 471.172, + "args": { + "External id": 3721136,"Record function id": 0, "Sequence number": 37295197, "Fwd thread id": 1, "Ev Idx": 943 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SwiGLULinearFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1625851833455.324, "dur": 458.308, + "args": { + "External id": 3721137,"Sequence number": 37295197, "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": 1625851833455.324, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1381189, + "ts": 1625851833485.638, "dur": 7.908, + "args": { + "External id": 3721138,"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": 1625851833489.963, "dur": 3.335, + "args": { + "External id": 3721139,"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": 1625851833496.520, "dur": 9.285, + "args": { + "External id": 3721140,"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": 1625851833498.086, "dur": 7.028, + "args": { + "External id": 3721141,"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": 1625851833501.914, "dur": 3.022, + "args": { + "External id": 3721142,"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": 1625851833509.216, "dur": 101.272, + "args": { + "External id": 3721143,"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": 1625851833510.457, "dur": 3.637, + "args": { + "External id": 3721144,"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": 1625851833512.562, "dur": 1.097, + "args": { + "External id": 3721145,"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": 1625851833513.259, "dur": 0.320, + "args": { + "External id": 3721146,"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": 1625851833515.195, "dur": 94.894, + "args": { + "External id": 3721147,"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": 1625851833516.634, "dur": 92.508, + "args": { + "External id": 3721148,"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": 1625851833613.822, "dur": 2.457, + "args": { + "External id": 3721149,"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": 1625851833614.593, "dur": 1.569, + "args": { + "External id": 3721150,"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": 1625851833646.585, "dur": 4.576, + "args": { + "External id": 3721151,"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": 1625851833654.178, "dur": 1.929, + "args": { + "External id": 3721152,"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": 1625851833656.811, "dur": 1.542, + "args": { + "External id": 3721153,"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": 1625851833714.018, "dur": 2.772, + "args": { + "External id": 3721154,"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": 1625851833714.782, "dur": 1.727, + "args": { + "External id": 3721155,"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": 1625851833739.542, "dur": 155.194, + "args": { + "External id": 3721156,"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": 1625851833744.606, "dur": 10.424, + "args": { + "External id": 3721157,"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": 1625851833750.107, "dur": 3.944, + "args": { + "External id": 3721158,"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": 1625851833756.403, "dur": 8.603, + "args": { + "External id": 3721159,"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": 1625851833763.021, "dur": 0.570, + "args": { + "External id": 3721160,"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": 1625851833766.539, "dur": 1.940, + "args": { + "External id": 3721161,"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": 1625851833767.543, "dur": 0.565, + "args": { + "External id": 3721162,"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": 1625851833771.459, "dur": 1.887, + "args": { + "External id": 3721163,"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": 1625851833772.390, "dur": 0.524, + "args": { + "External id": 3721164,"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": 1625851833779.544, "dur": 2.059, + "args": { + "External id": 3721165,"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": 1625851833780.679, "dur": 0.658, + "args": { + "External id": 3721166,"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": 1625851833782.479, "dur": 7.708, + "args": { + "External id": 3721167,"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": 1625851833787.497, "dur": 2.510, + "args": { + "External id": 3721168,"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": 1625851833790.817, "dur": 3.857, + "args": { + "External id": 3721169,"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": 1625851833793.752, "dur": 0.668, + "args": { + "External id": 3721170,"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": 1625851833797.577, "dur": 4.074, + "args": { + "External id": 3721171,"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": 1625851833798.293, "dur": 3.260, + "args": { + "External id": 3721172,"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": 1625851833803.225, "dur": 76.177, + "args": { + "External id": 3721173,"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": 1625851833883.307, "dur": 1.398, + "args": { + "External id": 3721174,"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": 1625851833885.447, "dur": 4.883, + "args": { + "External id": 3721175,"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": 1625851833888.949, "dur": 0.745, + "args": { + "External id": 3721176,"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": 1625851833892.375, "dur": 1.043, + "args": { + "External id": 3721177,"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": 1625851833937.237, "dur": 9.043, + "args": { + "External id": 3721178,"Record function id": 0, "Ev Idx": 985 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625851833939.454, "dur": 6.205, + "args": { + "External id": 3721179,"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": 1625851833941.630, "dur": 3.147, + "args": { + "External id": 3721180,"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": 1625851833942.779, "dur": 1.890, + "args": { + "External id": 3721181,"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": 1625851833950.044, "dur": 9.143, + "args": { + "External id": 3721182,"Record function id": 0, "Sequence number": 37295196, "Fwd thread id": 1, "Ev Idx": 989 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1625851833951.042, "dur": 5.699, + "args": { + "External id": 3721183,"Sequence number": 37295196, "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": 1625851833951.042, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1381189, + "ts": 1625851833954.588, "dur": 1.945, + "args": { + "External id": 3721184,"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": 1625851833955.427, "dur": 0.973, + "args": { + "External id": 3721185,"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": 1625851833962.672, "dur": 220.608, + "args": { + "External id": 3721186,"Record function id": 0, "Sequence number": 37295195, "Fwd thread id": 1, "Ev Idx": 993 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1625851833963.430, "dur": 211.906, + "args": { + "External id": 3721187,"Sequence number": 37295195, "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": 1625851833963.430, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1381189, + "ts": 1625851833966.749, "dur": 6.290, + "args": { + "External id": 3721188,"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": 1625851833967.856, "dur": 4.613, + "args": { + "External id": 3721189,"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": 1625851833971.482, "dur": 0.847, + "args": { + "External id": 3721190,"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": 1625851833974.103, "dur": 101.161, + "args": { + "External id": 3721191,"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": 1625851834077.806, "dur": 7.046, + "args": { + "External id": 3721192,"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": 1625851834078.804, "dur": 5.092, + "args": { + "External id": 3721193,"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": 1625851834082.673, "dur": 1.070, + "args": { + "External id": 3721194,"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": 1625851834086.478, "dur": 7.225, + "args": { + "External id": 3721195,"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": 1625851834087.475, "dur": 5.620, + "args": { + "External id": 3721196,"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": 1625851834090.703, "dur": 2.272, + "args": { + "External id": 3721197,"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": 1625851834094.543, "dur": 80.136, + "args": { + "External id": 3721198,"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": 1625851834190.054, "dur": 9.371, + "args": { + "External id": 3721199,"Record function id": 0, "Sequence number": 37295194, "Fwd thread id": 1, "Ev Idx": 1006 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1625851834191.374, "dur": 6.430, + "args": { + "External id": 3721200,"Sequence number": 37295194, "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": 1625851834191.374, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1381189, + "ts": 1625851834193.030, "dur": 4.620, + "args": { + "External id": 3721201,"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": 1625851834195.942, "dur": 1.549, + "args": { + "External id": 3721202,"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": 1625851834202.797, "dur": 9.646, + "args": { + "External id": 3721203,"Record function id": 0, "Sequence number": 37295193, "Fwd thread id": 1, "Ev Idx": 1010 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1625851834204.150, "dur": 5.880, + "args": { + "External id": 3721204,"Sequence number": 37295193, "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": 1625851834204.150, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1381189, + "ts": 1625851834205.060, "dur": 4.777, + "args": { + "External id": 3721205,"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": 1625851834205.907, "dur": 3.479, + "args": { + "External id": 3721206,"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": 1625851834208.704, "dur": 0.554, + "args": { + "External id": 3721207,"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": 1625851834216.630, "dur": 6.059, + "args": { + "External id": 3721208,"Record function id": 0, "Ev Idx": 1015 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625851834218.167, "dur": 3.933, + "args": { + "External id": 3721209,"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": 1625851834219.632, "dur": 2.217, + "args": { + "External id": 3721210,"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": 1625851834220.331, "dur": 1.430, + "args": { + "External id": 3721211,"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": 1625851834228.031, "dur": 8.018, + "args": { + "External id": 3721212,"Record function id": 0, "Sequence number": 37295192, "Fwd thread id": 1, "Ev Idx": 1019 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1625851834229.046, "dur": 5.061, + "args": { + "External id": 3721213,"Sequence number": 37295192, "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": 1625851834229.046, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1381189, + "ts": 1625851834229.996, "dur": 3.946, + "args": { + "External id": 3721214,"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": 1625851834232.926, "dur": 0.888, + "args": { + "External id": 3721215,"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": 1625851834239.018, "dur": 141.261, + "args": { + "External id": 3721216,"Record function id": 0, "Sequence number": 37295191, "Fwd thread id": 1, "Ev Idx": 1023 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1625851834265.754, "dur": 107.890, + "args": { + "External id": 3721217,"Sequence number": 37295191, "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": 1625851834265.754, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1381189, + "ts": 1625851834270.624, "dur": 2.073, + "args": { + "External id": 3721218,"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": 1625851834271.113, "dur": 1.121, + "args": { + "External id": 3721219,"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": 1625851834271.740, "dur": 0.340, + "args": { + "External id": 3721220,"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": 1625851834273.213, "dur": 36.465, + "args": { + "External id": 3721221,"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": 1625851834310.692, "dur": 7.599, + "args": { + "External id": 3721222,"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": 1625851834311.237, "dur": 6.549, + "args": { + "External id": 3721223,"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": 1625851834313.868, "dur": 3.736, + "args": { + "External id": 3721224,"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": 1625851834319.174, "dur": 5.415, + "args": { + "External id": 3721225,"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": 1625851834320.351, "dur": 3.525, + "args": { + "External id": 3721226,"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": 1625851834323.482, "dur": 0.324, + "args": { + "External id": 3721227,"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": 1625851834325.000, "dur": 47.980, + "args": { + "External id": 3721228,"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": 1625851834384.675, "dur": 33.263, + "args": { + "External id": 3721229,"Record function id": 0, "Sequence number": 37295190, "Fwd thread id": 1, "Ev Idx": 1036 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1625851834385.513, "dur": 4.475, + "args": { + "External id": 3721230,"Sequence number": 37295190, "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": 1625851834385.513, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1381189, + "ts": 1625851834388.312, "dur": 1.532, + "args": { + "External id": 3721231,"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": 1625851834388.773, "dur": 0.974, + "args": { + "External id": 3721232,"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": 1625851834393.004, "dur": 21.779, + "args": { + "External id": 3721233,"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": 1625851834421.541, "dur": 7.989, + "args": { + "External id": 3721234,"Record function id": 0, "Sequence number": 37295189, "Fwd thread id": 1, "Ev Idx": 1041 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1625851834422.323, "dur": 5.196, + "args": { + "External id": 3721235,"Sequence number": 37295189, "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": 1625851834422.323, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1381189, + "ts": 1625851834422.884, "dur": 4.449, + "args": { + "External id": 3721236,"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": 1625851834423.408, "dur": 3.430, + "args": { + "External id": 3721237,"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": 1625851834426.260, "dur": 0.453, + "args": { + "External id": 3721238,"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": 1625851834433.052, "dur": 6.301, + "args": { + "External id": 3721239,"Record function id": 0, "Ev Idx": 1046 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625851834434.254, "dur": 4.646, + "args": { + "External id": 3721240,"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": 1625851834435.050, "dur": 3.588, + "args": { + "External id": 3721241,"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": 1625851834437.572, "dur": 0.933, + "args": { + "External id": 3721242,"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": 1625851834443.561, "dur": 432.914, + "args": { + "External id": 3721243,"Record function id": 0, "Sequence number": 37295188, "Fwd thread id": 1, "Ev Idx": 1050 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1625851834444.829, "dur": 400.429, + "args": { + "External id": 3721244,"Sequence number": 37295188, "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": 1625851834444.829, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::contiguous", "pid": 1336756, "tid": 1381189, + "ts": 1625851834467.949, "dur": 33.237, + "args": { + "External id": 3721245,"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": 1625851834469.263, "dur": 31.678, + "args": { + "External id": 3721246,"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": 1625851834471.805, "dur": 5.412, + "args": { + "External id": 3721247,"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": 1625851834474.061, "dur": 2.622, + "args": { + "External id": 3721248,"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": 1625851834478.540, "dur": 21.962, + "args": { + "External id": 3721249,"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": 1625851834513.508, "dur": 3.917, + "args": { + "External id": 3721250,"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": 1625851834514.206, "dur": 3.069, + "args": { + "External id": 3721251,"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": 1625851834521.418, "dur": 3.845, + "args": { + "External id": 3721252,"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": 1625851834524.385, "dur": 0.772, + "args": { + "External id": 3721253,"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": 1625851834536.297, "dur": 2.130, + "args": { + "External id": 3721254,"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": 1625851834549.345, "dur": 2.447, + "args": { + "External id": 3721255,"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": 1625851834728.112, "dur": 3.396, + "args": { + "External id": 3721256,"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": 1625851834737.543, "dur": 33.525, + "args": { + "External id": 3721257,"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": 1625851834746.991, "dur": 0.892, + "args": { + "External id": 3721258,"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": 1625851834776.672, "dur": 33.375, + "args": { + "External id": 3721259,"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": 1625851834780.614, "dur": 29.229, + "args": { + "External id": 3721260,"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": 1625851834786.540, "dur": 4.282, + "args": { + "External id": 3721261,"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": 1625851834792.154, "dur": 17.197, + "args": { + "External id": 3721262,"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": 1625851834814.511, "dur": 1.990, + "args": { + "External id": 3721263,"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": 1625851834815.552, "dur": 0.810, + "args": { + "External id": 3721264,"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": 1625851834822.839, "dur": 6.550, + "args": { + "External id": 3721265,"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": 1625851834825.796, "dur": 3.493, + "args": { + "External id": 3721266,"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": 1625851834831.332, "dur": 4.717, + "args": { + "External id": 3721267,"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": 1625851834834.806, "dur": 1.150, + "args": { + "External id": 3721268,"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": 1625851834858.454, "dur": 16.534, + "args": { + "External id": 3721269,"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": 1625851834888.229, "dur": 8.646, + "args": { + "External id": 3721270,"Record function id": 0, "Ev Idx": 1077 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625851834890.140, "dur": 6.094, + "args": { + "External id": 3721271,"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": 1625851834892.141, "dur": 3.131, + "args": { + "External id": 3721272,"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": 1625851834893.228, "dur": 1.977, + "args": { + "External id": 3721273,"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": 1625851834900.188, "dur": 9.043, + "args": { + "External id": 3721274,"Record function id": 0, "Sequence number": 37295187, "Fwd thread id": 1, "Ev Idx": 1081 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1625851834901.255, "dur": 5.646, + "args": { + "External id": 3721275,"Sequence number": 37295187, "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": 1625851834901.255, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1381189, + "ts": 1625851834904.754, "dur": 1.952, + "args": { + "External id": 3721276,"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": 1625851834905.554, "dur": 1.058, + "args": { + "External id": 3721277,"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": 1625851834912.551, "dur": 176.248, + "args": { + "External id": 3721278,"Record function id": 0, "Sequence number": 37295186, "Fwd thread id": 1, "Ev Idx": 1085 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1625851834913.324, "dur": 167.004, + "args": { + "External id": 3721279,"Sequence number": 37295186, "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": 1625851834913.324, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1381189, + "ts": 1625851834916.226, "dur": 6.426, + "args": { + "External id": 3721280,"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": 1625851834917.872, "dur": 4.266, + "args": { + "External id": 3721281,"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": 1625851834921.218, "dur": 0.779, + "args": { + "External id": 3721282,"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": 1625851834923.932, "dur": 53.703, + "args": { + "External id": 3721283,"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": 1625851834978.662, "dur": 43.220, + "args": { + "External id": 3721284,"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": 1625851834979.446, "dur": 41.460, + "args": { + "External id": 3721285,"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": 1625851834982.767, "dur": 37.446, + "args": { + "External id": 3721286,"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": 1625851835024.350, "dur": 5.785, + "args": { + "External id": 3721287,"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": 1625851835025.649, "dur": 4.051, + "args": { + "External id": 3721288,"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": 1625851835029.192, "dur": 0.436, + "args": { + "External id": 3721289,"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": 1625851835030.915, "dur": 48.673, + "args": { + "External id": 3721290,"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": 1625851835095.799, "dur": 10.613, + "args": { + "External id": 3721291,"Record function id": 0, "Sequence number": 37295185, "Fwd thread id": 1, "Ev Idx": 1098 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1625851835096.988, "dur": 7.640, + "args": { + "External id": 3721292,"Sequence number": 37295185, "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": 1625851835096.988, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1381189, + "ts": 1625851835098.423, "dur": 6.052, + "args": { + "External id": 3721293,"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": 1625851835100.965, "dur": 3.414, + "args": { + "External id": 3721294,"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": 1625851835111.430, "dur": 9.234, + "args": { + "External id": 3721295,"Record function id": 0, "Sequence number": 37295184, "Fwd thread id": 1, "Ev Idx": 1102 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1625851835112.565, "dur": 6.407, + "args": { + "External id": 3721296,"Sequence number": 37295184, "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": 1625851835112.565, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1381189, + "ts": 1625851835113.830, "dur": 4.941, + "args": { + "External id": 3721297,"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": 1625851835114.444, "dur": 3.827, + "args": { + "External id": 3721298,"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": 1625851835117.587, "dur": 0.574, + "args": { + "External id": 3721299,"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": 1625851835124.773, "dur": 5.478, + "args": { + "External id": 3721300,"Record function id": 0, "Ev Idx": 1107 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625851835125.899, "dur": 3.811, + "args": { + "External id": 3721301,"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": 1625851835127.144, "dur": 2.272, + "args": { + "External id": 3721302,"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": 1625851835127.872, "dur": 1.450, + "args": { + "External id": 3721303,"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": 1625851835135.567, "dur": 5.630, + "args": { + "External id": 3721304,"Record function id": 0, "Sequence number": 37295183, "Fwd thread id": 1, "Ev Idx": 1111 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1625851835136.256, "dur": 2.776, + "args": { + "External id": 3721305,"Sequence number": 37295183, "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": 1625851835136.256, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1381189, + "ts": 1625851835137.300, "dur": 1.575, + "args": { + "External id": 3721306,"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": 1625851835137.660, "dur": 1.087, + "args": { + "External id": 3721307,"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": 1625851835147.342, "dur": 296.575, + "args": { + "External id": 3721308,"Record function id": 0, "Sequence number": 37295182, "Fwd thread id": 1, "Ev Idx": 1115 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "FlashAttnFuncBackward", "pid": 1336756, "tid": 1381189, + "ts": 1625851835148.539, "dur": 278.420, + "args": { + "External id": 3721309,"Sequence number": 37295182, "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": 1625851835148.539, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336756, "tid": 1381189, + "ts": 1625851835164.650, "dur": 6.478, + "args": { + "External id": 3721310,"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": 1625851835166.823, "dur": 3.856, + "args": { + "External id": 3721311,"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": 1625851835172.996, "dur": 7.337, + "args": { + "External id": 3721312,"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": 1625851835176.480, "dur": 3.681, + "args": { + "External id": 3721313,"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": 1625851835190.589, "dur": 5.618, + "args": { + "External id": 3721314,"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": 1625851835194.120, "dur": 1.896, + "args": { + "External id": 3721315,"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": 1625851835225.535, "dur": 176.857, + "args": { + "External id": 3721316,"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": 1625851835307.608, "dur": 5.563, + "args": { + "External id": 3721317,"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": 1625851835314.646, "dur": 4.137, + "args": { + "External id": 3721318,"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": 1625851835414.426, "dur": 3.400, + "args": { + "External id": 3721319,"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": 1625851835420.775, "dur": 0.918, + "args": { + "External id": 3721320,"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": 1625851835423.612, "dur": 0.960, + "args": { + "External id": 3721321,"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": 1625851835451.033, "dur": 218.675, + "args": { + "External id": 3721322,"Record function id": 0, "Sequence number": 37295181, "Fwd thread id": 1, "Ev Idx": 1129 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1625851835452.476, "dur": 211.314, + "args": { + "External id": 3721323,"Sequence number": 37295181, "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": 1625851835452.476, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 1336756, "tid": 1381189, + "ts": 1625851835469.354, "dur": 43.388, + "args": { + "External id": 3721324,"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": 1625851835471.920, "dur": 2.783, + "args": { + "External id": 3721325,"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": 1625851835476.218, "dur": 36.020, + "args": { + "External id": 3721326,"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": 1625851835521.681, "dur": 6.089, + "args": { + "External id": 3721327,"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": 1625851835525.024, "dur": 2.424, + "args": { + "External id": 3721328,"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": 1625851835695.120, "dur": 178.823, + "args": { + "External id": 3721329,"Record function id": 0, "Sequence number": 37295180, "Fwd thread id": 1, "Ev Idx": 1136 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1625851835698.168, "dur": 169.343, + "args": { + "External id": 3721330,"Sequence number": 37295180, "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": 1625851835698.168, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 1336756, "tid": 1381189, + "ts": 1625851835713.080, "dur": 52.550, + "args": { + "External id": 3721331,"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": 1625851835715.405, "dur": 3.975, + "args": { + "External id": 3721332,"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": 1625851835725.597, "dur": 39.522, + "args": { + "External id": 3721333,"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": 1625851835773.438, "dur": 5.413, + "args": { + "External id": 3721334,"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": 1625851835776.534, "dur": 2.050, + "args": { + "External id": 3721335,"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": 1625851835881.703, "dur": 17.485, + "args": { + "External id": 3721336,"Record function id": 0, "Sequence number": 37295179, "Fwd thread id": 1, "Ev Idx": 1143 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1625851835883.092, "dur": 13.647, + "args": { + "External id": 3721337,"Sequence number": 37295179, "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": 1625851835883.092, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1381189, + "ts": 1625851835885.231, "dur": 11.225, + "args": { + "External id": 3721338,"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": 1625851835888.898, "dur": 7.345, + "args": { + "External id": 3721339,"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": 1625851835902.980, "dur": 8.489, + "args": { + "External id": 3721340,"Record function id": 0, "Sequence number": 37295178, "Fwd thread id": 1, "Ev Idx": 1147 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1625851835904.165, "dur": 5.304, + "args": { + "External id": 3721341,"Sequence number": 37295178, "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": 1625851835904.165, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1381189, + "ts": 1625851835905.172, "dur": 4.148, + "args": { + "External id": 3721342,"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": 1625851835908.342, "dur": 0.831, + "args": { + "External id": 3721343,"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": 1625851835914.610, "dur": 5.688, + "args": { + "External id": 3721344,"Record function id": 0, "Sequence number": 37295177, "Fwd thread id": 1, "Ev Idx": 1151 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1625851835915.297, "dur": 2.919, + "args": { + "External id": 3721345,"Sequence number": 37295177, "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": 1625851835915.297, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1381189, + "ts": 1625851835916.388, "dur": 1.689, + "args": { + "External id": 3721346,"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": 1625851835917.164, "dur": 0.824, + "args": { + "External id": 3721347,"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": 1625851835924.111, "dur": 9.029, + "args": { + "External id": 3721348,"Record function id": 0, "Sequence number": 37295176, "Fwd thread id": 1, "Ev Idx": 1155 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1625851835924.819, "dur": 6.486, + "args": { + "External id": 3721349,"Sequence number": 37295176, "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": 1625851835924.819, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1381189, + "ts": 1625851835925.690, "dur": 5.470, + "args": { + "External id": 3721350,"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": 1625851835930.111, "dur": 0.947, + "args": { + "External id": 3721351,"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": 1625851835936.551, "dur": 195.979, + "args": { + "External id": 3721352,"Record function id": 0, "Sequence number": 37295175, "Fwd thread id": 1, "Ev Idx": 1159 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1625851835937.581, "dur": 187.102, + "args": { + "External id": 3721353,"Sequence number": 37295175, "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": 1625851835937.581, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1381189, + "ts": 1625851835940.816, "dur": 6.353, + "args": { + "External id": 3721354,"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": 1625851835942.689, "dur": 3.824, + "args": { + "External id": 3721355,"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": 1625851835944.862, "dur": 1.409, + "args": { + "External id": 3721356,"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": 1625851835950.754, "dur": 104.119, + "args": { + "External id": 3721357,"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": 1625851836057.546, "dur": 5.927, + "args": { + "External id": 3721358,"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": 1625851836058.679, "dur": 3.801, + "args": { + "External id": 3721359,"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": 1625851836060.416, "dur": 1.942, + "args": { + "External id": 3721360,"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": 1625851836065.427, "dur": 6.486, + "args": { + "External id": 3721361,"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": 1625851836067.064, "dur": 4.205, + "args": { + "External id": 3721362,"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": 1625851836070.762, "dur": 0.436, + "args": { + "External id": 3721363,"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": 1625851836074.826, "dur": 48.989, + "args": { + "External id": 3721364,"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": 1625851836141.566, "dur": 7.046, + "args": { + "External id": 3721365,"Record function id": 0, "Sequence number": 37295174, "Fwd thread id": 1, "Ev Idx": 1172 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1625851836142.534, "dur": 4.106, + "args": { + "External id": 3721366,"Sequence number": 37295174, "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": 1625851836142.534, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1381189, + "ts": 1625851836144.062, "dur": 2.437, + "args": { + "External id": 3721367,"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": 1625851836145.023, "dur": 1.334, + "args": { + "External id": 3721368,"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": 1625851836152.081, "dur": 8.086, + "args": { + "External id": 3721369,"Record function id": 0, "Sequence number": 37295173, "Fwd thread id": 1, "Ev Idx": 1176 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1625851836152.730, "dur": 5.616, + "args": { + "External id": 3721370,"Sequence number": 37295173, "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": 1625851836152.730, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1381189, + "ts": 1625851836153.741, "dur": 4.391, + "args": { + "External id": 3721371,"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": 1625851836154.319, "dur": 3.345, + "args": { + "External id": 3721372,"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": 1625851836157.105, "dur": 0.460, + "args": { + "External id": 3721373,"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": 1625851836168.256, "dur": 8.889, + "args": { + "External id": 3721374,"Record function id": 0, "Ev Idx": 1181 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625851836169.957, "dur": 6.506, + "args": { + "External id": 3721375,"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": 1625851836172.356, "dur": 3.762, + "args": { + "External id": 3721376,"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": 1625851836173.384, "dur": 2.563, + "args": { + "External id": 3721377,"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": 1625851836180.492, "dur": 5.343, + "args": { + "External id": 3721378,"Record function id": 0, "Sequence number": 37295172, "Fwd thread id": 1, "Ev Idx": 1185 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1625851836181.357, "dur": 2.540, + "args": { + "External id": 3721379,"Sequence number": 37295172, "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": 1625851836181.357, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1381189, + "ts": 1625851836182.241, "dur": 1.497, + "args": { + "External id": 3721380,"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": 1625851836182.830, "dur": 0.780, + "args": { + "External id": 3721381,"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": 1625851836189.037, "dur": 95.204, + "args": { + "External id": 3721382,"Record function id": 0, "Sequence number": 37295171, "Fwd thread id": 1, "Ev Idx": 1189 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1625851836190.163, "dur": 88.652, + "args": { + "External id": 3721383,"Sequence number": 37295171, "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": 1625851836190.163, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1381189, + "ts": 1625851836194.014, "dur": 2.786, + "args": { + "External id": 3721384,"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": 1625851836194.748, "dur": 1.626, + "args": { + "External id": 3721385,"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": 1625851836195.635, "dur": 0.597, + "args": { + "External id": 3721386,"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": 1625851836197.468, "dur": 30.116, + "args": { + "External id": 3721387,"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": 1625851836228.612, "dur": 7.760, + "args": { + "External id": 3721388,"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": 1625851836229.398, "dur": 6.467, + "args": { + "External id": 3721389,"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": 1625851836235.016, "dur": 0.747, + "args": { + "External id": 3721390,"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": 1625851836237.761, "dur": 4.494, + "args": { + "External id": 3721391,"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": 1625851836238.542, "dur": 3.332, + "args": { + "External id": 3721392,"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": 1625851836239.580, "dur": 2.230, + "args": { + "External id": 3721393,"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": 1625851836242.684, "dur": 35.357, + "args": { + "External id": 3721394,"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": 1625851836288.592, "dur": 36.279, + "args": { + "External id": 3721395,"Record function id": 0, "Sequence number": 37295170, "Fwd thread id": 1, "Ev Idx": 1202 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1625851836289.589, "dur": 7.185, + "args": { + "External id": 3721396,"Sequence number": 37295170, "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": 1625851836289.589, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1381189, + "ts": 1625851836292.842, "dur": 3.787, + "args": { + "External id": 3721397,"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": 1625851836295.499, "dur": 0.997, + "args": { + "External id": 3721398,"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": 1625851836299.791, "dur": 22.722, + "args": { + "External id": 3721399,"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": 1625851836331.224, "dur": 6.296, + "args": { + "External id": 3721400,"Record function id": 0, "Sequence number": 37295169, "Fwd thread id": 1, "Ev Idx": 1207 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1625851836332.164, "dur": 3.581, + "args": { + "External id": 3721401,"Sequence number": 37295169, "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": 1625851836332.164, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1381189, + "ts": 1625851836333.031, "dur": 2.542, + "args": { + "External id": 3721402,"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": 1625851836333.624, "dur": 1.480, + "args": { + "External id": 3721403,"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": 1625851836334.567, "dur": 0.423, + "args": { + "External id": 3721404,"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": 1625851836341.420, "dur": 6.656, + "args": { + "External id": 3721405,"Record function id": 0, "Ev Idx": 1212 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625851836342.473, "dur": 5.096, + "args": { + "External id": 3721406,"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": 1625851836343.551, "dur": 3.568, + "args": { + "External id": 3721407,"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": 1625851836345.913, "dur": 1.117, + "args": { + "External id": 3721408,"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": 1625851836351.452, "dur": 10.489, + "args": { + "External id": 3721409,"Record function id": 0, "Sequence number": 37295168, "Fwd thread id": 1, "Ev Idx": 1216 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1625851836352.222, "dur": 8.114, + "args": { + "External id": 3721410,"Sequence number": 37295168, "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": 1625851836352.222, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1381189, + "ts": 1625851836352.975, "dur": 7.219, + "args": { + "External id": 3721411,"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": 1625851836359.240, "dur": 0.826, + "args": { + "External id": 3721412,"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": 1625851836365.039, "dur": 89.504, + "args": { + "External id": 3721413,"Record function id": 0, "Sequence number": 37295167, "Fwd thread id": 1, "Ev Idx": 1220 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1625851836365.892, "dur": 81.212, + "args": { + "External id": 3721414,"Sequence number": 37295167, "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": 1625851836365.892, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1381189, + "ts": 1625851836370.221, "dur": 1.853, + "args": { + "External id": 3721415,"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": 1625851836370.574, "dur": 1.115, + "args": { + "External id": 3721416,"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": 1625851836371.184, "dur": 0.384, + "args": { + "External id": 3721417,"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": 1625851836372.528, "dur": 27.811, + "args": { + "External id": 3721418,"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": 1625851836401.179, "dur": 7.045, + "args": { + "External id": 3721419,"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": 1625851836401.727, "dur": 5.924, + "args": { + "External id": 3721420,"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": 1625851836404.955, "dur": 2.543, + "args": { + "External id": 3721421,"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": 1625851836409.085, "dur": 4.518, + "args": { + "External id": 3721422,"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": 1625851836409.865, "dur": 3.352, + "args": { + "External id": 3721423,"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": 1625851836412.655, "dur": 0.462, + "args": { + "External id": 3721424,"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": 1625851836414.032, "dur": 32.448, + "args": { + "External id": 3721425,"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": 1625851836458.556, "dur": 22.639, + "args": { + "External id": 3721426,"Record function id": 0, "Sequence number": 37295166, "Fwd thread id": 1, "Ev Idx": 1233 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1625851836459.489, "dur": 3.103, + "args": { + "External id": 3721427,"Sequence number": 37295166, "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": 1625851836459.489, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1381189, + "ts": 1625851836460.628, "dur": 1.817, + "args": { + "External id": 3721428,"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": 1625851836461.195, "dur": 1.105, + "args": { + "External id": 3721429,"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": 1625851836464.809, "dur": 14.509, + "args": { + "External id": 3721430,"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": 1625851836486.532, "dur": 6.831, + "args": { + "External id": 3721431,"Record function id": 0, "Sequence number": 37295165, "Fwd thread id": 1, "Ev Idx": 1238 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1625851836487.415, "dur": 3.884, + "args": { + "External id": 3721432,"Sequence number": 37295165, "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": 1625851836487.415, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1381189, + "ts": 1625851836488.361, "dur": 2.775, + "args": { + "External id": 3721433,"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": 1625851836489.222, "dur": 1.434, + "args": { + "External id": 3721434,"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": 1625851836490.088, "dur": 0.402, + "args": { + "External id": 3721435,"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": 1625851836498.945, "dur": 3.958, + "args": { + "External id": 3721436,"Record function id": 0, "Ev Idx": 1243 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625851836499.924, "dur": 2.528, + "args": { + "External id": 3721437,"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": 1625851836500.650, "dur": 1.532, + "args": { + "External id": 3721438,"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": 1625851836501.053, "dur": 1.017, + "args": { + "External id": 3721439,"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": 1625851836508.834, "dur": 372.473, + "args": { + "External id": 3721440,"Record function id": 0, "Sequence number": 37295164, "Fwd thread id": 1, "Ev Idx": 1247 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1625851836509.976, "dur": 340.070, + "args": { + "External id": 3721441,"Sequence number": 37295164, "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": 1625851836509.976, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1381189, + "ts": 1625851836541.727, "dur": 1.566, + "args": { + "External id": 3721442,"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": 1625851836542.259, "dur": 0.881, + "args": { + "External id": 3721443,"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": 1625851836556.921, "dur": 5.387, + "args": { + "External id": 3721444,"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": 1625851836571.087, "dur": 1.718, + "args": { + "External id": 3721445,"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": 1625851836738.293, "dur": 2.810, + "args": { + "External id": 3721446,"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": 1625851836745.749, "dur": 37.460, + "args": { + "External id": 3721447,"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": 1625851836757.026, "dur": 1.111, + "args": { + "External id": 3721448,"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": 1625851836789.010, "dur": 36.861, + "args": { + "External id": 3721449,"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": 1625851836793.233, "dur": 32.421, + "args": { + "External id": 3721450,"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": 1625851836798.980, "dur": 5.857, + "args": { + "External id": 3721451,"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": 1625851836806.759, "dur": 18.463, + "args": { + "External id": 3721452,"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": 1625851836830.343, "dur": 2.163, + "args": { + "External id": 3721453,"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": 1625851836831.330, "dur": 1.080, + "args": { + "External id": 3721454,"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": 1625851836838.675, "dur": 3.980, + "args": { + "External id": 3721455,"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": 1625851836841.728, "dur": 0.789, + "args": { + "External id": 3721456,"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": 1625851836859.649, "dur": 17.522, + "args": { + "External id": 3721457,"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": 1625851836893.830, "dur": 8.670, + "args": { + "External id": 3721458,"Record function id": 0, "Ev Idx": 1265 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625851836895.921, "dur": 5.857, + "args": { + "External id": 3721459,"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": 1625851836897.832, "dur": 3.006, + "args": { + "External id": 3721460,"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": 1625851836898.805, "dur": 1.968, + "args": { + "External id": 3721461,"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": 1625851836905.847, "dur": 5.855, + "args": { + "External id": 3721462,"Record function id": 0, "Sequence number": 37295163, "Fwd thread id": 1, "Ev Idx": 1269 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "AddBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1625851836907.326, "dur": 1.536, + "args": { + "External id": 3721463,"Sequence number": 37295163, "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": 1625851836907.326, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "autograd::engine::evaluate_function: SwiGLULinearFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1625851836915.396, "dur": 469.033, + "args": { + "External id": 3721464,"Record function id": 0, "Sequence number": 37295162, "Fwd thread id": 1, "Ev Idx": 1271 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "SwiGLULinearFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1625851836918.502, "dur": 454.531, + "args": { + "External id": 3721465,"Sequence number": 37295162, "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": 1625851836918.502, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1381189, + "ts": 1625851836950.298, "dur": 8.110, + "args": { + "External id": 3721466,"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": 1625851836954.900, "dur": 3.272, + "args": { + "External id": 3721467,"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": 1625851836961.398, "dur": 6.850, + "args": { + "External id": 3721468,"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": 1625851836963.014, "dur": 4.617, + "args": { + "External id": 3721469,"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": 1625851836964.630, "dur": 2.863, + "args": { + "External id": 3721470,"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": 1625851836971.735, "dur": 132.924, + "args": { + "External id": 3721471,"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": 1625851836974.468, "dur": 5.028, + "args": { + "External id": 3721472,"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": 1625851836975.188, "dur": 3.889, + "args": { + "External id": 3721473,"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": 1625851836978.164, "dur": 0.807, + "args": { + "External id": 3721474,"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": 1625851836980.620, "dur": 123.333, + "args": { + "External id": 3721475,"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": 1625851836982.016, "dur": 120.334, + "args": { + "External id": 3721476,"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": 1625851837110.020, "dur": 3.603, + "args": { + "External id": 3721477,"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": 1625851837111.439, "dur": 2.064, + "args": { + "External id": 3721478,"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": 1625851837146.631, "dur": 6.496, + "args": { + "External id": 3721479,"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": 1625851837156.269, "dur": 2.034, + "args": { + "External id": 3721480,"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": 1625851837159.128, "dur": 1.946, + "args": { + "External id": 3721481,"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": 1625851837194.879, "dur": 2.407, + "args": { + "External id": 3721482,"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": 1625851837195.845, "dur": 1.281, + "args": { + "External id": 3721483,"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": 1625851837220.466, "dur": 132.253, + "args": { + "External id": 3721484,"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": 1625851837225.876, "dur": 12.464, + "args": { + "External id": 3721485,"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": 1625851837231.756, "dur": 5.715, + "args": { + "External id": 3721486,"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": 1625851837239.801, "dur": 6.091, + "args": { + "External id": 3721487,"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": 1625851837244.417, "dur": 0.753, + "args": { + "External id": 3721488,"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": 1625851837247.525, "dur": 2.058, + "args": { + "External id": 3721489,"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": 1625851837248.596, "dur": 0.635, + "args": { + "External id": 3721490,"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": 1625851837251.925, "dur": 2.500, + "args": { + "External id": 3721491,"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": 1625851837252.975, "dur": 0.594, + "args": { + "External id": 3721492,"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": 1625851837257.802, "dur": 4.560, + "args": { + "External id": 3721493,"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": 1625851837261.318, "dur": 0.789, + "args": { + "External id": 3721494,"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": 1625851837263.361, "dur": 7.451, + "args": { + "External id": 3721495,"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": 1625851837268.152, "dur": 2.470, + "args": { + "External id": 3721496,"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": 1625851837273.525, "dur": 3.242, + "args": { + "External id": 3721497,"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": 1625851837276.091, "dur": 0.424, + "args": { + "External id": 3721498,"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": 1625851837277.618, "dur": 4.215, + "args": { + "External id": 3721499,"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": 1625851837278.351, "dur": 3.394, + "args": { + "External id": 3721500,"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": 1625851837283.393, "dur": 54.599, + "args": { + "External id": 3721501,"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": 1625851837342.182, "dur": 1.127, + "args": { + "External id": 3721502,"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": 1625851837344.039, "dur": 2.347, + "args": { + "External id": 3721503,"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": 1625851837345.174, "dur": 0.668, + "args": { + "External id": 3721504,"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": 1625851837350.388, "dur": 1.194, + "args": { + "External id": 3721505,"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": 1625851837395.484, "dur": 9.599, + "args": { + "External id": 3721506,"Record function id": 0, "Ev Idx": 1313 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625851837397.673, "dur": 6.744, + "args": { + "External id": 3721507,"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": 1625851837400.129, "dur": 3.533, + "args": { + "External id": 3721508,"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": 1625851837401.351, "dur": 2.222, + "args": { + "External id": 3721509,"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": 1625851837408.862, "dur": 6.723, + "args": { + "External id": 3721510,"Record function id": 0, "Sequence number": 37295161, "Fwd thread id": 1, "Ev Idx": 1317 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1625851837410.253, "dur": 3.333, + "args": { + "External id": 3721511,"Sequence number": 37295161, "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": 1625851837410.253, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1381189, + "ts": 1625851837411.450, "dur": 1.916, + "args": { + "External id": 3721512,"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": 1625851837412.315, "dur": 0.964, + "args": { + "External id": 3721513,"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": 1625851837419.022, "dur": 122.462, + "args": { + "External id": 3721514,"Record function id": 0, "Sequence number": 37295160, "Fwd thread id": 1, "Ev Idx": 1321 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1625851837419.959, "dur": 115.222, + "args": { + "External id": 3721515,"Sequence number": 37295160, "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": 1625851837419.959, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1381189, + "ts": 1625851837422.670, "dur": 5.732, + "args": { + "External id": 3721516,"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": 1625851837423.901, "dur": 3.907, + "args": { + "External id": 3721517,"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": 1625851837427.082, "dur": 0.574, + "args": { + "External id": 3721518,"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": 1625851837429.622, "dur": 40.394, + "args": { + "External id": 3721519,"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": 1625851837471.343, "dur": 6.132, + "args": { + "External id": 3721520,"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": 1625851837472.365, "dur": 4.317, + "args": { + "External id": 3721521,"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": 1625851837475.406, "dur": 1.138, + "args": { + "External id": 3721522,"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": 1625851837479.157, "dur": 7.838, + "args": { + "External id": 3721523,"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": 1625851837482.664, "dur": 3.923, + "args": { + "External id": 3721524,"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": 1625851837483.917, "dur": 2.607, + "args": { + "External id": 3721525,"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": 1625851837487.478, "dur": 46.990, + "args": { + "External id": 3721526,"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": 1625851837546.597, "dur": 6.124, + "args": { + "External id": 3721527,"Record function id": 0, "Sequence number": 37295159, "Fwd thread id": 1, "Ev Idx": 1334 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1625851837547.579, "dur": 3.604, + "args": { + "External id": 3721528,"Sequence number": 37295159, "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": 1625851837547.579, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1381189, + "ts": 1625851837549.029, "dur": 2.005, + "args": { + "External id": 3721529,"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": 1625851837549.578, "dur": 1.321, + "args": { + "External id": 3721530,"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": 1625851837556.104, "dur": 11.256, + "args": { + "External id": 3721531,"Record function id": 0, "Sequence number": 37295158, "Fwd thread id": 1, "Ev Idx": 1338 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1625851837557.209, "dur": 7.983, + "args": { + "External id": 3721532,"Sequence number": 37295158, "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": 1625851837557.209, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1381189, + "ts": 1625851837559.943, "dur": 5.053, + "args": { + "External id": 3721533,"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": 1625851837560.729, "dur": 3.806, + "args": { + "External id": 3721534,"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": 1625851837563.910, "dur": 0.482, + "args": { + "External id": 3721535,"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": 1625851837571.253, "dur": 5.266, + "args": { + "External id": 3721536,"Record function id": 0, "Ev Idx": 1343 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625851837572.367, "dur": 3.631, + "args": { + "External id": 3721537,"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": 1625851837573.303, "dur": 2.482, + "args": { + "External id": 3721538,"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": 1625851837574.197, "dur": 1.496, + "args": { + "External id": 3721539,"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": 1625851837579.470, "dur": 7.582, + "args": { + "External id": 3721540,"Record function id": 0, "Sequence number": 37295157, "Fwd thread id": 1, "Ev Idx": 1347 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1625851837580.538, "dur": 4.627, + "args": { + "External id": 3721541,"Sequence number": 37295157, "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": 1625851837580.538, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1381189, + "ts": 1625851837581.341, "dur": 3.701, + "args": { + "External id": 3721542,"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": 1625851837584.210, "dur": 0.714, + "args": { + "External id": 3721543,"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": 1625851837590.090, "dur": 135.585, + "args": { + "External id": 3721544,"Record function id": 0, "Sequence number": 37295156, "Fwd thread id": 1, "Ev Idx": 1351 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1625851837590.909, "dur": 126.139, + "args": { + "External id": 3721545,"Sequence number": 37295156, "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": 1625851837590.909, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1381189, + "ts": 1625851837593.107, "dur": 5.379, + "args": { + "External id": 3721546,"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": 1625851837593.860, "dur": 4.205, + "args": { + "External id": 3721547,"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": 1625851837597.429, "dur": 0.512, + "args": { + "External id": 3721548,"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": 1625851837599.053, "dur": 31.571, + "args": { + "External id": 3721549,"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": 1625851837633.896, "dur": 5.190, + "args": { + "External id": 3721550,"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": 1625851837634.415, "dur": 4.109, + "args": { + "External id": 3721551,"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": 1625851837635.156, "dur": 3.236, + "args": { + "External id": 3721552,"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": 1625851837640.379, "dur": 3.355, + "args": { + "External id": 3721553,"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": 1625851837641.657, "dur": 1.684, + "args": { + "External id": 3721554,"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": 1625851837642.663, "dur": 0.602, + "args": { + "External id": 3721555,"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": 1625851837646.803, "dur": 68.951, + "args": { + "External id": 3721556,"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": 1625851837734.705, "dur": 36.631, + "args": { + "External id": 3721557,"Record function id": 0, "Sequence number": 37295155, "Fwd thread id": 1, "Ev Idx": 1364 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1625851837735.806, "dur": 6.498, + "args": { + "External id": 3721558,"Sequence number": 37295155, "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": 1625851837735.806, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1381189, + "ts": 1625851837739.705, "dur": 2.460, + "args": { + "External id": 3721559,"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": 1625851837740.445, "dur": 1.590, + "args": { + "External id": 3721560,"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": 1625851837745.166, "dur": 23.082, + "args": { + "External id": 3721561,"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": 1625851837775.171, "dur": 10.752, + "args": { + "External id": 3721562,"Record function id": 0, "Sequence number": 37295154, "Fwd thread id": 1, "Ev Idx": 1369 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1625851837776.489, "dur": 7.197, + "args": { + "External id": 3721563,"Sequence number": 37295154, "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": 1625851837776.489, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1381189, + "ts": 1625851837777.479, "dur": 5.979, + "args": { + "External id": 3721564,"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": 1625851837778.555, "dur": 4.351, + "args": { + "External id": 3721565,"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": 1625851837782.277, "dur": 0.532, + "args": { + "External id": 3721566,"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": 1625851837790.005, "dur": 7.690, + "args": { + "External id": 3721567,"Record function id": 0, "Ev Idx": 1374 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625851837793.256, "dur": 3.939, + "args": { + "External id": 3721568,"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": 1625851837794.568, "dur": 2.289, + "args": { + "External id": 3721569,"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": 1625851837795.454, "dur": 1.309, + "args": { + "External id": 3721570,"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": 1625851837802.021, "dur": 464.403, + "args": { + "External id": 3721571,"Record function id": 0, "Sequence number": 37295153, "Fwd thread id": 1, "Ev Idx": 1378 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1625851837807.920, "dur": 420.932, + "args": { + "External id": 3721572,"Sequence number": 37295153, "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": 1625851837807.920, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::contiguous", "pid": 1336756, "tid": 1381189, + "ts": 1625851837831.840, "dur": 33.745, + "args": { + "External id": 3721573,"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": 1625851837833.330, "dur": 32.051, + "args": { + "External id": 3721574,"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": 1625851837835.947, "dur": 5.806, + "args": { + "External id": 3721575,"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": 1625851837838.335, "dur": 2.898, + "args": { + "External id": 3721576,"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": 1625851837842.900, "dur": 21.927, + "args": { + "External id": 3721577,"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": 1625851837878.693, "dur": 6.258, + "args": { + "External id": 3721578,"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": 1625851837881.668, "dur": 3.130, + "args": { + "External id": 3721579,"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": 1625851837888.659, "dur": 1.711, + "args": { + "External id": 3721580,"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": 1625851837889.310, "dur": 0.954, + "args": { + "External id": 3721581,"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": 1625851837903.450, "dur": 2.462, + "args": { + "External id": 3721582,"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": 1625851837916.638, "dur": 3.460, + "args": { + "External id": 3721583,"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": 1625851838108.850, "dur": 5.167, + "args": { + "External id": 3721584,"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": 1625851838118.713, "dur": 35.564, + "args": { + "External id": 3721585,"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": 1625851838130.139, "dur": 1.154, + "args": { + "External id": 3721586,"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": 1625851838159.547, "dur": 31.462, + "args": { + "External id": 3721587,"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": 1625851838161.570, "dur": 29.234, + "args": { + "External id": 3721588,"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": 1625851838165.217, "dur": 3.828, + "args": { + "External id": 3721589,"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": 1625851838173.089, "dur": 17.225, + "args": { + "External id": 3721590,"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": 1625851838195.586, "dur": 4.804, + "args": { + "External id": 3721591,"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": 1625851838198.948, "dur": 1.347, + "args": { + "External id": 3721592,"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": 1625851838207.007, "dur": 4.456, + "args": { + "External id": 3721593,"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": 1625851838207.758, "dur": 3.597, + "args": { + "External id": 3721594,"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": 1625851838213.361, "dur": 4.244, + "args": { + "External id": 3721595,"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": 1625851838216.539, "dur": 0.975, + "args": { + "External id": 3721596,"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": 1625851838243.847, "dur": 21.053, + "args": { + "External id": 3721597,"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": 1625851838278.445, "dur": 9.013, + "args": { + "External id": 3721598,"Record function id": 0, "Ev Idx": 1405 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625851838280.697, "dur": 6.054, + "args": { + "External id": 3721599,"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": 1625851838282.884, "dur": 2.913, + "args": { + "External id": 3721600,"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": 1625851838283.925, "dur": 1.783, + "args": { + "External id": 3721601,"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": 1625851838290.900, "dur": 9.556, + "args": { + "External id": 3721602,"Record function id": 0, "Sequence number": 37295152, "Fwd thread id": 1, "Ev Idx": 1409 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1625851838291.858, "dur": 5.784, + "args": { + "External id": 3721603,"Sequence number": 37295152, "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": 1625851838291.858, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1381189, + "ts": 1625851838293.382, "dur": 4.051, + "args": { + "External id": 3721604,"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": 1625851838296.172, "dur": 1.095, + "args": { + "External id": 3721605,"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": 1625851838303.710, "dur": 134.585, + "args": { + "External id": 3721606,"Record function id": 0, "Sequence number": 37295151, "Fwd thread id": 1, "Ev Idx": 1413 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1625851838304.656, "dur": 128.012, + "args": { + "External id": 3721607,"Sequence number": 37295151, "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": 1625851838304.656, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1381189, + "ts": 1625851838307.576, "dur": 4.840, + "args": { + "External id": 3721608,"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": 1625851838309.011, "dur": 2.769, + "args": { + "External id": 3721609,"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": 1625851838310.423, "dur": 1.098, + "args": { + "External id": 3721610,"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": 1625851838313.618, "dur": 59.650, + "args": { + "External id": 3721611,"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": 1625851838376.248, "dur": 8.536, + "args": { + "External id": 3721612,"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": 1625851838377.372, "dur": 6.873, + "args": { + "External id": 3721613,"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": 1625851838381.257, "dur": 2.836, + "args": { + "External id": 3721614,"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": 1625851838386.080, "dur": 3.158, + "args": { + "External id": 3721615,"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": 1625851838387.265, "dur": 1.316, + "args": { + "External id": 3721616,"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": 1625851838388.122, "dur": 0.387, + "args": { + "External id": 3721617,"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": 1625851838391.899, "dur": 39.888, + "args": { + "External id": 3721618,"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": 1625851838443.335, "dur": 10.611, + "args": { + "External id": 3721619,"Record function id": 0, "Sequence number": 37295150, "Fwd thread id": 1, "Ev Idx": 1426 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1625851838444.286, "dur": 7.957, + "args": { + "External id": 3721620,"Sequence number": 37295150, "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": 1625851838444.286, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1381189, + "ts": 1625851838445.539, "dur": 6.556, + "args": { + "External id": 3721621,"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": 1625851838448.149, "dur": 3.798, + "args": { + "External id": 3721622,"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": 1625851838457.648, "dur": 8.833, + "args": { + "External id": 3721623,"Record function id": 0, "Sequence number": 37295149, "Fwd thread id": 1, "Ev Idx": 1430 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1625851838458.487, "dur": 6.101, + "args": { + "External id": 3721624,"Sequence number": 37295149, "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": 1625851838458.487, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1381189, + "ts": 1625851838459.390, "dur": 5.000, + "args": { + "External id": 3721625,"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": 1625851838460.292, "dur": 3.607, + "args": { + "External id": 3721626,"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": 1625851838463.246, "dur": 0.548, + "args": { + "External id": 3721627,"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": 1625851838470.106, "dur": 5.349, + "args": { + "External id": 3721628,"Record function id": 0, "Ev Idx": 1435 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625851838471.315, "dur": 3.648, + "args": { + "External id": 3721629,"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": 1625851838472.416, "dur": 2.320, + "args": { + "External id": 3721630,"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": 1625851838473.234, "dur": 1.417, + "args": { + "External id": 3721631,"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": 1625851838478.530, "dur": 6.077, + "args": { + "External id": 3721632,"Record function id": 0, "Sequence number": 37295148, "Fwd thread id": 1, "Ev Idx": 1439 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1625851838479.599, "dur": 3.280, + "args": { + "External id": 3721633,"Sequence number": 37295148, "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": 1625851838479.599, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1381189, + "ts": 1625851838480.846, "dur": 1.874, + "args": { + "External id": 3721634,"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": 1625851838481.454, "dur": 1.144, + "args": { + "External id": 3721635,"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": 1625851838488.343, "dur": 306.496, + "args": { + "External id": 3721636,"Record function id": 0, "Sequence number": 37295147, "Fwd thread id": 1, "Ev Idx": 1443 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "FlashAttnFuncBackward", "pid": 1336756, "tid": 1381189, + "ts": 1625851838491.776, "dur": 285.368, + "args": { + "External id": 3721637,"Sequence number": 37295147, "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": 1625851838491.776, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336756, "tid": 1381189, + "ts": 1625851838505.822, "dur": 8.480, + "args": { + "External id": 3721638,"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": 1625851838510.652, "dur": 3.243, + "args": { + "External id": 3721639,"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": 1625851838516.180, "dur": 5.187, + "args": { + "External id": 3721640,"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": 1625851838518.992, "dur": 2.173, + "args": { + "External id": 3721641,"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": 1625851838522.838, "dur": 2.641, + "args": { + "External id": 3721642,"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": 1625851838523.685, "dur": 1.613, + "args": { + "External id": 3721643,"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": 1625851838549.416, "dur": 201.079, + "args": { + "External id": 3721644,"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": 1625851838630.742, "dur": 5.123, + "args": { + "External id": 3721645,"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": 1625851838639.586, "dur": 3.940, + "args": { + "External id": 3721646,"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": 1625851838763.817, "dur": 3.754, + "args": { + "External id": 3721647,"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": 1625851838770.986, "dur": 0.596, + "args": { + "External id": 3721648,"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": 1625851838773.806, "dur": 0.701, + "args": { + "External id": 3721649,"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": 1625851838804.548, "dur": 274.613, + "args": { + "External id": 3721650,"Record function id": 0, "Sequence number": 37295146, "Fwd thread id": 1, "Ev Idx": 1457 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1625851838806.309, "dur": 264.284, + "args": { + "External id": 3721651,"Sequence number": 37295146, "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": 1625851838806.309, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 1336756, "tid": 1381189, + "ts": 1625851838825.512, "dur": 54.386, + "args": { + "External id": 3721652,"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": 1625851838830.604, "dur": 3.445, + "args": { + "External id": 3721653,"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": 1625851838835.389, "dur": 43.698, + "args": { + "External id": 3721654,"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": 1625851838889.340, "dur": 4.293, + "args": { + "External id": 3721655,"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": 1625851838890.943, "dur": 2.357, + "args": { + "External id": 3721656,"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": 1625851839089.290, "dur": 163.129, + "args": { + "External id": 3721657,"Record function id": 0, "Sequence number": 37295145, "Fwd thread id": 1, "Ev Idx": 1464 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1625851839093.773, "dur": 152.908, + "args": { + "External id": 3721658,"Sequence number": 37295145, "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": 1625851839093.773, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::clone", "pid": 1336756, "tid": 1381189, + "ts": 1625851839107.222, "dur": 36.054, + "args": { + "External id": 3721659,"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": 1625851839109.936, "dur": 3.359, + "args": { + "External id": 3721660,"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": 1625851839114.197, "dur": 28.452, + "args": { + "External id": 3721661,"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": 1625851839150.646, "dur": 4.906, + "args": { + "External id": 3721662,"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": 1625851839152.107, "dur": 3.153, + "args": { + "External id": 3721663,"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": 1625851839258.453, "dur": 16.992, + "args": { + "External id": 3721664,"Record function id": 0, "Sequence number": 37295144, "Fwd thread id": 1, "Ev Idx": 1471 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1625851839259.899, "dur": 13.076, + "args": { + "External id": 3721665,"Sequence number": 37295144, "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": 1625851839259.899, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1381189, + "ts": 1625851839264.946, "dur": 7.757, + "args": { + "External id": 3721666,"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": 1625851839266.192, "dur": 6.337, + "args": { + "External id": 3721667,"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": 1625851839278.890, "dur": 6.032, + "args": { + "External id": 3721668,"Record function id": 0, "Sequence number": 37295143, "Fwd thread id": 1, "Ev Idx": 1475 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1625851839279.978, "dur": 2.975, + "args": { + "External id": 3721669,"Sequence number": 37295143, "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": 1625851839279.978, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1381189, + "ts": 1625851839280.929, "dur": 1.891, + "args": { + "External id": 3721670,"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": 1625851839281.677, "dur": 1.001, + "args": { + "External id": 3721671,"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": 1625851839288.018, "dur": 9.088, + "args": { + "External id": 3721672,"Record function id": 0, "Sequence number": 37295142, "Fwd thread id": 1, "Ev Idx": 1479 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1625851839288.914, "dur": 6.556, + "args": { + "External id": 3721673,"Sequence number": 37295142, "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": 1625851839288.914, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1381189, + "ts": 1625851839293.645, "dur": 1.688, + "args": { + "External id": 3721674,"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": 1625851839294.419, "dur": 0.829, + "args": { + "External id": 3721675,"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": 1625851839300.362, "dur": 6.092, + "args": { + "External id": 3721676,"Record function id": 0, "Sequence number": 37295141, "Fwd thread id": 1, "Ev Idx": 1483 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1625851839301.179, "dur": 3.172, + "args": { + "External id": 3721677,"Sequence number": 37295141, "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": 1625851839301.179, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1381189, + "ts": 1625851839302.032, "dur": 2.192, + "args": { + "External id": 3721678,"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": 1625851839303.185, "dur": 0.941, + "args": { + "External id": 3721679,"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": 1625851839309.715, "dur": 148.054, + "args": { + "External id": 3721680,"Record function id": 0, "Sequence number": 37295140, "Fwd thread id": 1, "Ev Idx": 1487 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1625851839310.461, "dur": 140.523, + "args": { + "External id": 3721681,"Sequence number": 37295140, "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": 1625851839310.461, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1381189, + "ts": 1625851839314.235, "dur": 10.595, + "args": { + "External id": 3721682,"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": 1625851839318.498, "dur": 5.642, + "args": { + "External id": 3721683,"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": 1625851839322.178, "dur": 1.732, + "args": { + "External id": 3721684,"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": 1625851839326.459, "dur": 67.017, + "args": { + "External id": 3721685,"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": 1625851839394.870, "dur": 4.564, + "args": { + "External id": 3721686,"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": 1625851839395.706, "dur": 2.649, + "args": { + "External id": 3721687,"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": 1625851839396.748, "dur": 1.452, + "args": { + "External id": 3721688,"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": 1625851839401.154, "dur": 5.022, + "args": { + "External id": 3721689,"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": 1625851839404.334, "dur": 1.352, + "args": { + "External id": 3721690,"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": 1625851839405.241, "dur": 0.365, + "args": { + "External id": 3721691,"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": 1625851839406.695, "dur": 43.440, + "args": { + "External id": 3721692,"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": 1625851839462.739, "dur": 8.191, + "args": { + "External id": 3721693,"Record function id": 0, "Sequence number": 37295139, "Fwd thread id": 1, "Ev Idx": 1500 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1625851839463.668, "dur": 5.579, + "args": { + "External id": 3721694,"Sequence number": 37295139, "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": 1625851839463.668, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1381189, + "ts": 1625851839467.145, "dur": 1.960, + "args": { + "External id": 3721695,"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": 1625851839467.982, "dur": 1.031, + "args": { + "External id": 3721696,"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": 1625851839474.325, "dur": 9.465, + "args": { + "External id": 3721697,"Record function id": 0, "Sequence number": 37295138, "Fwd thread id": 1, "Ev Idx": 1504 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1625851839475.185, "dur": 6.778, + "args": { + "External id": 3721698,"Sequence number": 37295138, "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": 1625851839475.185, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1381189, + "ts": 1625851839478.758, "dur": 3.000, + "args": { + "External id": 3721699,"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": 1625851839479.683, "dur": 1.577, + "args": { + "External id": 3721700,"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": 1625851839480.660, "dur": 0.491, + "args": { + "External id": 3721701,"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": 1625851839489.556, "dur": 8.246, + "args": { + "External id": 3721702,"Record function id": 0, "Ev Idx": 1509 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625851839490.748, "dur": 6.365, + "args": { + "External id": 3721703,"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": 1625851839493.049, "dur": 3.633, + "args": { + "External id": 3721704,"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": 1625851839494.005, "dur": 2.572, + "args": { + "External id": 3721705,"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": 1625851839501.136, "dur": 9.167, + "args": { + "External id": 3721706,"Record function id": 0, "Sequence number": 37295137, "Fwd thread id": 1, "Ev Idx": 1513 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1625851839503.985, "dur": 4.803, + "args": { + "External id": 3721707,"Sequence number": 37295137, "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": 1625851839503.985, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1381189, + "ts": 1625851839505.196, "dur": 3.435, + "args": { + "External id": 3721708,"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": 1625851839507.829, "dur": 0.683, + "args": { + "External id": 3721709,"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": 1625851839513.350, "dur": 94.537, + "args": { + "External id": 3721710,"Record function id": 0, "Sequence number": 37295136, "Fwd thread id": 1, "Ev Idx": 1517 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1625851839514.018, "dur": 88.274, + "args": { + "External id": 3721711,"Sequence number": 37295136, "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": 1625851839514.018, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1381189, + "ts": 1625851839516.143, "dur": 2.769, + "args": { + "External id": 3721712,"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": 1625851839516.958, "dur": 1.515, + "args": { + "External id": 3721713,"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": 1625851839517.898, "dur": 0.474, + "args": { + "External id": 3721714,"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": 1625851839519.637, "dur": 27.883, + "args": { + "External id": 3721715,"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": 1625851839550.672, "dur": 3.834, + "args": { + "External id": 3721716,"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": 1625851839551.743, "dur": 2.237, + "args": { + "External id": 3721717,"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": 1625851839552.552, "dur": 1.302, + "args": { + "External id": 3721718,"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": 1625851839555.769, "dur": 9.037, + "args": { + "External id": 3721719,"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": 1625851839557.072, "dur": 7.165, + "args": { + "External id": 3721720,"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": 1625851839559.828, "dur": 4.318, + "args": { + "External id": 3721721,"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": 1625851839567.983, "dur": 33.626, + "args": { + "External id": 3721722,"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": 1625851839614.114, "dur": 35.137, + "args": { + "External id": 3721723,"Record function id": 0, "Sequence number": 37295135, "Fwd thread id": 1, "Ev Idx": 1530 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1625851839615.058, "dur": 7.368, + "args": { + "External id": 3721724,"Sequence number": 37295135, "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": 1625851839615.058, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1381189, + "ts": 1625851839616.514, "dur": 5.755, + "args": { + "External id": 3721725,"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": 1625851839620.912, "dur": 1.252, + "args": { + "External id": 3721726,"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": 1625851839625.167, "dur": 21.821, + "args": { + "External id": 3721727,"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": 1625851839652.806, "dur": 56.000, + "args": { + "External id": 3721728,"Record function id": 0, "Sequence number": 37295134, "Fwd thread id": 1, "Ev Idx": 1535 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1625851839695.375, "dur": 10.357, + "args": { + "External id": 3721729,"Sequence number": 37295134, "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": 1625851839695.375, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1381189, + "ts": 1625851839699.175, "dur": 6.347, + "args": { + "External id": 3721730,"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": 1625851839700.344, "dur": 4.408, + "args": { + "External id": 3721731,"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": 1625851839703.839, "dur": 0.634, + "args": { + "External id": 3721732,"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": 1625851839714.902, "dur": 6.151, + "args": { + "External id": 3721733,"Record function id": 0, "Ev Idx": 1540 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625851839716.454, "dur": 4.024, + "args": { + "External id": 3721734,"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": 1625851839717.818, "dur": 2.312, + "args": { + "External id": 3721735,"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": 1625851839718.509, "dur": 1.525, + "args": { + "External id": 3721736,"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": 1625851839724.029, "dur": 7.615, + "args": { + "External id": 3721737,"Record function id": 0, "Sequence number": 37295133, "Fwd thread id": 1, "Ev Idx": 1544 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "UnsafeViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1625851839724.912, "dur": 5.093, + "args": { + "External id": 3721738,"Sequence number": 37295133, "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": 1625851839724.912, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1381189, + "ts": 1625851839726.031, "dur": 3.826, + "args": { + "External id": 3721739,"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": 1625851839728.742, "dur": 1.022, + "args": { + "External id": 3721740,"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": 1625851839734.695, "dur": 100.059, + "args": { + "External id": 3721741,"Record function id": 0, "Sequence number": 37295132, "Fwd thread id": 1, "Ev Idx": 1548 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "MmBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1625851839735.393, "dur": 90.919, + "args": { + "External id": 3721742,"Sequence number": 37295132, "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": 1625851839735.393, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1381189, + "ts": 1625851839737.515, "dur": 3.922, + "args": { + "External id": 3721743,"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": 1625851839737.973, "dur": 3.059, + "args": { + "External id": 3721744,"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": 1625851839740.400, "dur": 0.515, + "args": { + "External id": 3721745,"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": 1625851839742.157, "dur": 34.477, + "args": { + "External id": 3721746,"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": 1625851839779.425, "dur": 2.757, + "args": { + "External id": 3721747,"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": 1625851839780.223, "dur": 1.477, + "args": { + "External id": 3721748,"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": 1625851839780.946, "dur": 0.641, + "args": { + "External id": 3721749,"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": 1625851839783.550, "dur": 2.444, + "args": { + "External id": 3721750,"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": 1625851839784.441, "dur": 1.153, + "args": { + "External id": 3721751,"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": 1625851839785.150, "dur": 0.378, + "args": { + "External id": 3721752,"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": 1625851839789.040, "dur": 36.619, + "args": { + "External id": 3721753,"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": 1625851839839.450, "dur": 28.090, + "args": { + "External id": 3721754,"Record function id": 0, "Sequence number": 37295131, "Fwd thread id": 1, "Ev Idx": 1561 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "ViewBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1625851839840.294, "dur": 4.764, + "args": { + "External id": 3721755,"Sequence number": 37295131, "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": 1625851839840.294, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1381189, + "ts": 1625851839843.372, "dur": 1.540, + "args": { + "External id": 3721756,"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": 1625851839843.845, "dur": 0.971, + "args": { + "External id": 3721757,"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": 1625851839847.427, "dur": 18.309, + "args": { + "External id": 3721758,"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": 1625851839871.192, "dur": 8.490, + "args": { + "External id": 3721759,"Record function id": 0, "Sequence number": 37295130, "Fwd thread id": 1, "Ev Idx": 1566 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "TBackward0", "pid": 1336756, "tid": 1381189, + "ts": 1625851839872.023, "dur": 5.718, + "args": { + "External id": 3721760,"Sequence number": 37295130, "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": 1625851839872.023, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::t", "pid": 1336756, "tid": 1381189, + "ts": 1625851839873.019, "dur": 4.519, + "args": { + "External id": 3721761,"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": 1625851839873.630, "dur": 3.396, + "args": { + "External id": 3721762,"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": 1625851839876.332, "dur": 0.572, + "args": { + "External id": 3721763,"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": 1625851839883.599, "dur": 4.479, + "args": { + "External id": 3721764,"Record function id": 0, "Ev Idx": 1571 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625851839884.654, "dur": 2.947, + "args": { + "External id": 3721765,"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": 1625851839885.692, "dur": 1.589, + "args": { + "External id": 3721766,"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": 1625851839886.089, "dur": 1.089, + "args": { + "External id": 3721767,"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": 1625851839891.925, "dur": 422.511, + "args": { + "External id": 3721768,"Record function id": 0, "Sequence number": 37295129, "Fwd thread id": 1, "Ev Idx": 1575 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1625851839894.672, "dur": 380.524, + "args": { + "External id": 3721769,"Sequence number": 37295129, "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": 1625851839894.672, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1381189, + "ts": 1625851839926.428, "dur": 1.792, + "args": { + "External id": 3721770,"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": 1625851839926.894, "dur": 1.181, + "args": { + "External id": 3721771,"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": 1625851839944.036, "dur": 5.035, + "args": { + "External id": 3721772,"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": 1625851839958.529, "dur": 2.491, + "args": { + "External id": 3721773,"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": 1625851840164.566, "dur": 3.073, + "args": { + "External id": 3721774,"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": 1625851840172.539, "dur": 40.881, + "args": { + "External id": 3721775,"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": 1625851840185.910, "dur": 0.873, + "args": { + "External id": 3721776,"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": 1625851840219.214, "dur": 32.572, + "args": { + "External id": 3721777,"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": 1625851840220.983, "dur": 30.598, + "args": { + "External id": 3721778,"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": 1625851840224.999, "dur": 4.464, + "args": { + "External id": 3721779,"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": 1625851840233.370, "dur": 17.725, + "args": { + "External id": 3721780,"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": 1625851840256.301, "dur": 4.884, + "args": { + "External id": 3721781,"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": 1625851840259.940, "dur": 1.153, + "args": { + "External id": 3721782,"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": 1625851840266.755, "dur": 1.865, + "args": { + "External id": 3721783,"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": 1625851840267.443, "dur": 1.080, + "args": { + "External id": 3721784,"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": 1625851840289.274, "dur": 19.901, + "args": { + "External id": 3721785,"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": 1625851840326.687, "dur": 9.997, + "args": { + "External id": 3721786,"Record function id": 0, "Ev Idx": 1593 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625851840328.534, "dur": 7.377, + "args": { + "External id": 3721787,"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": 1625851840330.766, "dur": 4.301, + "args": { + "External id": 3721788,"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": 1625851840333.087, "dur": 1.890, + "args": { + "External id": 3721789,"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": 1625851840340.980, "dur": 2796.318, + "args": { + "External id": 3721790,"Record function id": 0, "Ev Idx": 1597 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.27)", "pid": 1336756, "tid": 1381189, + "ts": 1625851840370.049, "dur": 996.372, + "args": { + "External id": 3721791,"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": 1625851840396.362, "dur": 960.606, + "args": { + "External id": 3721792,"Record function id": 0, "Ev Idx": 1599 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.26)", "pid": 1336756, "tid": 1381189, + "ts": 1625851840409.082, "dur": 932.319, + "args": { + "External id": 3721793,"Record function id": 0, "Ev Idx": 1600 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1625851840484.281, "dur": 6.854, + "args": { + "External id": 3721794,"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": 1625851840508.706, "dur": 35.643, + "args": { + "External id": 3721795,"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": 1625851840514.358, "dur": 3.149, + "args": { + "External id": 3721796,"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": 1625851840518.830, "dur": 0.738, + "args": { + "External id": 3721797,"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": 1625851840524.046, "dur": 0.586, + "args": { + "External id": 3721798,"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": 1625851840525.143, "dur": 0.527, + "args": { + "External id": 3721799,"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": 1625851840526.297, "dur": 0.528, + "args": { + "External id": 3721800,"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": 1625851840530.043, "dur": 0.436, + "args": { + "External id": 3721801,"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": 1625851840531.206, "dur": 0.332, + "args": { + "External id": 3721802,"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": 1625851840532.217, "dur": 1.953, + "args": { + "External id": 3721803,"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": 1625851840536.736, "dur": 1.989, + "args": { + "External id": 3721804,"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": 1625851840558.415, "dur": 30.785, + "args": { + "External id": 3721805,"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": 1625851840623.180, "dur": 136.873, + "args": { + "External id": 3721806,"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": 1625851840636.028, "dur": 6.681, + "args": { + "External id": 3721807,"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": 1625851840647.760, "dur": 8.694, + "args": { + "External id": 3721808,"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": 1625851840651.344, "dur": 4.707, + "args": { + "External id": 3721809,"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": 1625851840654.263, "dur": 0.496, + "args": { + "External id": 3721810,"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": 1625851840662.639, "dur": 51.486, + "args": { + "External id": 3721811,"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": 1625851840665.937, "dur": 0.274, + "args": { + "External id": 3721812,"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": 1625851840667.230, "dur": 2.073, + "args": { + "External id": 3721813,"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": 1625851840670.125, "dur": 0.455, + "args": { + "External id": 3721814,"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": 1625851840672.917, "dur": 0.287, + "args": { + "External id": 3721815,"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": 1625851840693.342, "dur": 0.693, + "args": { + "External id": 3721816,"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": 1625851840695.976, "dur": 2.284, + "args": { + "External id": 3721817,"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": 1625851840701.042, "dur": 0.551, + "args": { + "External id": 3721818,"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": 1625851840704.915, "dur": 0.373, + "args": { + "External id": 3721819,"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": 1625851840707.667, "dur": 0.366, + "args": { + "External id": 3721820,"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": 1625851840726.029, "dur": 25.423, + "args": { + "External id": 3721821,"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": 1625851840817.463, "dur": 413.572, + "args": { + "External id": 3721822,"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": 1625851840851.793, "dur": 374.046, + "args": { + "External id": 3721823,"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": 1625851840861.856, "dur": 357.784, + "args": { + "External id": 3721824,"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": 1625851841258.517, "dur": 2.183, + "args": { + "External id": 3721825,"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": 1625851841374.184, "dur": 1740.102, + "args": { + "External id": 3721826,"Sequence number": 37295128, "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": 1625851841374.184, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1625851841497.104, "dur": 101.532, + "args": { + "External id": 3721827,"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": 1625851841645.515, "dur": 59.559, + "args": { + "External id": 3721828,"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": 1625851841727.782, "dur": 54.831, + "args": { + "External id": 3721829,"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": 1625851841793.224, "dur": 32.473, + "args": { + "External id": 3721830,"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": 1625851841831.931, "dur": 44.478, + "args": { + "External id": 3721831,"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": 1625851841884.493, "dur": 27.163, + "args": { + "External id": 3721832,"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": 1625851841918.833, "dur": 41.363, + "args": { + "External id": 3721833,"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": 1625851842023.494, "dur": 29.688, + "args": { + "External id": 3721834,"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": 1625851842076.813, "dur": 32.640, + "args": { + "External id": 3721835,"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": 1625851842136.040, "dur": 21.064, + "args": { + "External id": 3721836,"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": 1625851842172.890, "dur": 26.767, + "args": { + "External id": 3721837,"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": 1625851842208.545, "dur": 33.699, + "args": { + "External id": 3721838,"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": 1625851842245.408, "dur": 32.250, + "args": { + "External id": 3721839,"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": 1625851842306.840, "dur": 175.388, + "args": { + "External id": 3721840,"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": 1625851842390.888, "dur": 7.578, + "args": { + "External id": 3721841,"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": 1625851842400.069, "dur": 2.020, + "args": { + "External id": 3721842,"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": 1625851842519.088, "dur": 29.570, + "args": { + "External id": 3721843,"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": 1625851842566.639, "dur": 15.336, + "args": { + "External id": 3721844,"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": 1625851842590.421, "dur": 35.446, + "args": { + "External id": 3721845,"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": 1625851842631.437, "dur": 33.543, + "args": { + "External id": 3721846,"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": 1625851842672.041, "dur": 43.309, + "args": { + "External id": 3721847,"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": 1625851842723.759, "dur": 30.975, + "args": { + "External id": 3721848,"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": 1625851842760.446, "dur": 21.491, + "args": { + "External id": 3721849,"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": 1625851842787.870, "dur": 28.751, + "args": { + "External id": 3721850,"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": 1625851842840.403, "dur": 26.571, + "args": { + "External id": 3721851,"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": 1625851842885.578, "dur": 26.943, + "args": { + "External id": 3721852,"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": 1625851842942.669, "dur": 28.497, + "args": { + "External id": 3721853,"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": 1625851843024.331, "dur": 18.247, + "args": { + "External id": 3721854,"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": 1625851843064.487, "dur": 20.412, + "args": { + "External id": 3721855,"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": 1625851843160.057, "dur": 14.733, + "args": { + "External id": 3721856,"Record function id": 0, "Ev Idx": 1663 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625851843163.375, "dur": 10.541, + "args": { + "External id": 3721857,"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": 1625851843167.754, "dur": 5.292, + "args": { + "External id": 3721858,"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": 1625851843169.234, "dur": 3.729, + "args": { + "External id": 3721859,"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": 1625851843178.846, "dur": 6.896, + "args": { + "External id": 3721860,"Record function id": 0, "Ev Idx": 1667 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625851843182.608, "dur": 2.645, + "args": { + "External id": 3721861,"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": 1625851843183.374, "dur": 1.318, + "args": { + "External id": 3721862,"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": 1625851843183.681, "dur": 0.943, + "args": { + "External id": 3721863,"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": 1625851843188.871, "dur": 5.182, + "args": { + "External id": 3721864,"Record function id": 0, "Ev Idx": 1671 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625851843190.310, "dur": 3.294, + "args": { + "External id": 3721865,"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": 1625851843191.426, "dur": 1.739, + "args": { + "External id": 3721866,"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": 1625851843192.357, "dur": 0.695, + "args": { + "External id": 3721867,"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": 1625851843197.179, "dur": 5.959, + "args": { + "External id": 3721868,"Record function id": 0, "Ev Idx": 1675 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625851843198.399, "dur": 4.291, + "args": { + "External id": 3721869,"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": 1625851843199.158, "dur": 3.092, + "args": { + "External id": 3721870,"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": 1625851843199.680, "dur": 2.496, + "args": { + "External id": 3721871,"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": 1625851843206.134, "dur": 3.807, + "args": { + "External id": 3721872,"Record function id": 0, "Ev Idx": 1679 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625851843207.063, "dur": 2.445, + "args": { + "External id": 3721873,"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": 1625851843207.520, "dur": 1.539, + "args": { + "External id": 3721874,"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": 1625851843208.142, "dur": 0.825, + "args": { + "External id": 3721875,"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": 1625851843212.881, "dur": 4.108, + "args": { + "External id": 3721876,"Record function id": 0, "Ev Idx": 1683 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625851843214.107, "dur": 2.455, + "args": { + "External id": 3721877,"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": 1625851843214.881, "dur": 1.170, + "args": { + "External id": 3721878,"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": 1625851843215.441, "dur": 0.542, + "args": { + "External id": 3721879,"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": 1625851843220.051, "dur": 3.758, + "args": { + "External id": 3721880,"Record function id": 0, "Ev Idx": 1687 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625851843221.430, "dur": 1.964, + "args": { + "External id": 3721881,"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": 1625851843221.940, "dur": 0.974, + "args": { + "External id": 3721882,"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": 1625851843222.192, "dur": 0.655, + "args": { + "External id": 3721883,"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": 1625851843226.790, "dur": 5.337, + "args": { + "External id": 3721884,"Record function id": 0, "Ev Idx": 1691 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625851843227.719, "dur": 4.001, + "args": { + "External id": 3721885,"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": 1625851843228.168, "dur": 3.064, + "args": { + "External id": 3721886,"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": 1625851843230.569, "dur": 0.601, + "args": { + "External id": 3721887,"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": 1625851843236.763, "dur": 3.338, + "args": { + "External id": 3721888,"Record function id": 0, "Ev Idx": 1695 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625851843237.842, "dur": 1.846, + "args": { + "External id": 3721889,"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": 1625851843238.347, "dur": 0.927, + "args": { + "External id": 3721890,"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": 1625851843238.640, "dur": 0.569, + "args": { + "External id": 3721891,"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": 1625851843244.000, "dur": 167972.237, + "args": { + "External id": 3721892,"Record function id": 0, "Sequence number": 37295127, "Fwd thread id": 1, "Ev Idx": 1699 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1625851843245.472, "dur": 167962.204, + "args": { + "External id": 3721893,"Sequence number": 37295127, "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": 1625851843245.472, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.27)", "pid": 1336756, "tid": 1381189, + "ts": 1625851843275.921, "dur": 41.824, + "args": { + "External id": 3721894,"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": 1625851843325.289, "dur": 71.220, + "args": { + "External id": 3721895,"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": 1625851843404.066, "dur": 167795.323, + "args": { + "External id": 3721896,"Record function id": 0, "Ev Idx": 1703 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1625851843460.828, "dur": 6.529, + "args": { + "External id": 3721897,"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": 1625851843479.126, "dur": 4.812, + "args": { + "External id": 3721898,"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": 1625851843503.777, "dur": 166872.645, + "args": { + "External id": 3721899,"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": 1625851843518.524, "dur": 166846.863, + "args": { + "External id": 3721900,"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": 1625851843580.860, "dur": 6.329, + "args": { + "External id": 3721901,"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": 1625851843597.209, "dur": 166722.455, + "args": { + "External id": 3721902,"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": 1625851843599.725, "dur": 166718.877, + "args": { + "External id": 3721903,"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": 1625851843602.884, "dur": 8.006, + "args": { + "External id": 3721904,"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": 1625851843612.871, "dur": 166701.573, + "args": { + "External id": 3721905,"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": 1625852010477.867, "dur": 9.566, + "args": { + "External id": 3721906,"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": 1625852010480.756, "dur": 6.267, + "args": { + "External id": 3721907,"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": 1625852010526.535, "dur": 320.086, + "args": { + "External id": 3721908,"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": 1625852010562.848, "dur": 278.877, + "args": { + "External id": 3721909,"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": 1625852010579.333, "dur": 255.928, + "args": { + "External id": 3721910,"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": 1625852010870.717, "dur": 2.026, + "args": { + "External id": 3721911,"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": 1625852010932.192, "dur": 7.341, + "args": { + "External id": 3721912,"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": 1625852011024.181, "dur": 2.125, + "args": { + "External id": 3721913,"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": 1625852011045.003, "dur": 1.419, + "args": { + "External id": 3721914,"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": 1625852011062.741, "dur": 0.922, + "args": { + "External id": 3721915,"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": 1625852011074.965, "dur": 1.244, + "args": { + "External id": 3721916,"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": 1625852011086.266, "dur": 1.808, + "args": { + "External id": 3721917,"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": 1625852011100.326, "dur": 1.091, + "args": { + "External id": 3721918,"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": 1625852011115.651, "dur": 2.947, + "args": { + "External id": 3721919,"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": 1625852011129.951, "dur": 0.819, + "args": { + "External id": 3721920,"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": 1625852011231.496, "dur": 2814.067, + "args": { + "External id": 3721921,"Record function id": 0, "Ev Idx": 1728 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.26)", "pid": 1336756, "tid": 1381189, + "ts": 1625852011251.062, "dur": 1065.556, + "args": { + "External id": 3721922,"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": 1625852011266.986, "dur": 322.426, + "args": { + "External id": 3721923,"Record function id": 0, "Ev Idx": 1730 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1625852011344.255, "dur": 4.225, + "args": { + "External id": 3721924,"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": 1625852011351.739, "dur": 0.793, + "args": { + "External id": 3721925,"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": 1625852011354.299, "dur": 0.779, + "args": { + "External id": 3721926,"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": 1625852011356.889, "dur": 2.549, + "args": { + "External id": 3721927,"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": 1625852011362.938, "dur": 0.929, + "args": { + "External id": 3721928,"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": 1625852011365.303, "dur": 1.088, + "args": { + "External id": 3721929,"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": 1625852011367.876, "dur": 2.709, + "args": { + "External id": 3721930,"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": 1625852011371.886, "dur": 1.051, + "args": { + "External id": 3721931,"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": 1625852011376.859, "dur": 0.899, + "args": { + "External id": 3721932,"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": 1625852011379.247, "dur": 1.177, + "args": { + "External id": 3721933,"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": 1625852011398.190, "dur": 160.972, + "args": { + "External id": 3721934,"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": 1625852011416.834, "dur": 137.852, + "args": { + "External id": 3721935,"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": 1625852011441.592, "dur": 12.091, + "args": { + "External id": 3721936,"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": 1625852011456.719, "dur": 69.324, + "args": { + "External id": 3721937,"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": 1625852011461.472, "dur": 64.246, + "args": { + "External id": 3721938,"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": 1625852011464.941, "dur": 9.443, + "args": { + "External id": 3721939,"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": 1625852011476.104, "dur": 48.901, + "args": { + "External id": 3721940,"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": 1625852011663.050, "dur": 645.792, + "args": { + "External id": 3721941,"Record function id": 0, "Ev Idx": 1748 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.25)", "pid": 1336756, "tid": 1381189, + "ts": 1625852011698.015, "dur": 598.931, + "args": { + "External id": 3721942,"Record function id": 0, "Ev Idx": 1749 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1625852011756.037, "dur": 6.258, + "args": { + "External id": 3721943,"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": 1625852011778.027, "dur": 39.424, + "args": { + "External id": 3721944,"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": 1625852011784.641, "dur": 3.009, + "args": { + "External id": 3721945,"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": 1625852011788.772, "dur": 0.565, + "args": { + "External id": 3721946,"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": 1625852011790.107, "dur": 0.412, + "args": { + "External id": 3721947,"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": 1625852011795.485, "dur": 0.366, + "args": { + "External id": 3721948,"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": 1625852011796.783, "dur": 0.355, + "args": { + "External id": 3721949,"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": 1625852011797.658, "dur": 0.348, + "args": { + "External id": 3721950,"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": 1625852011803.165, "dur": 2.235, + "args": { + "External id": 3721951,"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": 1625852011806.083, "dur": 0.530, + "args": { + "External id": 3721952,"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": 1625852011809.262, "dur": 1.819, + "args": { + "External id": 3721953,"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": 1625852011839.344, "dur": 35.320, + "args": { + "External id": 3721954,"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": 1625852011904.824, "dur": 150.199, + "args": { + "External id": 3721955,"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": 1625852011914.476, "dur": 5.678, + "args": { + "External id": 3721956,"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": 1625852011925.337, "dur": 11.147, + "args": { + "External id": 3721957,"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": 1625852011929.280, "dur": 6.794, + "args": { + "External id": 3721958,"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": 1625852011934.273, "dur": 0.573, + "args": { + "External id": 3721959,"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": 1625852011942.771, "dur": 32.061, + "args": { + "External id": 3721960,"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": 1625852011943.845, "dur": 0.566, + "args": { + "External id": 3721961,"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": 1625852011948.009, "dur": 2.504, + "args": { + "External id": 3721962,"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": 1625852011951.260, "dur": 0.268, + "args": { + "External id": 3721963,"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": 1625852011952.255, "dur": 2.762, + "args": { + "External id": 3721964,"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": 1625852011959.508, "dur": 0.598, + "args": { + "External id": 3721965,"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": 1625852011960.954, "dur": 0.539, + "args": { + "External id": 3721966,"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": 1625852011963.704, "dur": 0.317, + "args": { + "External id": 3721967,"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": 1625852011966.957, "dur": 0.341, + "args": { + "External id": 3721968,"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": 1625852011967.940, "dur": 0.372, + "args": { + "External id": 3721969,"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": 1625852012022.297, "dur": 23.500, + "args": { + "External id": 3721970,"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": 1625852012101.178, "dur": 124.522, + "args": { + "External id": 3721971,"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": 1625852012131.893, "dur": 90.403, + "args": { + "External id": 3721972,"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": 1625852012143.372, "dur": 74.798, + "args": { + "External id": 3721973,"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": 1625852012245.063, "dur": 1.733, + "args": { + "External id": 3721974,"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": 1625852012323.604, "dur": 1699.626, + "args": { + "External id": 3721975,"Sequence number": 37295126, "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": 1625852012323.604, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1625852012431.569, "dur": 102.193, + "args": { + "External id": 3721976,"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": 1625852012577.361, "dur": 37.630, + "args": { + "External id": 3721977,"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": 1625852012630.524, "dur": 67.372, + "args": { + "External id": 3721978,"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": 1625852012711.896, "dur": 38.026, + "args": { + "External id": 3721979,"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": 1625852012758.181, "dur": 44.719, + "args": { + "External id": 3721980,"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": 1625852012809.471, "dur": 27.933, + "args": { + "External id": 3721981,"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": 1625852012845.303, "dur": 41.506, + "args": { + "External id": 3721982,"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": 1625852012911.988, "dur": 24.704, + "args": { + "External id": 3721983,"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": 1625852012961.117, "dur": 68.771, + "args": { + "External id": 3721984,"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": 1625852013056.183, "dur": 20.767, + "args": { + "External id": 3721985,"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": 1625852013093.955, "dur": 16.393, + "args": { + "External id": 3721986,"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": 1625852013119.099, "dur": 35.398, + "args": { + "External id": 3721987,"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": 1625852013157.835, "dur": 35.217, + "args": { + "External id": 3721988,"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": 1625852013222.937, "dur": 172.665, + "args": { + "External id": 3721989,"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": 1625852013308.148, "dur": 5.976, + "args": { + "External id": 3721990,"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": 1625852013315.764, "dur": 2.086, + "args": { + "External id": 3721991,"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": 1625852013434.360, "dur": 27.439, + "args": { + "External id": 3721992,"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": 1625852013475.796, "dur": 15.549, + "args": { + "External id": 3721993,"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": 1625852013499.231, "dur": 37.607, + "args": { + "External id": 3721994,"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": 1625852013542.316, "dur": 34.580, + "args": { + "External id": 3721995,"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": 1625852013588.159, "dur": 22.550, + "args": { + "External id": 3721996,"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": 1625852013614.834, "dur": 28.610, + "args": { + "External id": 3721997,"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": 1625852013647.997, "dur": 51.733, + "args": { + "External id": 3721998,"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": 1625852013717.623, "dur": 44.007, + "args": { + "External id": 3721999,"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": 1625852013784.936, "dur": 25.335, + "args": { + "External id": 3722000,"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": 1625852013830.432, "dur": 27.082, + "args": { + "External id": 3722001,"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": 1625852013877.200, "dur": 17.307, + "args": { + "External id": 3722002,"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": 1625852013914.376, "dur": 14.684, + "args": { + "External id": 3722003,"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": 1625852013946.196, "dur": 15.547, + "args": { + "External id": 3722004,"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": 1625852014068.745, "dur": 15.251, + "args": { + "External id": 3722005,"Record function id": 0, "Ev Idx": 1812 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852014072.049, "dur": 11.134, + "args": { + "External id": 3722006,"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": 1625852014076.352, "dur": 5.871, + "args": { + "External id": 3722007,"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": 1625852014077.947, "dur": 4.174, + "args": { + "External id": 3722008,"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": 1625852014087.752, "dur": 4.743, + "args": { + "External id": 3722009,"Record function id": 0, "Ev Idx": 1816 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852014089.240, "dur": 2.850, + "args": { + "External id": 3722010,"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": 1625852014089.939, "dur": 1.699, + "args": { + "External id": 3722011,"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": 1625852014090.672, "dur": 0.880, + "args": { + "External id": 3722012,"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": 1625852014095.587, "dur": 7.114, + "args": { + "External id": 3722013,"Record function id": 0, "Ev Idx": 1820 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852014097.023, "dur": 5.271, + "args": { + "External id": 3722014,"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": 1625852014097.679, "dur": 4.164, + "args": { + "External id": 3722015,"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": 1625852014098.439, "dur": 3.277, + "args": { + "External id": 3722016,"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": 1625852014105.765, "dur": 4.634, + "args": { + "External id": 3722017,"Record function id": 0, "Ev Idx": 1824 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852014107.076, "dur": 2.917, + "args": { + "External id": 3722018,"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": 1625852014107.977, "dur": 1.542, + "args": { + "External id": 3722019,"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": 1625852014108.497, "dur": 0.938, + "args": { + "External id": 3722020,"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": 1625852014113.377, "dur": 4.588, + "args": { + "External id": 3722021,"Record function id": 0, "Ev Idx": 1828 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852014114.689, "dur": 2.892, + "args": { + "External id": 3722022,"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": 1625852014115.771, "dur": 1.406, + "args": { + "External id": 3722023,"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": 1625852014116.275, "dur": 0.837, + "args": { + "External id": 3722024,"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": 1625852014121.037, "dur": 6.237, + "args": { + "External id": 3722025,"Record function id": 0, "Ev Idx": 1832 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852014124.107, "dur": 2.696, + "args": { + "External id": 3722026,"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": 1625852014124.792, "dur": 1.353, + "args": { + "External id": 3722027,"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": 1625852014125.393, "dur": 0.687, + "args": { + "External id": 3722028,"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": 1625852014130.394, "dur": 3.585, + "args": { + "External id": 3722029,"Record function id": 0, "Ev Idx": 1836 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852014131.435, "dur": 2.112, + "args": { + "External id": 3722030,"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": 1625852014131.879, "dur": 1.253, + "args": { + "External id": 3722031,"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": 1625852014132.163, "dur": 0.903, + "args": { + "External id": 3722032,"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": 1625852014136.921, "dur": 5.300, + "args": { + "External id": 3722033,"Record function id": 0, "Ev Idx": 1840 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852014137.884, "dur": 3.946, + "args": { + "External id": 3722034,"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": 1625852014138.488, "dur": 2.923, + "args": { + "External id": 3722035,"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": 1625852014140.719, "dur": 0.627, + "args": { + "External id": 3722036,"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": 1625852014145.298, "dur": 3.626, + "args": { + "External id": 3722037,"Record function id": 0, "Ev Idx": 1844 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852014146.457, "dur": 1.898, + "args": { + "External id": 3722038,"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": 1625852014146.900, "dur": 1.045, + "args": { + "External id": 3722039,"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": 1625852014147.165, "dur": 0.715, + "args": { + "External id": 3722040,"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": 1625852014152.713, "dur": 44210.076, + "args": { + "External id": 3722041,"Record function id": 0, "Sequence number": 37295125, "Fwd thread id": 1, "Ev Idx": 1848 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1625852014154.340, "dur": 44200.169, + "args": { + "External id": 3722042,"Sequence number": 37295125, "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": 1625852014154.340, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.26)", "pid": 1336756, "tid": 1381189, + "ts": 1625852014184.043, "dur": 37.855, + "args": { + "External id": 3722043,"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": 1625852014229.524, "dur": 62.149, + "args": { + "External id": 3722044,"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": 1625852014299.527, "dur": 44047.759, + "args": { + "External id": 3722045,"Record function id": 0, "Ev Idx": 1852 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1625852014391.465, "dur": 6.706, + "args": { + "External id": 3722046,"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": 1625852014407.080, "dur": 7.292, + "args": { + "External id": 3722047,"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": 1625852014432.676, "dur": 43049.832, + "args": { + "External id": 3722048,"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": 1625852014449.049, "dur": 43023.482, + "args": { + "External id": 3722049,"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": 1625852014518.649, "dur": 12.920, + "args": { + "External id": 3722050,"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": 1625852014540.032, "dur": 42893.001, + "args": { + "External id": 3722051,"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": 1625852014542.357, "dur": 42889.988, + "args": { + "External id": 3722052,"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": 1625852014547.274, "dur": 5.029, + "args": { + "External id": 3722053,"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": 1625852014553.863, "dur": 42874.472, + "args": { + "External id": 3722054,"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": 1625852057570.579, "dur": 8.405, + "args": { + "External id": 3722055,"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": 1625852057573.067, "dur": 5.543, + "args": { + "External id": 3722056,"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": 1625852057610.953, "dur": 435.613, + "args": { + "External id": 3722057,"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": 1625852057644.430, "dur": 396.295, + "args": { + "External id": 3722058,"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": 1625852057659.187, "dur": 375.077, + "args": { + "External id": 3722059,"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": 1625852058071.115, "dur": 2.544, + "args": { + "External id": 3722060,"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": 1625852058136.969, "dur": 6.681, + "args": { + "External id": 3722061,"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": 1625852058189.308, "dur": 1.332, + "args": { + "External id": 3722062,"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": 1625852058205.709, "dur": 2.827, + "args": { + "External id": 3722063,"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": 1625852058221.617, "dur": 1.093, + "args": { + "External id": 3722064,"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": 1625852058232.851, "dur": 0.872, + "args": { + "External id": 3722065,"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": 1625852058245.662, "dur": 0.831, + "args": { + "External id": 3722066,"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": 1625852058256.726, "dur": 2.726, + "args": { + "External id": 3722067,"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": 1625852058271.225, "dur": 3.521, + "args": { + "External id": 3722068,"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": 1625852058287.367, "dur": 1.080, + "args": { + "External id": 3722069,"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": 1625852058376.077, "dur": 2800.728, + "args": { + "External id": 3722070,"Record function id": 0, "Ev Idx": 1877 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.25)", "pid": 1336756, "tid": 1381189, + "ts": 1625852058394.031, "dur": 1058.772, + "args": { + "External id": 3722071,"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": 1625852058407.669, "dur": 337.257, + "args": { + "External id": 3722072,"Record function id": 0, "Ev Idx": 1879 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1625852058483.069, "dur": 4.173, + "args": { + "External id": 3722073,"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": 1625852058489.988, "dur": 1.342, + "args": { + "External id": 3722074,"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": 1625852058493.132, "dur": 2.896, + "args": { + "External id": 3722075,"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": 1625852058497.561, "dur": 1.076, + "args": { + "External id": 3722076,"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": 1625852058501.895, "dur": 0.866, + "args": { + "External id": 3722077,"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": 1625852058504.034, "dur": 1.103, + "args": { + "External id": 3722078,"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": 1625852058508.666, "dur": 2.858, + "args": { + "External id": 3722079,"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": 1625852058512.853, "dur": 1.243, + "args": { + "External id": 3722080,"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": 1625852058517.352, "dur": 1.153, + "args": { + "External id": 3722081,"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": 1625852058519.750, "dur": 0.904, + "args": { + "External id": 3722082,"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": 1625852058538.105, "dur": 176.252, + "args": { + "External id": 3722083,"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": 1625852058556.110, "dur": 153.064, + "args": { + "External id": 3722084,"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": 1625852058574.261, "dur": 16.991, + "args": { + "External id": 3722085,"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": 1625852058594.444, "dur": 64.892, + "args": { + "External id": 3722086,"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": 1625852058598.594, "dur": 60.493, + "args": { + "External id": 3722087,"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": 1625852058601.896, "dur": 4.530, + "args": { + "External id": 3722088,"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": 1625852058608.207, "dur": 50.313, + "args": { + "External id": 3722089,"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": 1625852058821.168, "dur": 624.254, + "args": { + "External id": 3722090,"Record function id": 0, "Ev Idx": 1897 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.24)", "pid": 1336756, "tid": 1381189, + "ts": 1625852058837.893, "dur": 594.937, + "args": { + "External id": 3722091,"Record function id": 0, "Ev Idx": 1898 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1625852058891.158, "dur": 5.267, + "args": { + "External id": 3722092,"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": 1625852058911.357, "dur": 36.289, + "args": { + "External id": 3722093,"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": 1625852058917.380, "dur": 1.548, + "args": { + "External id": 3722094,"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": 1625852058921.822, "dur": 0.316, + "args": { + "External id": 3722095,"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": 1625852058922.966, "dur": 0.539, + "args": { + "External id": 3722096,"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": 1625852058925.416, "dur": 1.906, + "args": { + "External id": 3722097,"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": 1625852058928.090, "dur": 0.440, + "args": { + "External id": 3722098,"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": 1625852058931.067, "dur": 2.376, + "args": { + "External id": 3722099,"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": 1625852058935.892, "dur": 0.379, + "args": { + "External id": 3722100,"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": 1625852058937.174, "dur": 0.515, + "args": { + "External id": 3722101,"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": 1625852058940.580, "dur": 0.474, + "args": { + "External id": 3722102,"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": 1625852058956.596, "dur": 69.933, + "args": { + "External id": 3722103,"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": 1625852059060.862, "dur": 125.866, + "args": { + "External id": 3722104,"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": 1625852059071.117, "dur": 4.412, + "args": { + "External id": 3722105,"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": 1625852059080.482, "dur": 13.249, + "args": { + "External id": 3722106,"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": 1625852059084.580, "dur": 8.718, + "args": { + "External id": 3722107,"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": 1625852059089.010, "dur": 2.659, + "args": { + "External id": 3722108,"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": 1625852059100.694, "dur": 43.766, + "args": { + "External id": 3722109,"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": 1625852059102.508, "dur": 0.457, + "args": { + "External id": 3722110,"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": 1625852059106.067, "dur": 0.470, + "args": { + "External id": 3722111,"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": 1625852059120.213, "dur": 2.554, + "args": { + "External id": 3722112,"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": 1625852059127.056, "dur": 0.517, + "args": { + "External id": 3722113,"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": 1625852059128.298, "dur": 0.468, + "args": { + "External id": 3722114,"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": 1625852059129.232, "dur": 2.007, + "args": { + "External id": 3722115,"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": 1625852059133.606, "dur": 0.348, + "args": { + "External id": 3722116,"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": 1625852059134.854, "dur": 0.343, + "args": { + "External id": 3722117,"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": 1625852059137.492, "dur": 0.310, + "args": { + "External id": 3722118,"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": 1625852059154.815, "dur": 24.446, + "args": { + "External id": 3722119,"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": 1625852059231.425, "dur": 131.010, + "args": { + "External id": 3722120,"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": 1625852059262.436, "dur": 96.396, + "args": { + "External id": 3722121,"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": 1625852059271.727, "dur": 82.662, + "args": { + "External id": 3722122,"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": 1625852059378.461, "dur": 2.372, + "args": { + "External id": 3722123,"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": 1625852059459.192, "dur": 1696.110, + "args": { + "External id": 3722124,"Sequence number": 37295124, "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": 1625852059459.192, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1625852059563.617, "dur": 102.288, + "args": { + "External id": 3722125,"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": 1625852059729.962, "dur": 42.542, + "args": { + "External id": 3722126,"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": 1625852059791.396, "dur": 53.873, + "args": { + "External id": 3722127,"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": 1625852059853.949, "dur": 33.640, + "args": { + "External id": 3722128,"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": 1625852059895.649, "dur": 43.954, + "args": { + "External id": 3722129,"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": 1625852059947.858, "dur": 27.238, + "args": { + "External id": 3722130,"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": 1625852060026.515, "dur": 49.720, + "args": { + "External id": 3722131,"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": 1625852060108.988, "dur": 27.390, + "args": { + "External id": 3722132,"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": 1625852060156.431, "dur": 29.663, + "args": { + "External id": 3722133,"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": 1625852060210.247, "dur": 19.356, + "args": { + "External id": 3722134,"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": 1625852060247.357, "dur": 15.980, + "args": { + "External id": 3722135,"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": 1625852060272.450, "dur": 30.610, + "args": { + "External id": 3722136,"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": 1625852060305.693, "dur": 32.156, + "args": { + "External id": 3722137,"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": 1625852060367.713, "dur": 172.897, + "args": { + "External id": 3722138,"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": 1625852060450.232, "dur": 8.472, + "args": { + "External id": 3722139,"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": 1625852060460.687, "dur": 2.121, + "args": { + "External id": 3722140,"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": 1625852060573.483, "dur": 25.701, + "args": { + "External id": 3722141,"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": 1625852060612.471, "dur": 15.035, + "args": { + "External id": 3722142,"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": 1625852060634.189, "dur": 34.330, + "args": { + "External id": 3722143,"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": 1625852060673.829, "dur": 53.290, + "args": { + "External id": 3722144,"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": 1625852060736.800, "dur": 23.193, + "args": { + "External id": 3722145,"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": 1625852060765.908, "dur": 28.682, + "args": { + "External id": 3722146,"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": 1625852060799.431, "dur": 20.903, + "args": { + "External id": 3722147,"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": 1625852060826.846, "dur": 47.459, + "args": { + "External id": 3722148,"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": 1625852060902.056, "dur": 27.253, + "args": { + "External id": 3722149,"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": 1625852060952.391, "dur": 23.600, + "args": { + "External id": 3722150,"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": 1625852061027.837, "dur": 22.033, + "args": { + "External id": 3722151,"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": 1625852061071.315, "dur": 14.192, + "args": { + "External id": 3722152,"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": 1625852061101.664, "dur": 25.920, + "args": { + "External id": 3722153,"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": 1625852061202.521, "dur": 14.811, + "args": { + "External id": 3722154,"Record function id": 0, "Ev Idx": 1961 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852061205.847, "dur": 10.591, + "args": { + "External id": 3722155,"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": 1625852061210.116, "dur": 5.524, + "args": { + "External id": 3722156,"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": 1625852061211.793, "dur": 3.764, + "args": { + "External id": 3722157,"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": 1625852061221.159, "dur": 6.200, + "args": { + "External id": 3722158,"Record function id": 0, "Ev Idx": 1965 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852061223.956, "dur": 2.948, + "args": { + "External id": 3722159,"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": 1625852061224.766, "dur": 1.580, + "args": { + "External id": 3722160,"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": 1625852061225.340, "dur": 0.921, + "args": { + "External id": 3722161,"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": 1625852061230.546, "dur": 4.124, + "args": { + "External id": 3722162,"Record function id": 0, "Ev Idx": 1969 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852061231.667, "dur": 2.536, + "args": { + "External id": 3722163,"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": 1625852061232.205, "dur": 1.542, + "args": { + "External id": 3722164,"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": 1625852061232.878, "dur": 0.790, + "args": { + "External id": 3722165,"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": 1625852061237.766, "dur": 8.955, + "args": { + "External id": 3722166,"Record function id": 0, "Ev Idx": 1973 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852061239.074, "dur": 7.257, + "args": { + "External id": 3722167,"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": 1625852061239.699, "dur": 6.231, + "args": { + "External id": 3722168,"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": 1625852061243.080, "dur": 2.790, + "args": { + "External id": 3722169,"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": 1625852061249.983, "dur": 3.790, + "args": { + "External id": 3722170,"Record function id": 0, "Ev Idx": 1977 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852061250.936, "dur": 2.453, + "args": { + "External id": 3722171,"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": 1625852061251.547, "dur": 1.358, + "args": { + "External id": 3722172,"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": 1625852061252.027, "dur": 0.817, + "args": { + "External id": 3722173,"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": 1625852061256.800, "dur": 3.176, + "args": { + "External id": 3722174,"Record function id": 0, "Ev Idx": 1981 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852061257.738, "dur": 1.853, + "args": { + "External id": 3722175,"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": 1625852061258.209, "dur": 0.949, + "args": { + "External id": 3722176,"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": 1625852061258.582, "dur": 0.509, + "args": { + "External id": 3722177,"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": 1625852061263.166, "dur": 5.539, + "args": { + "External id": 3722178,"Record function id": 0, "Ev Idx": 1985 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852061264.156, "dur": 4.160, + "args": { + "External id": 3722179,"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": 1625852061264.677, "dur": 3.217, + "args": { + "External id": 3722180,"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": 1625852061267.249, "dur": 0.583, + "args": { + "External id": 3722181,"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": 1625852061271.769, "dur": 3.306, + "args": { + "External id": 3722182,"Record function id": 0, "Ev Idx": 1989 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852061272.663, "dur": 2.011, + "args": { + "External id": 3722183,"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": 1625852061273.111, "dur": 1.118, + "args": { + "External id": 3722184,"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": 1625852061273.609, "dur": 0.554, + "args": { + "External id": 3722185,"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": 1625852061278.037, "dur": 3.380, + "args": { + "External id": 3722186,"Record function id": 0, "Ev Idx": 1993 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852061278.954, "dur": 2.075, + "args": { + "External id": 3722187,"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": 1625852061279.387, "dur": 1.238, + "args": { + "External id": 3722188,"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": 1625852061279.970, "dur": 0.591, + "args": { + "External id": 3722189,"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": 1625852061285.076, "dur": 42251.390, + "args": { + "External id": 3722190,"Record function id": 0, "Sequence number": 37295123, "Fwd thread id": 1, "Ev Idx": 1997 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1625852061286.477, "dur": 42241.337, + "args": { + "External id": 3722191,"Sequence number": 37295123, "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": 1625852061286.477, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.25)", "pid": 1336756, "tid": 1381189, + "ts": 1625852061315.473, "dur": 39.253, + "args": { + "External id": 3722192,"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": 1625852061362.153, "dur": 63.182, + "args": { + "External id": 3722193,"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": 1625852061434.949, "dur": 42084.205, + "args": { + "External id": 3722194,"Record function id": 0, "Ev Idx": 2001 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1625852061516.544, "dur": 6.038, + "args": { + "External id": 3722195,"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": 1625852061532.751, "dur": 4.489, + "args": { + "External id": 3722196,"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": 1625852061550.738, "dur": 41090.440, + "args": { + "External id": 3722197,"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": 1625852061564.225, "dur": 41067.376, + "args": { + "External id": 3722198,"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": 1625852061623.701, "dur": 15.311, + "args": { + "External id": 3722199,"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": 1625852061645.850, "dur": 40943.778, + "args": { + "External id": 3722200,"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": 1625852061648.178, "dur": 40940.621, + "args": { + "External id": 3722201,"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": 1625852061651.611, "dur": 6.174, + "args": { + "External id": 3722202,"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": 1625852061659.296, "dur": 40925.387, + "args": { + "External id": 3722203,"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": 1625852102741.398, "dur": 8.732, + "args": { + "External id": 3722204,"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": 1625852102744.193, "dur": 5.444, + "args": { + "External id": 3722205,"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": 1625852102780.576, "dur": 432.381, + "args": { + "External id": 3722206,"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": 1625852102811.308, "dur": 396.302, + "args": { + "External id": 3722207,"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": 1625852102823.373, "dur": 377.890, + "args": { + "External id": 3722208,"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": 1625852103239.379, "dur": 2.606, + "args": { + "External id": 3722209,"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": 1625852103304.627, "dur": 6.506, + "args": { + "External id": 3722210,"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": 1625852103355.596, "dur": 1.602, + "args": { + "External id": 3722211,"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": 1625852103373.406, "dur": 1.410, + "args": { + "External id": 3722212,"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": 1625852103387.436, "dur": 3.008, + "args": { + "External id": 3722213,"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": 1625852103400.505, "dur": 0.924, + "args": { + "External id": 3722214,"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": 1625852103410.894, "dur": 0.755, + "args": { + "External id": 3722215,"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": 1625852103423.454, "dur": 1.308, + "args": { + "External id": 3722216,"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": 1625852103437.520, "dur": 5.123, + "args": { + "External id": 3722217,"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": 1625852103455.239, "dur": 1.121, + "args": { + "External id": 3722218,"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": 1625852103550.729, "dur": 2818.963, + "args": { + "External id": 3722219,"Record function id": 0, "Ev Idx": 2026 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.24)", "pid": 1336756, "tid": 1381189, + "ts": 1625852103572.764, "dur": 1072.908, + "args": { + "External id": 3722220,"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": 1625852103588.096, "dur": 341.918, + "args": { + "External id": 3722221,"Record function id": 0, "Ev Idx": 2028 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1625852103667.304, "dur": 3.820, + "args": { + "External id": 3722222,"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": 1625852103674.062, "dur": 1.239, + "args": { + "External id": 3722223,"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": 1625852103697.144, "dur": 1.550, + "args": { + "External id": 3722224,"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": 1625852103701.136, "dur": 1.275, + "args": { + "External id": 3722225,"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": 1625852103704.142, "dur": 3.037, + "args": { + "External id": 3722226,"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": 1625852103708.878, "dur": 1.093, + "args": { + "External id": 3722227,"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": 1625852103713.462, "dur": 3.359, + "args": { + "External id": 3722228,"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": 1625852103718.349, "dur": 1.265, + "args": { + "External id": 3722229,"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": 1625852103721.416, "dur": 0.918, + "args": { + "External id": 3722230,"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": 1625852103723.963, "dur": 0.744, + "args": { + "External id": 3722231,"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": 1625852103744.275, "dur": 153.256, + "args": { + "External id": 3722232,"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": 1625852103760.589, "dur": 133.065, + "args": { + "External id": 3722233,"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": 1625852103781.171, "dur": 12.686, + "args": { + "External id": 3722234,"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": 1625852103797.107, "dur": 66.172, + "args": { + "External id": 3722235,"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": 1625852103799.703, "dur": 63.295, + "args": { + "External id": 3722236,"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": 1625852103803.852, "dur": 6.807, + "args": { + "External id": 3722237,"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": 1625852103812.330, "dur": 50.037, + "args": { + "External id": 3722238,"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": 1625852104058.176, "dur": 580.236, + "args": { + "External id": 3722239,"Record function id": 0, "Ev Idx": 2046 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.23)", "pid": 1336756, "tid": 1381189, + "ts": 1625852104077.571, "dur": 548.651, + "args": { + "External id": 3722240,"Record function id": 0, "Ev Idx": 2047 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1625852104159.513, "dur": 8.237, + "args": { + "External id": 3722241,"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": 1625852104183.805, "dur": 35.457, + "args": { + "External id": 3722242,"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": 1625852104188.604, "dur": 3.601, + "args": { + "External id": 3722243,"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": 1625852104194.072, "dur": 0.356, + "args": { + "External id": 3722244,"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": 1625852104195.728, "dur": 0.322, + "args": { + "External id": 3722245,"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": 1625852104199.095, "dur": 0.345, + "args": { + "External id": 3722246,"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": 1625852104201.063, "dur": 0.144, + "args": { + "External id": 3722247,"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": 1625852104202.447, "dur": 0.329, + "args": { + "External id": 3722248,"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": 1625852104205.615, "dur": 0.246, + "args": { + "External id": 3722249,"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": 1625852104207.292, "dur": 2.264, + "args": { + "External id": 3722250,"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": 1625852104210.496, "dur": 2.046, + "args": { + "External id": 3722251,"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": 1625852104229.236, "dur": 36.912, + "args": { + "External id": 3722252,"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": 1625852104296.849, "dur": 104.680, + "args": { + "External id": 3722253,"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": 1625852104306.567, "dur": 3.491, + "args": { + "External id": 3722254,"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": 1625852104315.130, "dur": 9.480, + "args": { + "External id": 3722255,"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": 1625852104319.048, "dur": 5.133, + "args": { + "External id": 3722256,"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": 1625852104322.390, "dur": 0.534, + "args": { + "External id": 3722257,"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": 1625852104331.017, "dur": 30.293, + "args": { + "External id": 3722258,"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": 1625852104333.209, "dur": 0.359, + "args": { + "External id": 3722259,"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": 1625852104335.327, "dur": 0.580, + "args": { + "External id": 3722260,"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": 1625852104337.896, "dur": 1.560, + "args": { + "External id": 3722261,"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": 1625852104341.208, "dur": 0.393, + "args": { + "External id": 3722262,"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": 1625852104343.175, "dur": 2.170, + "args": { + "External id": 3722263,"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": 1625852104348.066, "dur": 0.246, + "args": { + "External id": 3722264,"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": 1625852104349.285, "dur": 0.282, + "args": { + "External id": 3722265,"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": 1625852104351.131, "dur": 0.343, + "args": { + "External id": 3722266,"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": 1625852104354.010, "dur": 0.355, + "args": { + "External id": 3722267,"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": 1625852104374.084, "dur": 19.849, + "args": { + "External id": 3722268,"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": 1625852104443.878, "dur": 116.726, + "args": { + "External id": 3722269,"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": 1625852104472.501, "dur": 84.830, + "args": { + "External id": 3722270,"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": 1625852104481.518, "dur": 71.872, + "args": { + "External id": 3722271,"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": 1625852104577.458, "dur": 1.746, + "args": { + "External id": 3722272,"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": 1625852104652.537, "dur": 1692.624, + "args": { + "External id": 3722273,"Sequence number": 37295122, "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": 1625852104652.537, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1625852104776.228, "dur": 106.869, + "args": { + "External id": 3722274,"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": 1625852104928.087, "dur": 38.872, + "args": { + "External id": 3722275,"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": 1625852105018.072, "dur": 59.303, + "args": { + "External id": 3722276,"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": 1625852105089.482, "dur": 34.633, + "args": { + "External id": 3722277,"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": 1625852105132.291, "dur": 47.037, + "args": { + "External id": 3722278,"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": 1625852105185.907, "dur": 27.461, + "args": { + "External id": 3722279,"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": 1625852105220.155, "dur": 43.756, + "args": { + "External id": 3722280,"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": 1625852105290.095, "dur": 24.632, + "args": { + "External id": 3722281,"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": 1625852105335.749, "dur": 28.434, + "args": { + "External id": 3722282,"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": 1625852105385.108, "dur": 21.240, + "args": { + "External id": 3722283,"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": 1625852105422.160, "dur": 14.842, + "args": { + "External id": 3722284,"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": 1625852105446.307, "dur": 30.472, + "args": { + "External id": 3722285,"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": 1625852105479.907, "dur": 32.647, + "args": { + "External id": 3722286,"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": 1625852105546.406, "dur": 194.547, + "args": { + "External id": 3722287,"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": 1625852105632.143, "dur": 5.371, + "args": { + "External id": 3722288,"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": 1625852105639.245, "dur": 2.035, + "args": { + "External id": 3722289,"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": 1625852105775.826, "dur": 26.300, + "args": { + "External id": 3722290,"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": 1625852105814.634, "dur": 15.275, + "args": { + "External id": 3722291,"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": 1625852105838.067, "dur": 40.783, + "args": { + "External id": 3722292,"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": 1625852105884.572, "dur": 34.071, + "args": { + "External id": 3722293,"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": 1625852105925.659, "dur": 21.129, + "args": { + "External id": 3722294,"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": 1625852105952.981, "dur": 63.204, + "args": { + "External id": 3722295,"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": 1625852106026.108, "dur": 43.047, + "args": { + "External id": 3722296,"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": 1625852106083.662, "dur": 34.157, + "args": { + "External id": 3722297,"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": 1625852106143.426, "dur": 25.153, + "args": { + "External id": 3722298,"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": 1625852106193.537, "dur": 22.771, + "args": { + "External id": 3722299,"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": 1625852106229.906, "dur": 17.566, + "args": { + "External id": 3722300,"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": 1625852106268.452, "dur": 14.630, + "args": { + "External id": 3722301,"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": 1625852106297.223, "dur": 21.646, + "args": { + "External id": 3722302,"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": 1625852106393.103, "dur": 14.898, + "args": { + "External id": 3722303,"Record function id": 0, "Ev Idx": 2110 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852106396.665, "dur": 10.575, + "args": { + "External id": 3722304,"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": 1625852106400.905, "dur": 5.408, + "args": { + "External id": 3722305,"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": 1625852106402.148, "dur": 4.030, + "args": { + "External id": 3722306,"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": 1625852106411.985, "dur": 4.866, + "args": { + "External id": 3722307,"Record function id": 0, "Ev Idx": 2114 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852106413.714, "dur": 2.682, + "args": { + "External id": 3722308,"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": 1625852106414.704, "dur": 1.262, + "args": { + "External id": 3722309,"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": 1625852106415.033, "dur": 0.816, + "args": { + "External id": 3722310,"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": 1625852106420.123, "dur": 7.210, + "args": { + "External id": 3722311,"Record function id": 0, "Ev Idx": 2118 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852106421.711, "dur": 5.223, + "args": { + "External id": 3722312,"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": 1625852106422.205, "dur": 4.266, + "args": { + "External id": 3722313,"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": 1625852106422.876, "dur": 0.586, + "args": { + "External id": 3722314,"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": 1625852106430.471, "dur": 5.353, + "args": { + "External id": 3722315,"Record function id": 0, "Ev Idx": 2122 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852106431.562, "dur": 3.852, + "args": { + "External id": 3722316,"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": 1625852106432.033, "dur": 2.953, + "args": { + "External id": 3722317,"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": 1625852106432.584, "dur": 2.325, + "args": { + "External id": 3722318,"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": 1625852106438.871, "dur": 3.517, + "args": { + "External id": 3722319,"Record function id": 0, "Ev Idx": 2126 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852106439.971, "dur": 1.965, + "args": { + "External id": 3722320,"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": 1625852106440.407, "dur": 1.129, + "args": { + "External id": 3722321,"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": 1625852106440.701, "dur": 0.768, + "args": { + "External id": 3722322,"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": 1625852106445.441, "dur": 3.683, + "args": { + "External id": 3722323,"Record function id": 0, "Ev Idx": 2130 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852106446.667, "dur": 2.039, + "args": { + "External id": 3722324,"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": 1625852106447.112, "dur": 1.144, + "args": { + "External id": 3722325,"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": 1625852106447.444, "dur": 0.747, + "args": { + "External id": 3722326,"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": 1625852106452.424, "dur": 6.098, + "args": { + "External id": 3722327,"Record function id": 0, "Ev Idx": 2134 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852106453.722, "dur": 4.391, + "args": { + "External id": 3722328,"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": 1625852106454.429, "dur": 3.269, + "args": { + "External id": 3722329,"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": 1625852106457.024, "dur": 0.609, + "args": { + "External id": 3722330,"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": 1625852106461.724, "dur": 4.418, + "args": { + "External id": 3722331,"Record function id": 0, "Ev Idx": 2138 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852106463.367, "dur": 2.360, + "args": { + "External id": 3722332,"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": 1625852106463.991, "dur": 1.330, + "args": { + "External id": 3722333,"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": 1625852106464.495, "dur": 0.759, + "args": { + "External id": 3722334,"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": 1625852106469.100, "dur": 4.036, + "args": { + "External id": 3722335,"Record function id": 0, "Ev Idx": 2142 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852106470.442, "dur": 2.295, + "args": { + "External id": 3722336,"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": 1625852106471.132, "dur": 1.199, + "args": { + "External id": 3722337,"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": 1625852106471.394, "dur": 0.873, + "args": { + "External id": 3722338,"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": 1625852106476.461, "dur": 38012.555, + "args": { + "External id": 3722339,"Record function id": 0, "Sequence number": 37295121, "Fwd thread id": 1, "Ev Idx": 2146 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1625852106477.878, "dur": 38002.626, + "args": { + "External id": 3722340,"Sequence number": 37295121, "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": 1625852106477.878, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.24)", "pid": 1336756, "tid": 1381189, + "ts": 1625852106504.826, "dur": 39.000, + "args": { + "External id": 3722341,"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": 1625852106551.837, "dur": 63.513, + "args": { + "External id": 3722342,"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": 1625852106623.066, "dur": 37849.304, + "args": { + "External id": 3722343,"Record function id": 0, "Ev Idx": 2150 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1625852106727.819, "dur": 7.492, + "args": { + "External id": 3722344,"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": 1625852106746.315, "dur": 4.950, + "args": { + "External id": 3722345,"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": 1625852106766.227, "dur": 36851.734, + "args": { + "External id": 3722346,"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": 1625852106780.322, "dur": 36829.031, + "args": { + "External id": 3722347,"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": 1625852106833.267, "dur": 16.365, + "args": { + "External id": 3722348,"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": 1625852106856.286, "dur": 36711.842, + "args": { + "External id": 3722349,"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": 1625852106860.964, "dur": 36706.433, + "args": { + "External id": 3722350,"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": 1625852106864.869, "dur": 4.612, + "args": { + "External id": 3722351,"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": 1625852106871.140, "dur": 36692.660, + "args": { + "External id": 3722352,"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": 1625852143722.788, "dur": 8.976, + "args": { + "External id": 3722353,"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": 1625852143725.982, "dur": 5.265, + "args": { + "External id": 3722354,"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": 1625852143764.986, "dur": 390.982, + "args": { + "External id": 3722355,"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": 1625852143798.067, "dur": 352.789, + "args": { + "External id": 3722356,"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": 1625852143809.332, "dur": 335.313, + "args": { + "External id": 3722357,"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": 1625852144185.357, "dur": 2.367, + "args": { + "External id": 3722358,"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": 1625852144252.257, "dur": 6.751, + "args": { + "External id": 3722359,"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": 1625852144305.499, "dur": 1.398, + "args": { + "External id": 3722360,"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": 1625852144323.783, "dur": 1.357, + "args": { + "External id": 3722361,"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": 1625852144337.846, "dur": 2.860, + "args": { + "External id": 3722362,"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": 1625852144354.253, "dur": 0.783, + "args": { + "External id": 3722363,"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": 1625852144366.325, "dur": 1.349, + "args": { + "External id": 3722364,"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": 1625852144379.658, "dur": 1.473, + "args": { + "External id": 3722365,"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": 1625852144393.663, "dur": 4.653, + "args": { + "External id": 3722366,"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": 1625852144411.133, "dur": 0.894, + "args": { + "External id": 3722367,"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": 1625852144503.220, "dur": 2754.823, + "args": { + "External id": 3722368,"Record function id": 0, "Ev Idx": 2175 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.23)", "pid": 1336756, "tid": 1381189, + "ts": 1625852144521.619, "dur": 1033.890, + "args": { + "External id": 3722369,"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": 1625852144536.644, "dur": 339.822, + "args": { + "External id": 3722370,"Record function id": 0, "Ev Idx": 2177 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1625852144614.018, "dur": 3.992, + "args": { + "External id": 3722371,"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": 1625852144620.998, "dur": 1.158, + "args": { + "External id": 3722372,"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": 1625852144623.983, "dur": 1.200, + "args": { + "External id": 3722373,"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": 1625852144627.429, "dur": 0.818, + "args": { + "External id": 3722374,"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": 1625852144631.636, "dur": 3.245, + "args": { + "External id": 3722375,"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": 1625852144636.556, "dur": 0.816, + "args": { + "External id": 3722376,"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": 1625852144638.858, "dur": 1.750, + "args": { + "External id": 3722377,"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": 1625852144641.930, "dur": 0.941, + "args": { + "External id": 3722378,"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": 1625852144646.152, "dur": 0.656, + "args": { + "External id": 3722379,"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": 1625852144648.419, "dur": 0.829, + "args": { + "External id": 3722380,"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": 1625852144667.194, "dur": 174.481, + "args": { + "External id": 3722381,"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": 1625852144702.718, "dur": 134.536, + "args": { + "External id": 3722382,"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": 1625852144721.643, "dur": 16.075, + "args": { + "External id": 3722383,"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": 1625852144740.977, "dur": 67.481, + "args": { + "External id": 3722384,"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": 1625852144743.824, "dur": 64.329, + "args": { + "External id": 3722385,"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": 1625852144747.941, "dur": 5.331, + "args": { + "External id": 3722386,"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": 1625852144756.967, "dur": 50.527, + "args": { + "External id": 3722387,"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": 1625852144956.603, "dur": 591.421, + "args": { + "External id": 3722388,"Record function id": 0, "Ev Idx": 2195 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.22)", "pid": 1336756, "tid": 1381189, + "ts": 1625852144972.941, "dur": 563.878, + "args": { + "External id": 3722389,"Record function id": 0, "Ev Idx": 2196 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1625852145072.051, "dur": 7.996, + "args": { + "External id": 3722390,"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": 1625852145095.580, "dur": 33.077, + "args": { + "External id": 3722391,"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": 1625852145100.585, "dur": 1.820, + "args": { + "External id": 3722392,"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": 1625852145105.740, "dur": 0.542, + "args": { + "External id": 3722393,"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": 1625852145107.839, "dur": 0.354, + "args": { + "External id": 3722394,"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": 1625852145109.506, "dur": 1.627, + "args": { + "External id": 3722395,"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": 1625852145112.540, "dur": 0.250, + "args": { + "External id": 3722396,"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": 1625852145114.119, "dur": 0.354, + "args": { + "External id": 3722397,"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": 1625852145117.621, "dur": 0.243, + "args": { + "External id": 3722398,"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": 1625852145119.366, "dur": 2.178, + "args": { + "External id": 3722399,"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": 1625852145122.876, "dur": 0.693, + "args": { + "External id": 3722400,"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": 1625852145141.842, "dur": 33.214, + "args": { + "External id": 3722401,"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": 1625852145209.235, "dur": 98.515, + "args": { + "External id": 3722402,"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": 1625852145219.386, "dur": 2.893, + "args": { + "External id": 3722403,"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": 1625852145227.172, "dur": 10.503, + "args": { + "External id": 3722404,"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": 1625852145231.224, "dur": 6.008, + "args": { + "External id": 3722405,"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": 1625852145234.496, "dur": 1.553, + "args": { + "External id": 3722406,"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": 1625852145243.777, "dur": 29.692, + "args": { + "External id": 3722407,"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": 1625852145246.037, "dur": 0.662, + "args": { + "External id": 3722408,"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": 1625852145248.260, "dur": 0.888, + "args": { + "External id": 3722409,"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": 1625852145250.408, "dur": 0.627, + "args": { + "External id": 3722410,"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": 1625852145253.602, "dur": 0.267, + "args": { + "External id": 3722411,"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": 1625852145255.377, "dur": 2.808, + "args": { + "External id": 3722412,"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": 1625852145259.920, "dur": 1.869, + "args": { + "External id": 3722413,"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": 1625852145263.538, "dur": 0.286, + "args": { + "External id": 3722414,"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": 1625852145265.241, "dur": 0.343, + "args": { + "External id": 3722415,"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": 1625852145268.805, "dur": 0.277, + "args": { + "External id": 3722416,"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": 1625852145282.552, "dur": 18.143, + "args": { + "External id": 3722417,"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": 1625852145351.170, "dur": 117.917, + "args": { + "External id": 3722418,"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": 1625852145379.194, "dur": 86.672, + "args": { + "External id": 3722419,"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": 1625852145388.824, "dur": 71.940, + "args": { + "External id": 3722420,"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": 1625852145487.786, "dur": 1.936, + "args": { + "External id": 3722421,"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": 1625852145563.275, "dur": 1673.893, + "args": { + "External id": 3722422,"Sequence number": 37295120, "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": 1625852145563.275, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1625852145665.374, "dur": 122.310, + "args": { + "External id": 3722423,"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": 1625852145838.323, "dur": 42.592, + "args": { + "External id": 3722424,"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": 1625852145897.448, "dur": 50.101, + "args": { + "External id": 3722425,"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": 1625852145956.158, "dur": 73.733, + "args": { + "External id": 3722426,"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": 1625852146042.420, "dur": 50.315, + "args": { + "External id": 3722427,"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": 1625852146101.114, "dur": 28.232, + "args": { + "External id": 3722428,"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": 1625852146136.515, "dur": 41.622, + "args": { + "External id": 3722429,"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": 1625852146204.413, "dur": 23.868, + "args": { + "External id": 3722430,"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": 1625852146246.977, "dur": 28.964, + "args": { + "External id": 3722431,"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": 1625852146299.754, "dur": 18.899, + "args": { + "External id": 3722432,"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": 1625852146332.107, "dur": 15.629, + "args": { + "External id": 3722433,"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": 1625852146356.780, "dur": 30.452, + "args": { + "External id": 3722434,"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": 1625852146390.319, "dur": 31.953, + "args": { + "External id": 3722435,"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": 1625852146450.730, "dur": 166.802, + "args": { + "External id": 3722436,"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": 1625852146526.070, "dur": 6.528, + "args": { + "External id": 3722437,"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": 1625852146534.566, "dur": 2.329, + "args": { + "External id": 3722438,"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": 1625852146649.342, "dur": 23.289, + "args": { + "External id": 3722439,"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": 1625852146702.205, "dur": 18.206, + "args": { + "External id": 3722440,"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": 1625852146729.581, "dur": 40.074, + "args": { + "External id": 3722441,"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": 1625852146778.174, "dur": 34.440, + "args": { + "External id": 3722442,"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": 1625852146827.687, "dur": 25.462, + "args": { + "External id": 3722443,"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": 1625852146858.763, "dur": 29.429, + "args": { + "External id": 3722444,"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": 1625852146894.390, "dur": 21.457, + "args": { + "External id": 3722445,"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": 1625852146923.314, "dur": 37.069, + "args": { + "External id": 3722446,"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": 1625852147022.674, "dur": 33.566, + "args": { + "External id": 3722447,"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": 1625852147077.920, "dur": 28.180, + "args": { + "External id": 3722448,"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": 1625852147123.163, "dur": 18.029, + "args": { + "External id": 3722449,"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": 1625852147163.268, "dur": 15.077, + "args": { + "External id": 3722450,"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": 1625852147193.190, "dur": 15.716, + "args": { + "External id": 3722451,"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": 1625852147279.855, "dur": 15.659, + "args": { + "External id": 3722452,"Record function id": 0, "Ev Idx": 2259 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852147283.501, "dur": 11.073, + "args": { + "External id": 3722453,"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": 1625852147288.101, "dur": 5.608, + "args": { + "External id": 3722454,"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": 1625852147289.710, "dur": 3.903, + "args": { + "External id": 3722455,"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": 1625852147299.375, "dur": 4.572, + "args": { + "External id": 3722456,"Record function id": 0, "Ev Idx": 2263 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852147300.771, "dur": 2.714, + "args": { + "External id": 3722457,"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": 1625852147301.522, "dur": 1.417, + "args": { + "External id": 3722458,"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": 1625852147301.989, "dur": 0.870, + "args": { + "External id": 3722459,"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": 1625852147307.270, "dur": 4.557, + "args": { + "External id": 3722460,"Record function id": 0, "Ev Idx": 2267 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852147308.682, "dur": 2.724, + "args": { + "External id": 3722461,"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": 1625852147309.390, "dur": 1.623, + "args": { + "External id": 3722462,"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": 1625852147310.177, "dur": 0.689, + "args": { + "External id": 3722463,"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": 1625852147314.929, "dur": 6.084, + "args": { + "External id": 3722464,"Record function id": 0, "Ev Idx": 2271 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852147316.122, "dur": 4.482, + "args": { + "External id": 3722465,"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": 1625852147316.735, "dur": 3.472, + "args": { + "External id": 3722466,"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": 1625852147317.232, "dur": 2.898, + "args": { + "External id": 3722467,"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": 1625852147324.008, "dur": 4.544, + "args": { + "External id": 3722468,"Record function id": 0, "Ev Idx": 2275 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852147325.299, "dur": 2.802, + "args": { + "External id": 3722469,"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": 1625852147325.961, "dur": 1.711, + "args": { + "External id": 3722470,"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": 1625852147326.634, "dur": 0.936, + "args": { + "External id": 3722471,"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": 1625852147331.677, "dur": 3.915, + "args": { + "External id": 3722472,"Record function id": 0, "Ev Idx": 2279 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852147332.878, "dur": 2.320, + "args": { + "External id": 3722473,"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": 1625852147333.510, "dur": 1.303, + "args": { + "External id": 3722474,"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": 1625852147334.099, "dur": 0.649, + "args": { + "External id": 3722475,"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": 1625852147338.714, "dur": 3.806, + "args": { + "External id": 3722476,"Record function id": 0, "Ev Idx": 2283 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852147339.861, "dur": 2.266, + "args": { + "External id": 3722477,"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": 1625852147340.550, "dur": 1.186, + "args": { + "External id": 3722478,"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": 1625852147340.880, "dur": 0.788, + "args": { + "External id": 3722479,"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": 1625852147345.618, "dur": 5.852, + "args": { + "External id": 3722480,"Record function id": 0, "Ev Idx": 2287 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852147346.938, "dur": 4.142, + "args": { + "External id": 3722481,"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": 1625852147347.607, "dur": 3.074, + "args": { + "External id": 3722482,"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": 1625852147350.083, "dur": 0.533, + "args": { + "External id": 3722483,"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": 1625852147354.460, "dur": 3.358, + "args": { + "External id": 3722484,"Record function id": 0, "Ev Idx": 2291 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852147355.459, "dur": 1.942, + "args": { + "External id": 3722485,"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": 1625852147355.993, "dur": 1.004, + "args": { + "External id": 3722486,"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": 1625852147356.275, "dur": 0.655, + "args": { + "External id": 3722487,"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": 1625852147361.442, "dur": 38172.679, + "args": { + "External id": 3722488,"Record function id": 0, "Sequence number": 37295119, "Fwd thread id": 1, "Ev Idx": 2295 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1625852147362.838, "dur": 38163.342, + "args": { + "External id": 3722489,"Sequence number": 37295119, "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": 1625852147362.838, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.23)", "pid": 1336756, "tid": 1381189, + "ts": 1625852147393.342, "dur": 37.495, + "args": { + "External id": 3722490,"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": 1625852147439.019, "dur": 62.139, + "args": { + "External id": 3722491,"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": 1625852147506.976, "dur": 38011.853, + "args": { + "External id": 3722492,"Record function id": 0, "Ev Idx": 2299 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1625852147590.121, "dur": 6.487, + "args": { + "External id": 3722493,"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": 1625852147606.144, "dur": 5.063, + "args": { + "External id": 3722494,"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": 1625852147627.026, "dur": 37074.451, + "args": { + "External id": 3722495,"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": 1625852147640.458, "dur": 37051.296, + "args": { + "External id": 3722496,"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": 1625852147706.337, "dur": 16.142, + "args": { + "External id": 3722497,"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": 1625852147729.050, "dur": 36913.653, + "args": { + "External id": 3722498,"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": 1625852147733.108, "dur": 36908.961, + "args": { + "External id": 3722499,"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": 1625852147737.279, "dur": 5.706, + "args": { + "External id": 3722500,"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": 1625852147744.602, "dur": 36893.942, + "args": { + "External id": 3722501,"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": 1625852184790.527, "dur": 8.124, + "args": { + "External id": 3722502,"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": 1625852184793.622, "dur": 4.706, + "args": { + "External id": 3722503,"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": 1625852184827.686, "dur": 386.417, + "args": { + "External id": 3722504,"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": 1625852184858.952, "dur": 350.112, + "args": { + "External id": 3722505,"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": 1625852184870.088, "dur": 332.435, + "args": { + "External id": 3722506,"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": 1625852185237.341, "dur": 2.171, + "args": { + "External id": 3722507,"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": 1625852185299.239, "dur": 6.377, + "args": { + "External id": 3722508,"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": 1625852185351.839, "dur": 1.319, + "args": { + "External id": 3722509,"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": 1625852185370.186, "dur": 1.640, + "args": { + "External id": 3722510,"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": 1625852185386.952, "dur": 1.002, + "args": { + "External id": 3722511,"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": 1625852185401.407, "dur": 0.871, + "args": { + "External id": 3722512,"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": 1625852185414.214, "dur": 1.096, + "args": { + "External id": 3722513,"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": 1625852185427.183, "dur": 1.146, + "args": { + "External id": 3722514,"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": 1625852185443.802, "dur": 2.682, + "args": { + "External id": 3722515,"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": 1625852185457.694, "dur": 0.910, + "args": { + "External id": 3722516,"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": 1625852185548.427, "dur": 2823.152, + "args": { + "External id": 3722517,"Record function id": 0, "Ev Idx": 2324 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.22)", "pid": 1336756, "tid": 1381189, + "ts": 1625852185569.802, "dur": 1045.220, + "args": { + "External id": 3722518,"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": 1625852185584.568, "dur": 338.572, + "args": { + "External id": 3722519,"Record function id": 0, "Ev Idx": 2326 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1625852185665.344, "dur": 3.843, + "args": { + "External id": 3722520,"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": 1625852185672.190, "dur": 1.274, + "args": { + "External id": 3722521,"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": 1625852185675.411, "dur": 17.669, + "args": { + "External id": 3722522,"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": 1625852185697.073, "dur": 3.291, + "args": { + "External id": 3722523,"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": 1625852185702.079, "dur": 1.133, + "args": { + "External id": 3722524,"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": 1625852185705.005, "dur": 0.842, + "args": { + "External id": 3722525,"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": 1625852185707.580, "dur": 2.194, + "args": { + "External id": 3722526,"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": 1625852185711.148, "dur": 1.097, + "args": { + "External id": 3722527,"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": 1625852185713.732, "dur": 1.424, + "args": { + "External id": 3722528,"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": 1625852185716.589, "dur": 1.199, + "args": { + "External id": 3722529,"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": 1625852185736.777, "dur": 152.328, + "args": { + "External id": 3722530,"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": 1625852185752.803, "dur": 131.694, + "args": { + "External id": 3722531,"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": 1625852185772.761, "dur": 12.966, + "args": { + "External id": 3722532,"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": 1625852185788.743, "dur": 67.781, + "args": { + "External id": 3722533,"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": 1625852185791.180, "dur": 65.048, + "args": { + "External id": 3722534,"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": 1625852185795.473, "dur": 8.144, + "args": { + "External id": 3722535,"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": 1625852185805.505, "dur": 50.083, + "args": { + "External id": 3722536,"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": 1625852186048.048, "dur": 559.314, + "args": { + "External id": 3722537,"Record function id": 0, "Ev Idx": 2344 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.21)", "pid": 1336756, "tid": 1381189, + "ts": 1625852186067.037, "dur": 527.093, + "args": { + "External id": 3722538,"Record function id": 0, "Ev Idx": 2345 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1625852186127.830, "dur": 5.981, + "args": { + "External id": 3722539,"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": 1625852186149.140, "dur": 31.903, + "args": { + "External id": 3722540,"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": 1625852186154.592, "dur": 1.608, + "args": { + "External id": 3722541,"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": 1625852186158.641, "dur": 0.562, + "args": { + "External id": 3722542,"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": 1625852186160.701, "dur": 0.454, + "args": { + "External id": 3722543,"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": 1625852186162.838, "dur": 0.397, + "args": { + "External id": 3722544,"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": 1625852186165.186, "dur": 0.401, + "args": { + "External id": 3722545,"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": 1625852186167.507, "dur": 0.509, + "args": { + "External id": 3722546,"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": 1625852186169.758, "dur": 2.451, + "args": { + "External id": 3722547,"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": 1625852186173.848, "dur": 0.506, + "args": { + "External id": 3722548,"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": 1625852186176.340, "dur": 0.445, + "args": { + "External id": 3722549,"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": 1625852186196.100, "dur": 35.606, + "args": { + "External id": 3722550,"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": 1625852186265.194, "dur": 101.695, + "args": { + "External id": 3722551,"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": 1625852186275.611, "dur": 2.721, + "args": { + "External id": 3722552,"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": 1625852186283.293, "dur": 11.054, + "args": { + "External id": 3722553,"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": 1625852186288.143, "dur": 5.763, + "args": { + "External id": 3722554,"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": 1625852186292.090, "dur": 0.655, + "args": { + "External id": 3722555,"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": 1625852186301.201, "dur": 27.096, + "args": { + "External id": 3722556,"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": 1625852186303.652, "dur": 0.417, + "args": { + "External id": 3722557,"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": 1625852186305.950, "dur": 0.418, + "args": { + "External id": 3722558,"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": 1625852186308.124, "dur": 0.694, + "args": { + "External id": 3722559,"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": 1625852186310.674, "dur": 2.577, + "args": { + "External id": 3722560,"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": 1625852186314.945, "dur": 0.446, + "args": { + "External id": 3722561,"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": 1625852186316.984, "dur": 0.538, + "args": { + "External id": 3722562,"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": 1625852186319.063, "dur": 0.464, + "args": { + "External id": 3722563,"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": 1625852186321.508, "dur": 0.425, + "args": { + "External id": 3722564,"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": 1625852186323.457, "dur": 0.407, + "args": { + "External id": 3722565,"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": 1625852186339.410, "dur": 20.479, + "args": { + "External id": 3722566,"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": 1625852186413.880, "dur": 114.742, + "args": { + "External id": 3722567,"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": 1625852186436.989, "dur": 88.269, + "args": { + "External id": 3722568,"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": 1625852186446.925, "dur": 74.362, + "args": { + "External id": 3722569,"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": 1625852186544.366, "dur": 1.727, + "args": { + "External id": 3722570,"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": 1625852186622.291, "dur": 1730.338, + "args": { + "External id": 3722571,"Sequence number": 37295118, "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": 1625852186622.291, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1625852186747.635, "dur": 106.336, + "args": { + "External id": 3722572,"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": 1625852186894.533, "dur": 40.829, + "args": { + "External id": 3722573,"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": 1625852186952.795, "dur": 92.655, + "args": { + "External id": 3722574,"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": 1625852187059.303, "dur": 42.487, + "args": { + "External id": 3722575,"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": 1625852187112.027, "dur": 52.306, + "args": { + "External id": 3722576,"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": 1625852187172.434, "dur": 28.878, + "args": { + "External id": 3722577,"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": 1625852187208.935, "dur": 45.893, + "args": { + "External id": 3722578,"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": 1625852187278.188, "dur": 24.947, + "args": { + "External id": 3722579,"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": 1625852187335.129, "dur": 30.496, + "args": { + "External id": 3722580,"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": 1625852187385.114, "dur": 18.871, + "args": { + "External id": 3722581,"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": 1625852187416.769, "dur": 16.227, + "args": { + "External id": 3722582,"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": 1625852187443.467, "dur": 30.987, + "args": { + "External id": 3722583,"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": 1625852187477.503, "dur": 34.727, + "args": { + "External id": 3722584,"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": 1625852187541.829, "dur": 192.061, + "args": { + "External id": 3722585,"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": 1625852187625.427, "dur": 5.707, + "args": { + "External id": 3722586,"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": 1625852187633.351, "dur": 2.036, + "args": { + "External id": 3722587,"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": 1625852187767.036, "dur": 27.411, + "args": { + "External id": 3722588,"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": 1625852187806.247, "dur": 15.245, + "args": { + "External id": 3722589,"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": 1625852187831.169, "dur": 41.042, + "args": { + "External id": 3722590,"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": 1625852187879.200, "dur": 36.418, + "args": { + "External id": 3722591,"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": 1625852187923.898, "dur": 23.261, + "args": { + "External id": 3722592,"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": 1625852187952.555, "dur": 65.805, + "args": { + "External id": 3722593,"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": 1625852188048.010, "dur": 36.538, + "args": { + "External id": 3722594,"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": 1625852188092.899, "dur": 33.354, + "args": { + "External id": 3722595,"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": 1625852188145.975, "dur": 26.602, + "args": { + "External id": 3722596,"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": 1625852188192.757, "dur": 24.967, + "args": { + "External id": 3722597,"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": 1625852188232.123, "dur": 21.504, + "args": { + "External id": 3722598,"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": 1625852188269.623, "dur": 15.947, + "args": { + "External id": 3722599,"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": 1625852188306.283, "dur": 17.277, + "args": { + "External id": 3722600,"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": 1625852188394.446, "dur": 16.117, + "args": { + "External id": 3722601,"Record function id": 0, "Ev Idx": 2408 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852188398.086, "dur": 11.626, + "args": { + "External id": 3722602,"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": 1625852188402.747, "dur": 6.014, + "args": { + "External id": 3722603,"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": 1625852188404.363, "dur": 4.276, + "args": { + "External id": 3722604,"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": 1625852188414.527, "dur": 5.418, + "args": { + "External id": 3722605,"Record function id": 0, "Ev Idx": 2412 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852188416.051, "dur": 3.465, + "args": { + "External id": 3722606,"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": 1625852188417.108, "dur": 1.877, + "args": { + "External id": 3722607,"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": 1625852188417.893, "dur": 0.998, + "args": { + "External id": 3722608,"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": 1625852188423.177, "dur": 7.519, + "args": { + "External id": 3722609,"Record function id": 0, "Ev Idx": 2416 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852188424.971, "dur": 5.222, + "args": { + "External id": 3722610,"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": 1625852188426.077, "dur": 3.658, + "args": { + "External id": 3722611,"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": 1625852188426.379, "dur": 3.296, + "args": { + "External id": 3722612,"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": 1625852188433.903, "dur": 4.495, + "args": { + "External id": 3722613,"Record function id": 0, "Ev Idx": 2420 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852188435.180, "dur": 2.832, + "args": { + "External id": 3722614,"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": 1625852188435.687, "dur": 1.833, + "args": { + "External id": 3722615,"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": 1625852188436.216, "dur": 1.240, + "args": { + "External id": 3722616,"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": 1625852188441.544, "dur": 4.379, + "args": { + "External id": 3722617,"Record function id": 0, "Ev Idx": 2424 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852188443.136, "dur": 2.391, + "args": { + "External id": 3722618,"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": 1625852188444.088, "dur": 1.026, + "args": { + "External id": 3722619,"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": 1625852188444.377, "dur": 0.669, + "args": { + "External id": 3722620,"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": 1625852188448.958, "dur": 4.024, + "args": { + "External id": 3722621,"Record function id": 0, "Ev Idx": 2428 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852188450.214, "dur": 2.340, + "args": { + "External id": 3722622,"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": 1625852188450.756, "dur": 1.330, + "args": { + "External id": 3722623,"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": 1625852188451.278, "dur": 0.707, + "args": { + "External id": 3722624,"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": 1625852188456.205, "dur": 3.872, + "args": { + "External id": 3722625,"Record function id": 0, "Ev Idx": 2432 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852188457.385, "dur": 2.296, + "args": { + "External id": 3722626,"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": 1625852188458.062, "dur": 1.224, + "args": { + "External id": 3722627,"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": 1625852188458.319, "dur": 0.889, + "args": { + "External id": 3722628,"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": 1625852188463.129, "dur": 4.028, + "args": { + "External id": 3722629,"Record function id": 0, "Ev Idx": 2436 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852188464.364, "dur": 2.362, + "args": { + "External id": 3722630,"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": 1625852188465.049, "dur": 1.267, + "args": { + "External id": 3722631,"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": 1625852188465.342, "dur": 0.880, + "args": { + "External id": 3722632,"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": 1625852188470.151, "dur": 4.158, + "args": { + "External id": 3722633,"Record function id": 0, "Ev Idx": 2440 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852188471.595, "dur": 2.336, + "args": { + "External id": 3722634,"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": 1625852188472.269, "dur": 1.221, + "args": { + "External id": 3722635,"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": 1625852188472.705, "dur": 0.670, + "args": { + "External id": 3722636,"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": 1625852188478.235, "dur": 38029.254, + "args": { + "External id": 3722637,"Record function id": 0, "Sequence number": 37295117, "Fwd thread id": 1, "Ev Idx": 2444 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1625852188479.507, "dur": 38019.807, + "args": { + "External id": 3722638,"Sequence number": 37295117, "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": 1625852188479.507, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.22)", "pid": 1336756, "tid": 1381189, + "ts": 1625852188509.352, "dur": 36.525, + "args": { + "External id": 3722639,"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": 1625852188553.252, "dur": 60.986, + "args": { + "External id": 3722640,"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": 1625852188620.512, "dur": 37871.359, + "args": { + "External id": 3722641,"Record function id": 0, "Ev Idx": 2448 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1625852188733.635, "dur": 7.639, + "args": { + "External id": 3722642,"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": 1625852188751.954, "dur": 6.697, + "args": { + "External id": 3722643,"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": 1625852188773.833, "dur": 36834.684, + "args": { + "External id": 3722644,"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": 1625852188788.226, "dur": 36811.102, + "args": { + "External id": 3722645,"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": 1625852188832.731, "dur": 13.732, + "args": { + "External id": 3722646,"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": 1625852188853.121, "dur": 36703.230, + "args": { + "External id": 3722647,"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": 1625852188855.977, "dur": 36699.721, + "args": { + "External id": 3722648,"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": 1625852188860.217, "dur": 5.018, + "args": { + "External id": 3722649,"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": 1625852188867.255, "dur": 36684.860, + "args": { + "External id": 3722650,"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": 1625852225710.996, "dur": 9.369, + "args": { + "External id": 3722651,"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": 1625852225714.256, "dur": 5.658, + "args": { + "External id": 3722652,"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": 1625852225755.122, "dur": 426.120, + "args": { + "External id": 3722653,"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": 1625852225782.460, "dur": 393.118, + "args": { + "External id": 3722654,"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": 1625852225793.539, "dur": 375.359, + "args": { + "External id": 3722655,"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": 1625852226203.824, "dur": 2.583, + "args": { + "External id": 3722656,"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": 1625852226269.093, "dur": 6.924, + "args": { + "External id": 3722657,"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": 1625852226324.053, "dur": 2.395, + "args": { + "External id": 3722658,"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": 1625852226344.040, "dur": 3.021, + "args": { + "External id": 3722659,"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": 1625852226359.939, "dur": 1.051, + "args": { + "External id": 3722660,"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": 1625852226374.369, "dur": 1.002, + "args": { + "External id": 3722661,"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": 1625852226388.016, "dur": 1.098, + "args": { + "External id": 3722662,"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": 1625852226401.987, "dur": 3.016, + "args": { + "External id": 3722663,"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": 1625852226418.161, "dur": 2.745, + "args": { + "External id": 3722664,"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": 1625852226433.135, "dur": 1.171, + "args": { + "External id": 3722665,"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": 1625852226522.466, "dur": 2833.416, + "args": { + "External id": 3722666,"Record function id": 0, "Ev Idx": 2473 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.21)", "pid": 1336756, "tid": 1381189, + "ts": 1625852226541.465, "dur": 1021.037, + "args": { + "External id": 3722667,"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": 1625852226556.319, "dur": 341.390, + "args": { + "External id": 3722668,"Record function id": 0, "Ev Idx": 2475 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1625852226631.453, "dur": 3.963, + "args": { + "External id": 3722669,"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": 1625852226638.381, "dur": 1.215, + "args": { + "External id": 3722670,"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": 1625852226641.417, "dur": 3.379, + "args": { + "External id": 3722671,"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": 1625852226646.442, "dur": 1.217, + "args": { + "External id": 3722672,"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": 1625852226649.548, "dur": 1.394, + "args": { + "External id": 3722673,"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": 1625852226652.622, "dur": 0.960, + "args": { + "External id": 3722674,"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": 1625852226655.120, "dur": 1.996, + "args": { + "External id": 3722675,"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": 1625852226658.635, "dur": 1.118, + "args": { + "External id": 3722676,"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": 1625852226661.265, "dur": 0.796, + "args": { + "External id": 3722677,"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": 1625852226663.564, "dur": 1.010, + "args": { + "External id": 3722678,"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": 1625852226698.373, "dur": 163.805, + "args": { + "External id": 3722679,"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": 1625852226726.220, "dur": 131.438, + "args": { + "External id": 3722680,"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": 1625852226742.926, "dur": 13.834, + "args": { + "External id": 3722681,"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": 1625852226760.161, "dur": 69.459, + "args": { + "External id": 3722682,"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": 1625852226763.079, "dur": 66.143, + "args": { + "External id": 3722683,"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": 1625852226767.365, "dur": 5.490, + "args": { + "External id": 3722684,"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": 1625852226774.827, "dur": 53.662, + "args": { + "External id": 3722685,"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": 1625852226974.364, "dur": 579.742, + "args": { + "External id": 3722686,"Record function id": 0, "Ev Idx": 2493 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.20)", "pid": 1336756, "tid": 1381189, + "ts": 1625852227029.558, "dur": 511.365, + "args": { + "External id": 3722687,"Record function id": 0, "Ev Idx": 2494 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1625852227091.737, "dur": 6.174, + "args": { + "External id": 3722688,"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": 1625852227112.678, "dur": 34.358, + "args": { + "External id": 3722689,"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": 1625852227118.335, "dur": 1.851, + "args": { + "External id": 3722690,"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": 1625852227122.632, "dur": 0.511, + "args": { + "External id": 3722691,"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": 1625852227124.816, "dur": 0.796, + "args": { + "External id": 3722692,"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": 1625852227127.245, "dur": 0.435, + "args": { + "External id": 3722693,"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": 1625852227129.248, "dur": 0.443, + "args": { + "External id": 3722694,"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": 1625852227131.396, "dur": 2.200, + "args": { + "External id": 3722695,"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": 1625852227135.907, "dur": 0.667, + "args": { + "External id": 3722696,"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": 1625852227138.320, "dur": 0.416, + "args": { + "External id": 3722697,"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": 1625852227140.380, "dur": 0.424, + "args": { + "External id": 3722698,"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": 1625852227157.564, "dur": 34.317, + "args": { + "External id": 3722699,"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": 1625852227224.598, "dur": 100.968, + "args": { + "External id": 3722700,"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": 1625852227234.687, "dur": 2.562, + "args": { + "External id": 3722701,"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": 1625852227242.750, "dur": 10.415, + "args": { + "External id": 3722702,"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": 1625852227247.377, "dur": 5.365, + "args": { + "External id": 3722703,"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": 1625852227250.886, "dur": 0.502, + "args": { + "External id": 3722704,"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": 1625852227260.511, "dur": 27.364, + "args": { + "External id": 3722705,"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": 1625852227262.599, "dur": 0.917, + "args": { + "External id": 3722706,"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": 1625852227265.471, "dur": 0.725, + "args": { + "External id": 3722707,"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": 1625852227267.730, "dur": 2.086, + "args": { + "External id": 3722708,"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": 1625852227271.526, "dur": 0.436, + "args": { + "External id": 3722709,"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": 1625852227273.844, "dur": 0.400, + "args": { + "External id": 3722710,"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": 1625852227276.129, "dur": 0.568, + "args": { + "External id": 3722711,"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": 1625852227278.083, "dur": 0.578, + "args": { + "External id": 3722712,"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": 1625852227280.553, "dur": 0.440, + "args": { + "External id": 3722713,"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": 1625852227282.709, "dur": 0.576, + "args": { + "External id": 3722714,"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": 1625852227297.544, "dur": 20.920, + "args": { + "External id": 3722715,"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": 1625852227369.343, "dur": 111.577, + "args": { + "External id": 3722716,"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": 1625852227391.272, "dur": 86.286, + "args": { + "External id": 3722717,"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": 1625852227400.848, "dur": 72.428, + "args": { + "External id": 3722718,"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": 1625852227494.222, "dur": 1.810, + "args": { + "External id": 3722719,"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": 1625852227570.106, "dur": 1765.426, + "args": { + "External id": 3722720,"Sequence number": 37295116, "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": 1625852227570.106, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1625852227675.472, "dur": 121.813, + "args": { + "External id": 3722721,"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": 1625852227838.243, "dur": 40.850, + "args": { + "External id": 3722722,"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": 1625852227897.720, "dur": 51.194, + "args": { + "External id": 3722723,"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": 1625852227961.120, "dur": 74.008, + "args": { + "External id": 3722724,"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": 1625852228046.542, "dur": 52.425, + "args": { + "External id": 3722725,"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": 1625852228107.700, "dur": 29.560, + "args": { + "External id": 3722726,"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": 1625852228145.135, "dur": 43.966, + "args": { + "External id": 3722727,"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": 1625852228217.301, "dur": 26.314, + "args": { + "External id": 3722728,"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": 1625852228262.529, "dur": 31.013, + "args": { + "External id": 3722729,"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": 1625852228312.552, "dur": 21.298, + "args": { + "External id": 3722730,"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": 1625852228347.749, "dur": 15.741, + "args": { + "External id": 3722731,"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": 1625852228374.159, "dur": 32.437, + "args": { + "External id": 3722732,"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": 1625852228409.607, "dur": 33.656, + "args": { + "External id": 3722733,"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": 1625852228473.685, "dur": 177.265, + "args": { + "External id": 3722734,"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": 1625852228554.890, "dur": 6.006, + "args": { + "External id": 3722735,"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": 1625852228563.209, "dur": 2.702, + "args": { + "External id": 3722736,"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": 1625852228721.520, "dur": 29.956, + "args": { + "External id": 3722737,"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": 1625852228767.617, "dur": 15.663, + "args": { + "External id": 3722738,"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": 1625852228794.789, "dur": 43.197, + "args": { + "External id": 3722739,"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": 1625852228845.560, "dur": 35.788, + "args": { + "External id": 3722740,"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": 1625852228890.629, "dur": 23.146, + "args": { + "External id": 3722741,"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": 1625852228919.341, "dur": 30.274, + "args": { + "External id": 3722742,"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": 1625852228956.253, "dur": 86.001, + "args": { + "External id": 3722743,"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": 1625852229062.085, "dur": 45.613, + "args": { + "External id": 3722744,"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": 1625852229131.596, "dur": 32.864, + "args": { + "External id": 3722745,"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": 1625852229181.735, "dur": 24.707, + "args": { + "External id": 3722746,"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": 1625852229224.445, "dur": 17.990, + "args": { + "External id": 3722747,"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": 1625852229257.622, "dur": 15.494, + "args": { + "External id": 3722748,"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": 1625852229289.335, "dur": 16.719, + "args": { + "External id": 3722749,"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": 1625852229378.630, "dur": 40.865, + "args": { + "External id": 3722750,"Record function id": 0, "Ev Idx": 2557 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852229382.065, "dur": 36.459, + "args": { + "External id": 3722751,"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": 1625852229386.522, "dur": 31.013, + "args": { + "External id": 3722752,"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": 1625852229413.226, "dur": 4.180, + "args": { + "External id": 3722753,"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": 1625852229423.862, "dur": 6.903, + "args": { + "External id": 3722754,"Record function id": 0, "Ev Idx": 2561 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852229425.160, "dur": 5.082, + "args": { + "External id": 3722755,"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": 1625852229425.832, "dur": 3.835, + "args": { + "External id": 3722756,"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": 1625852229426.515, "dur": 3.053, + "args": { + "External id": 3722757,"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": 1625852229433.949, "dur": 4.379, + "args": { + "External id": 3722758,"Record function id": 0, "Ev Idx": 2565 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852229435.479, "dur": 2.460, + "args": { + "External id": 3722759,"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": 1625852229436.058, "dur": 1.449, + "args": { + "External id": 3722760,"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": 1625852229436.373, "dur": 1.053, + "args": { + "External id": 3722761,"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": 1625852229441.872, "dur": 3.915, + "args": { + "External id": 3722762,"Record function id": 0, "Ev Idx": 2569 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852229443.234, "dur": 2.138, + "args": { + "External id": 3722763,"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": 1625852229443.802, "dur": 1.165, + "args": { + "External id": 3722764,"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": 1625852229444.195, "dur": 0.694, + "args": { + "External id": 3722765,"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": 1625852229449.343, "dur": 3.469, + "args": { + "External id": 3722766,"Record function id": 0, "Ev Idx": 2573 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852229450.418, "dur": 1.985, + "args": { + "External id": 3722767,"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": 1625852229451.042, "dur": 0.833, + "args": { + "External id": 3722768,"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": 1625852229451.316, "dur": 0.495, + "args": { + "External id": 3722769,"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": 1625852229456.389, "dur": 3.641, + "args": { + "External id": 3722770,"Record function id": 0, "Ev Idx": 2577 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852229457.565, "dur": 2.075, + "args": { + "External id": 3722771,"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": 1625852229458.226, "dur": 0.977, + "args": { + "External id": 3722772,"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": 1625852229458.677, "dur": 0.462, + "args": { + "External id": 3722773,"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": 1625852229463.394, "dur": 3.912, + "args": { + "External id": 3722774,"Record function id": 0, "Ev Idx": 2581 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852229464.862, "dur": 2.044, + "args": { + "External id": 3722775,"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": 1625852229465.417, "dur": 1.058, + "args": { + "External id": 3722776,"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": 1625852229465.729, "dur": 0.666, + "args": { + "External id": 3722777,"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": 1625852229470.480, "dur": 6.045, + "args": { + "External id": 3722778,"Record function id": 0, "Ev Idx": 2585 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852229471.912, "dur": 4.213, + "args": { + "External id": 3722779,"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": 1625852229472.434, "dur": 3.266, + "args": { + "External id": 3722780,"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": 1625852229475.047, "dur": 0.553, + "args": { + "External id": 3722781,"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": 1625852229479.832, "dur": 5.679, + "args": { + "External id": 3722782,"Record function id": 0, "Ev Idx": 2589 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852229480.882, "dur": 4.218, + "args": { + "External id": 3722783,"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": 1625852229481.418, "dur": 3.273, + "args": { + "External id": 3722784,"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": 1625852229481.919, "dur": 2.695, + "args": { + "External id": 3722785,"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": 1625852229492.690, "dur": 37410.878, + "args": { + "External id": 3722786,"Record function id": 0, "Sequence number": 37295115, "Fwd thread id": 1, "Ev Idx": 2593 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1625852229494.232, "dur": 37401.181, + "args": { + "External id": 3722787,"Sequence number": 37295115, "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": 1625852229494.232, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.21)", "pid": 1336756, "tid": 1381189, + "ts": 1625852229524.972, "dur": 41.900, + "args": { + "External id": 3722788,"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": 1625852229574.701, "dur": 63.216, + "args": { + "External id": 3722789,"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": 1625852229643.619, "dur": 37243.597, + "args": { + "External id": 3722790,"Record function id": 0, "Ev Idx": 2597 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1625852229753.447, "dur": 6.926, + "args": { + "External id": 3722791,"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": 1625852229771.256, "dur": 5.401, + "args": { + "External id": 3722792,"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": 1625852229796.485, "dur": 36283.381, + "args": { + "External id": 3722793,"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": 1625852229810.341, "dur": 36260.646, + "args": { + "External id": 3722794,"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": 1625852229848.725, "dur": 14.760, + "args": { + "External id": 3722795,"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": 1625852229869.992, "dur": 36160.456, + "args": { + "External id": 3722796,"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": 1625852229872.731, "dur": 36156.889, + "args": { + "External id": 3722797,"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": 1625852229876.965, "dur": 4.893, + "args": { + "External id": 3722798,"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": 1625852229883.697, "dur": 36142.036, + "args": { + "External id": 3722799,"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": 1625852266169.130, "dur": 8.728, + "args": { + "External id": 3722800,"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": 1625852266172.438, "dur": 5.144, + "args": { + "External id": 3722801,"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": 1625852266209.599, "dur": 357.187, + "args": { + "External id": 3722802,"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": 1625852266236.697, "dur": 325.707, + "args": { + "External id": 3722803,"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": 1625852266247.663, "dur": 308.353, + "args": { + "External id": 3722804,"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": 1625852266586.213, "dur": 2.300, + "args": { + "External id": 3722805,"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": 1625852266642.779, "dur": 6.033, + "args": { + "External id": 3722806,"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": 1625852266715.436, "dur": 3.945, + "args": { + "External id": 3722807,"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": 1625852266737.694, "dur": 1.194, + "args": { + "External id": 3722808,"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": 1625852266752.059, "dur": 1.003, + "args": { + "External id": 3722809,"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": 1625852266766.429, "dur": 1.154, + "args": { + "External id": 3722810,"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": 1625852266779.286, "dur": 2.830, + "args": { + "External id": 3722811,"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": 1625852266794.987, "dur": 0.798, + "args": { + "External id": 3722812,"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": 1625852266809.214, "dur": 2.170, + "args": { + "External id": 3722813,"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": 1625852266823.074, "dur": 0.781, + "args": { + "External id": 3722814,"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": 1625852266919.744, "dur": 2795.473, + "args": { + "External id": 3722815,"Record function id": 0, "Ev Idx": 2622 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.20)", "pid": 1336756, "tid": 1381189, + "ts": 1625852266939.330, "dur": 1032.014, + "args": { + "External id": 3722816,"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": 1625852266955.561, "dur": 366.645, + "args": { + "External id": 3722817,"Record function id": 0, "Ev Idx": 2624 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1625852267073.878, "dur": 6.554, + "args": { + "External id": 3722818,"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": 1625852267084.110, "dur": 1.144, + "args": { + "External id": 3722819,"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": 1625852267087.069, "dur": 1.000, + "args": { + "External id": 3722820,"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": 1625852267089.906, "dur": 0.778, + "args": { + "External id": 3722821,"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": 1625852267092.097, "dur": 0.889, + "args": { + "External id": 3722822,"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": 1625852267095.266, "dur": 1.326, + "args": { + "External id": 3722823,"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": 1625852267098.329, "dur": 2.365, + "args": { + "External id": 3722824,"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": 1625852267102.239, "dur": 1.007, + "args": { + "External id": 3722825,"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": 1625852267104.658, "dur": 3.027, + "args": { + "External id": 3722826,"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": 1625852267109.279, "dur": 0.853, + "args": { + "External id": 3722827,"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": 1625852267130.730, "dur": 157.400, + "args": { + "External id": 3722828,"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": 1625852267147.334, "dur": 136.873, + "args": { + "External id": 3722829,"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": 1625852267171.048, "dur": 12.991, + "args": { + "External id": 3722830,"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": 1625852267187.410, "dur": 68.016, + "args": { + "External id": 3722831,"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": 1625852267189.924, "dur": 65.168, + "args": { + "External id": 3722832,"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": 1625852267194.296, "dur": 5.584, + "args": { + "External id": 3722833,"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": 1625852267201.939, "dur": 52.354, + "args": { + "External id": 3722834,"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": 1625852267402.142, "dur": 560.042, + "args": { + "External id": 3722835,"Record function id": 0, "Ev Idx": 2642 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.19)", "pid": 1336756, "tid": 1381189, + "ts": 1625852267420.357, "dur": 529.123, + "args": { + "External id": 3722836,"Record function id": 0, "Ev Idx": 2643 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1625852267477.376, "dur": 4.388, + "args": { + "External id": 3722837,"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": 1625852267496.280, "dur": 32.880, + "args": { + "External id": 3722838,"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": 1625852267501.681, "dur": 1.460, + "args": { + "External id": 3722839,"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": 1625852267505.670, "dur": 0.463, + "args": { + "External id": 3722840,"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": 1625852267508.043, "dur": 0.496, + "args": { + "External id": 3722841,"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": 1625852267510.335, "dur": 2.415, + "args": { + "External id": 3722842,"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": 1625852267514.786, "dur": 0.466, + "args": { + "External id": 3722843,"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": 1625852267517.125, "dur": 0.407, + "args": { + "External id": 3722844,"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": 1625852267519.271, "dur": 0.414, + "args": { + "External id": 3722845,"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": 1625852267521.200, "dur": 0.408, + "args": { + "External id": 3722846,"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": 1625852267523.553, "dur": 0.394, + "args": { + "External id": 3722847,"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": 1625852267538.953, "dur": 31.473, + "args": { + "External id": 3722848,"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": 1625852267601.467, "dur": 123.955, + "args": { + "External id": 3722849,"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": 1625852267611.244, "dur": 2.959, + "args": { + "External id": 3722850,"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": 1625852267619.718, "dur": 10.422, + "args": { + "External id": 3722851,"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": 1625852267623.833, "dur": 5.893, + "args": { + "External id": 3722852,"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": 1625852267627.893, "dur": 0.489, + "args": { + "External id": 3722853,"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": 1625852267636.678, "dur": 28.892, + "args": { + "External id": 3722854,"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": 1625852267638.935, "dur": 2.058, + "args": { + "External id": 3722855,"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": 1625852267642.752, "dur": 0.348, + "args": { + "External id": 3722856,"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": 1625852267644.893, "dur": 0.454, + "args": { + "External id": 3722857,"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": 1625852267647.498, "dur": 0.479, + "args": { + "External id": 3722858,"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": 1625852267649.952, "dur": 0.507, + "args": { + "External id": 3722859,"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": 1625852267651.997, "dur": 0.415, + "args": { + "External id": 3722860,"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": 1625852267653.944, "dur": 0.421, + "args": { + "External id": 3722861,"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": 1625852267656.208, "dur": 0.410, + "args": { + "External id": 3722862,"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": 1625852267658.991, "dur": 2.266, + "args": { + "External id": 3722863,"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": 1625852267693.219, "dur": 23.849, + "args": { + "External id": 3722864,"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": 1625852267773.181, "dur": 112.253, + "args": { + "External id": 3722865,"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": 1625852267796.049, "dur": 86.049, + "args": { + "External id": 3722866,"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": 1625852267806.154, "dur": 71.668, + "args": { + "External id": 3722867,"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": 1625852267900.031, "dur": 1.948, + "args": { + "External id": 3722868,"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": 1625852267979.060, "dur": 1695.127, + "args": { + "External id": 3722869,"Sequence number": 37295114, "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": 1625852267979.060, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1625852268128.443, "dur": 107.006, + "args": { + "External id": 3722870,"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": 1625852268274.805, "dur": 41.330, + "args": { + "External id": 3722871,"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": 1625852268336.891, "dur": 50.355, + "args": { + "External id": 3722872,"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": 1625852268397.454, "dur": 34.422, + "args": { + "External id": 3722873,"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": 1625852268439.601, "dur": 46.357, + "args": { + "External id": 3722874,"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": 1625852268494.061, "dur": 30.120, + "args": { + "External id": 3722875,"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": 1625852268534.098, "dur": 43.302, + "args": { + "External id": 3722876,"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": 1625852268599.131, "dur": 22.498, + "args": { + "External id": 3722877,"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": 1625852268641.874, "dur": 29.396, + "args": { + "External id": 3722878,"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": 1625852268709.530, "dur": 26.287, + "args": { + "External id": 3722879,"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": 1625852268749.936, "dur": 16.686, + "args": { + "External id": 3722880,"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": 1625852268782.085, "dur": 34.138, + "args": { + "External id": 3722881,"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": 1625852268820.005, "dur": 35.199, + "args": { + "External id": 3722882,"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": 1625852268886.284, "dur": 221.213, + "args": { + "External id": 3722883,"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": 1625852268970.033, "dur": 6.493, + "args": { + "External id": 3722884,"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": 1625852268978.896, "dur": 40.119, + "args": { + "External id": 3722885,"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": 1625852269145.092, "dur": 26.526, + "args": { + "External id": 3722886,"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": 1625852269183.530, "dur": 15.022, + "args": { + "External id": 3722887,"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": 1625852269208.037, "dur": 42.154, + "args": { + "External id": 3722888,"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": 1625852269259.664, "dur": 35.663, + "args": { + "External id": 3722889,"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": 1625852269302.848, "dur": 22.985, + "args": { + "External id": 3722890,"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": 1625852269331.766, "dur": 31.315, + "args": { + "External id": 3722891,"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": 1625852269370.326, "dur": 22.685, + "args": { + "External id": 3722892,"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": 1625852269415.623, "dur": 44.137, + "args": { + "External id": 3722893,"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": 1625852269478.945, "dur": 26.053, + "args": { + "External id": 3722894,"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": 1625852269524.600, "dur": 24.951, + "args": { + "External id": 3722895,"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": 1625852269564.114, "dur": 21.541, + "args": { + "External id": 3722896,"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": 1625852269600.045, "dur": 14.839, + "args": { + "External id": 3722897,"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": 1625852269627.731, "dur": 16.792, + "args": { + "External id": 3722898,"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": 1625852269738.100, "dur": 17.982, + "args": { + "External id": 3722899,"Record function id": 0, "Ev Idx": 2706 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852269741.568, "dur": 13.582, + "args": { + "External id": 3722900,"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": 1625852269746.170, "dur": 8.060, + "args": { + "External id": 3722901,"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": 1625852269748.020, "dur": 6.087, + "args": { + "External id": 3722902,"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": 1625852269760.341, "dur": 4.944, + "args": { + "External id": 3722903,"Record function id": 0, "Ev Idx": 2710 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852269761.629, "dur": 3.213, + "args": { + "External id": 3722904,"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": 1625852269762.242, "dur": 2.096, + "args": { + "External id": 3722905,"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": 1625852269763.201, "dur": 1.018, + "args": { + "External id": 3722906,"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": 1625852269768.892, "dur": 4.264, + "args": { + "External id": 3722907,"Record function id": 0, "Ev Idx": 2714 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852269770.018, "dur": 2.716, + "args": { + "External id": 3722908,"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": 1625852269770.777, "dur": 1.548, + "args": { + "External id": 3722909,"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": 1625852269771.278, "dur": 0.972, + "args": { + "External id": 3722910,"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": 1625852269776.372, "dur": 4.545, + "args": { + "External id": 3722911,"Record function id": 0, "Ev Idx": 2718 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852269778.085, "dur": 2.421, + "args": { + "External id": 3722912,"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": 1625852269778.589, "dur": 1.552, + "args": { + "External id": 3722913,"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": 1625852269779.223, "dur": 0.842, + "args": { + "External id": 3722914,"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": 1625852269784.404, "dur": 3.873, + "args": { + "External id": 3722915,"Record function id": 0, "Ev Idx": 2722 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852269785.450, "dur": 2.381, + "args": { + "External id": 3722916,"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": 1625852269786.129, "dur": 1.304, + "args": { + "External id": 3722917,"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": 1625852269786.438, "dur": 0.932, + "args": { + "External id": 3722918,"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": 1625852269791.495, "dur": 3.910, + "args": { + "External id": 3722919,"Record function id": 0, "Ev Idx": 2726 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852269792.873, "dur": 2.117, + "args": { + "External id": 3722920,"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": 1625852269793.317, "dur": 1.190, + "args": { + "External id": 3722921,"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": 1625852269793.758, "dur": 0.647, + "args": { + "External id": 3722922,"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": 1625852269798.657, "dur": 3.580, + "args": { + "External id": 3722923,"Record function id": 0, "Ev Idx": 2730 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852269799.875, "dur": 1.939, + "args": { + "External id": 3722924,"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": 1625852269800.370, "dur": 1.038, + "args": { + "External id": 3722925,"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": 1625852269800.690, "dur": 0.635, + "args": { + "External id": 3722926,"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": 1625852269805.423, "dur": 5.715, + "args": { + "External id": 3722927,"Record function id": 0, "Ev Idx": 2734 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852269806.576, "dur": 4.134, + "args": { + "External id": 3722928,"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": 1625852269807.031, "dur": 3.269, + "args": { + "External id": 3722929,"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": 1625852269807.530, "dur": 2.681, + "args": { + "External id": 3722930,"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": 1625852269814.621, "dur": 4.078, + "args": { + "External id": 3722931,"Record function id": 0, "Ev Idx": 2738 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852269815.657, "dur": 2.639, + "args": { + "External id": 3722932,"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": 1625852269816.381, "dur": 1.490, + "args": { + "External id": 3722933,"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": 1625852269816.843, "dur": 0.940, + "args": { + "External id": 3722934,"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": 1625852269822.831, "dur": 36734.520, + "args": { + "External id": 3722935,"Record function id": 0, "Sequence number": 37295113, "Fwd thread id": 1, "Ev Idx": 2742 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1625852269824.336, "dur": 36724.859, + "args": { + "External id": 3722936,"Sequence number": 37295113, "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": 1625852269824.336, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.20)", "pid": 1336756, "tid": 1381189, + "ts": 1625852269854.181, "dur": 35.911, + "args": { + "External id": 3722937,"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": 1625852269897.889, "dur": 61.232, + "args": { + "External id": 3722938,"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": 1625852269965.250, "dur": 36576.117, + "args": { + "External id": 3722939,"Record function id": 0, "Ev Idx": 2746 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1625852270090.800, "dur": 7.588, + "args": { + "External id": 3722940,"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": 1625852270109.347, "dur": 5.087, + "args": { + "External id": 3722941,"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": 1625852270130.346, "dur": 35517.822, + "args": { + "External id": 3722942,"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": 1625852270144.617, "dur": 35494.896, + "args": { + "External id": 3722943,"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": 1625852270223.031, "dur": 13.730, + "args": { + "External id": 3722944,"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": 1625852270243.143, "dur": 35355.514, + "args": { + "External id": 3722945,"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": 1625852270245.998, "dur": 35352.026, + "args": { + "External id": 3722946,"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": 1625852270250.618, "dur": 5.904, + "args": { + "External id": 3722947,"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": 1625852270258.427, "dur": 35335.408, + "args": { + "External id": 3722948,"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": 1625852305752.388, "dur": 8.962, + "args": { + "External id": 3722949,"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": 1625852305755.707, "dur": 5.197, + "args": { + "External id": 3722950,"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": 1625852305797.705, "dur": 432.542, + "args": { + "External id": 3722951,"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": 1625852305827.772, "dur": 397.225, + "args": { + "External id": 3722952,"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": 1625852305839.319, "dur": 379.669, + "args": { + "External id": 3722953,"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": 1625852306252.797, "dur": 2.264, + "args": { + "External id": 3722954,"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": 1625852306318.140, "dur": 6.672, + "args": { + "External id": 3722955,"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": 1625852306374.469, "dur": 1.348, + "args": { + "External id": 3722956,"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": 1625852306393.939, "dur": 0.936, + "args": { + "External id": 3722957,"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": 1625852306408.388, "dur": 0.867, + "args": { + "External id": 3722958,"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": 1625852306422.282, "dur": 1.126, + "args": { + "External id": 3722959,"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": 1625852306436.756, "dur": 1.178, + "args": { + "External id": 3722960,"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": 1625852306450.600, "dur": 1.202, + "args": { + "External id": 3722961,"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": 1625852306464.419, "dur": 2.223, + "args": { + "External id": 3722962,"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": 1625852306479.117, "dur": 0.809, + "args": { + "External id": 3722963,"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": 1625852306571.370, "dur": 2791.607, + "args": { + "External id": 3722964,"Record function id": 0, "Ev Idx": 2771 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.19)", "pid": 1336756, "tid": 1381189, + "ts": 1625852306589.913, "dur": 1025.080, + "args": { + "External id": 3722965,"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": 1625852306605.339, "dur": 338.255, + "args": { + "External id": 3722966,"Record function id": 0, "Ev Idx": 2773 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1625852306702.881, "dur": 4.833, + "args": { + "External id": 3722967,"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": 1625852306710.880, "dur": 1.093, + "args": { + "External id": 3722968,"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": 1625852306714.103, "dur": 1.080, + "args": { + "External id": 3722969,"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": 1625852306716.958, "dur": 1.089, + "args": { + "External id": 3722970,"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": 1625852306719.960, "dur": 0.881, + "args": { + "External id": 3722971,"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": 1625852306728.214, "dur": 0.936, + "args": { + "External id": 3722972,"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": 1625852306730.995, "dur": 1.795, + "args": { + "External id": 3722973,"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": 1625852306734.442, "dur": 2.904, + "args": { + "External id": 3722974,"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": 1625852306739.084, "dur": 0.740, + "args": { + "External id": 3722975,"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": 1625852306741.408, "dur": 1.211, + "args": { + "External id": 3722976,"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": 1625852306761.998, "dur": 148.548, + "args": { + "External id": 3722977,"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": 1625852306778.672, "dur": 127.032, + "args": { + "External id": 3722978,"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": 1625852306795.849, "dur": 12.269, + "args": { + "External id": 3722979,"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": 1625852306811.273, "dur": 67.006, + "args": { + "External id": 3722980,"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": 1625852306814.079, "dur": 63.930, + "args": { + "External id": 3722981,"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": 1625852306818.231, "dur": 5.661, + "args": { + "External id": 3722982,"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": 1625852306826.238, "dur": 51.282, + "args": { + "External id": 3722983,"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": 1625852307065.605, "dur": 540.615, + "args": { + "External id": 3722984,"Record function id": 0, "Ev Idx": 2791 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.18)", "pid": 1336756, "tid": 1381189, + "ts": 1625852307084.228, "dur": 509.078, + "args": { + "External id": 3722985,"Record function id": 0, "Ev Idx": 2792 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1625852307142.165, "dur": 5.583, + "args": { + "External id": 3722986,"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": 1625852307163.594, "dur": 32.629, + "args": { + "External id": 3722987,"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": 1625852307169.043, "dur": 1.614, + "args": { + "External id": 3722988,"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": 1625852307173.297, "dur": 0.484, + "args": { + "External id": 3722989,"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": 1625852307175.452, "dur": 2.424, + "args": { + "External id": 3722990,"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": 1625852307179.850, "dur": 0.373, + "args": { + "External id": 3722991,"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": 1625852307181.821, "dur": 0.509, + "args": { + "External id": 3722992,"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": 1625852307184.305, "dur": 0.438, + "args": { + "External id": 3722993,"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": 1625852307186.571, "dur": 0.400, + "args": { + "External id": 3722994,"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": 1625852307188.796, "dur": 0.390, + "args": { + "External id": 3722995,"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": 1625852307191.100, "dur": 0.471, + "args": { + "External id": 3722996,"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": 1625852307205.341, "dur": 32.105, + "args": { + "External id": 3722997,"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": 1625852307269.029, "dur": 103.706, + "args": { + "External id": 3722998,"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": 1625852307279.604, "dur": 3.477, + "args": { + "External id": 3722999,"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": 1625852307288.699, "dur": 12.303, + "args": { + "External id": 3723000,"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": 1625852307292.911, "dur": 7.621, + "args": { + "External id": 3723001,"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": 1625852307296.554, "dur": 2.497, + "args": { + "External id": 3723002,"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": 1625852307308.362, "dur": 27.095, + "args": { + "External id": 3723003,"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": 1625852307311.199, "dur": 0.723, + "args": { + "External id": 3723004,"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": 1625852307314.035, "dur": 0.394, + "args": { + "External id": 3723005,"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": 1625852307316.320, "dur": 0.449, + "args": { + "External id": 3723006,"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": 1625852307318.485, "dur": 0.384, + "args": { + "External id": 3723007,"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": 1625852307320.780, "dur": 0.372, + "args": { + "External id": 3723008,"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": 1625852307322.793, "dur": 0.394, + "args": { + "External id": 3723009,"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": 1625852307324.851, "dur": 0.442, + "args": { + "External id": 3723010,"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": 1625852307327.340, "dur": 2.276, + "args": { + "External id": 3723011,"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": 1625852307331.143, "dur": 0.380, + "args": { + "External id": 3723012,"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": 1625852307344.509, "dur": 20.800, + "args": { + "External id": 3723013,"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": 1625852307418.445, "dur": 110.238, + "args": { + "External id": 3723014,"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": 1625852307440.072, "dur": 85.460, + "args": { + "External id": 3723015,"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": 1625852307449.970, "dur": 70.931, + "args": { + "External id": 3723016,"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": 1625852307543.238, "dur": 1.956, + "args": { + "External id": 3723017,"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": 1625852307622.094, "dur": 1716.080, + "args": { + "External id": 3723018,"Sequence number": 37295112, "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": 1625852307622.094, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1625852307750.553, "dur": 106.394, + "args": { + "External id": 3723019,"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": 1625852307894.729, "dur": 40.212, + "args": { + "External id": 3723020,"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": 1625852307954.897, "dur": 92.431, + "args": { + "External id": 3723021,"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": 1625852308061.821, "dur": 39.104, + "args": { + "External id": 3723022,"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": 1625852308108.502, "dur": 45.297, + "args": { + "External id": 3723023,"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": 1625852308161.498, "dur": 29.592, + "args": { + "External id": 3723024,"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": 1625852308201.746, "dur": 42.488, + "args": { + "External id": 3723025,"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": 1625852308269.752, "dur": 25.366, + "args": { + "External id": 3723026,"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": 1625852308314.494, "dur": 29.436, + "args": { + "External id": 3723027,"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": 1625852308363.412, "dur": 21.446, + "args": { + "External id": 3723028,"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": 1625852308397.876, "dur": 16.664, + "args": { + "External id": 3723029,"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": 1625852308426.518, "dur": 31.087, + "args": { + "External id": 3723030,"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": 1625852308461.276, "dur": 34.292, + "args": { + "External id": 3723031,"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": 1625852308522.349, "dur": 193.072, + "args": { + "External id": 3723032,"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": 1625852308602.933, "dur": 5.935, + "args": { + "External id": 3723033,"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": 1625852308611.400, "dur": 2.207, + "args": { + "External id": 3723034,"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": 1625852308750.302, "dur": 27.147, + "args": { + "External id": 3723035,"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": 1625852308789.148, "dur": 16.063, + "args": { + "External id": 3723036,"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": 1625852308816.768, "dur": 41.080, + "args": { + "External id": 3723037,"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": 1625852308864.544, "dur": 36.492, + "args": { + "External id": 3723038,"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": 1625852308908.253, "dur": 22.241, + "args": { + "External id": 3723039,"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": 1625852308935.879, "dur": 30.224, + "args": { + "External id": 3723040,"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": 1625852308974.458, "dur": 73.952, + "args": { + "External id": 3723041,"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": 1625852309070.005, "dur": 46.602, + "args": { + "External id": 3723042,"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": 1625852309139.932, "dur": 27.051, + "args": { + "External id": 3723043,"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": 1625852309188.568, "dur": 24.311, + "args": { + "External id": 3723044,"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": 1625852309226.439, "dur": 21.787, + "args": { + "External id": 3723045,"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": 1625852309264.075, "dur": 15.198, + "args": { + "External id": 3723046,"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": 1625852309291.593, "dur": 16.269, + "args": { + "External id": 3723047,"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": 1625852309385.461, "dur": 15.932, + "args": { + "External id": 3723048,"Record function id": 0, "Ev Idx": 2855 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852309389.142, "dur": 11.118, + "args": { + "External id": 3723049,"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": 1625852309393.290, "dur": 6.227, + "args": { + "External id": 3723050,"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": 1625852309395.217, "dur": 4.180, + "args": { + "External id": 3723051,"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": 1625852309405.245, "dur": 8.692, + "args": { + "External id": 3723052,"Record function id": 0, "Ev Idx": 2859 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852309406.675, "dur": 6.795, + "args": { + "External id": 3723053,"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": 1625852309407.413, "dur": 5.524, + "args": { + "External id": 3723054,"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": 1625852309411.536, "dur": 1.278, + "args": { + "External id": 3723055,"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": 1625852309417.180, "dur": 4.508, + "args": { + "External id": 3723056,"Record function id": 0, "Ev Idx": 2863 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852309418.379, "dur": 2.916, + "args": { + "External id": 3723057,"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": 1625852309419.112, "dur": 1.753, + "args": { + "External id": 3723058,"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": 1625852309419.828, "dur": 0.944, + "args": { + "External id": 3723059,"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": 1625852309424.961, "dur": 4.638, + "args": { + "External id": 3723060,"Record function id": 0, "Ev Idx": 2867 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852309426.236, "dur": 2.954, + "args": { + "External id": 3723061,"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": 1625852309427.079, "dur": 1.676, + "args": { + "External id": 3723062,"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": 1625852309428.081, "dur": 0.600, + "args": { + "External id": 3723063,"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": 1625852309432.761, "dur": 3.981, + "args": { + "External id": 3723064,"Record function id": 0, "Ev Idx": 2871 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852309434.281, "dur": 2.055, + "args": { + "External id": 3723065,"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": 1625852309434.724, "dur": 1.125, + "args": { + "External id": 3723066,"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": 1625852309435.037, "dur": 0.746, + "args": { + "External id": 3723067,"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": 1625852309439.844, "dur": 3.859, + "args": { + "External id": 3723068,"Record function id": 0, "Ev Idx": 2875 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852309441.196, "dur": 2.095, + "args": { + "External id": 3723069,"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": 1625852309441.636, "dur": 1.247, + "args": { + "External id": 3723070,"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": 1625852309442.131, "dur": 0.639, + "args": { + "External id": 3723071,"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": 1625852309447.204, "dur": 5.566, + "args": { + "External id": 3723072,"Record function id": 0, "Ev Idx": 2879 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852309448.466, "dur": 3.856, + "args": { + "External id": 3723073,"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": 1625852309448.961, "dur": 2.920, + "args": { + "External id": 3723074,"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": 1625852309449.235, "dur": 2.577, + "args": { + "External id": 3723075,"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": 1625852309456.015, "dur": 3.712, + "args": { + "External id": 3723076,"Record function id": 0, "Ev Idx": 2883 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852309457.155, "dur": 2.144, + "args": { + "External id": 3723077,"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": 1625852309457.609, "dur": 1.259, + "args": { + "External id": 3723078,"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": 1625852309457.885, "dur": 0.902, + "args": { + "External id": 3723079,"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": 1625852309462.761, "dur": 6.795, + "args": { + "External id": 3723080,"Record function id": 0, "Ev Idx": 2887 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852309463.962, "dur": 5.201, + "args": { + "External id": 3723081,"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": 1625852309464.408, "dur": 1.300, + "args": { + "External id": 3723082,"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": 1625852309464.933, "dur": 0.688, + "args": { + "External id": 3723083,"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": 1625852309473.277, "dur": 36612.031, + "args": { + "External id": 3723084,"Record function id": 0, "Sequence number": 37295111, "Fwd thread id": 1, "Ev Idx": 2891 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1625852309474.721, "dur": 36601.348, + "args": { + "External id": 3723085,"Sequence number": 37295111, "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": 1625852309474.721, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.19)", "pid": 1336756, "tid": 1381189, + "ts": 1625852309503.890, "dur": 41.326, + "args": { + "External id": 3723086,"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": 1625852309552.940, "dur": 63.760, + "args": { + "External id": 3723087,"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": 1625852309622.478, "dur": 36444.451, + "args": { + "External id": 3723088,"Record function id": 0, "Ev Idx": 2895 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1625852309726.119, "dur": 7.729, + "args": { + "External id": 3723089,"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": 1625852309744.792, "dur": 5.167, + "args": { + "External id": 3723090,"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": 1625852309765.645, "dur": 35455.695, + "args": { + "External id": 3723091,"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": 1625852309779.678, "dur": 35431.845, + "args": { + "External id": 3723092,"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": 1625852309851.356, "dur": 13.825, + "args": { + "External id": 3723093,"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": 1625852309871.626, "dur": 35295.734, + "args": { + "External id": 3723094,"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": 1625852309874.561, "dur": 35292.084, + "args": { + "External id": 3723095,"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": 1625852309879.012, "dur": 5.273, + "args": { + "External id": 3723096,"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": 1625852309886.367, "dur": 35276.921, + "args": { + "External id": 3723097,"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": 1625852345319.347, "dur": 9.957, + "args": { + "External id": 3723098,"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": 1625852345323.329, "dur": 5.558, + "args": { + "External id": 3723099,"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": 1625852345364.756, "dur": 361.210, + "args": { + "External id": 3723100,"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": 1625852345392.149, "dur": 328.399, + "args": { + "External id": 3723101,"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": 1625852345403.014, "dur": 311.424, + "args": { + "External id": 3723102,"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": 1625852345746.792, "dur": 2.270, + "args": { + "External id": 3723103,"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": 1625852345806.996, "dur": 8.677, + "args": { + "External id": 3723104,"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": 1625852345863.267, "dur": 1.352, + "args": { + "External id": 3723105,"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": 1625852345882.405, "dur": 1.106, + "args": { + "External id": 3723106,"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": 1625852345896.190, "dur": 1.186, + "args": { + "External id": 3723107,"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": 1625852345910.292, "dur": 2.919, + "args": { + "External id": 3723108,"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": 1625852345925.193, "dur": 0.962, + "args": { + "External id": 3723109,"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": 1625852345938.740, "dur": 1.319, + "args": { + "External id": 3723110,"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": 1625852345952.806, "dur": 2.235, + "args": { + "External id": 3723111,"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": 1625852345966.775, "dur": 2.912, + "args": { + "External id": 3723112,"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": 1625852346102.831, "dur": 2757.988, + "args": { + "External id": 3723113,"Record function id": 0, "Ev Idx": 2920 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.18)", "pid": 1336756, "tid": 1381189, + "ts": 1625852346122.385, "dur": 1055.971, + "args": { + "External id": 3723114,"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": 1625852346138.552, "dur": 319.774, + "args": { + "External id": 3723115,"Record function id": 0, "Ev Idx": 2922 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1625852346216.793, "dur": 4.761, + "args": { + "External id": 3723116,"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": 1625852346225.006, "dur": 1.307, + "args": { + "External id": 3723117,"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": 1625852346228.401, "dur": 1.139, + "args": { + "External id": 3723118,"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": 1625852346231.373, "dur": 0.931, + "args": { + "External id": 3723119,"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": 1625852346234.127, "dur": 0.914, + "args": { + "External id": 3723120,"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": 1625852346236.784, "dur": 0.995, + "args": { + "External id": 3723121,"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": 1625852346239.425, "dur": 3.866, + "args": { + "External id": 3723122,"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": 1625852346244.538, "dur": 0.893, + "args": { + "External id": 3723123,"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": 1625852346246.772, "dur": 0.783, + "args": { + "External id": 3723124,"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": 1625852346248.949, "dur": 0.918, + "args": { + "External id": 3723125,"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": 1625852346268.011, "dur": 157.288, + "args": { + "External id": 3723126,"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": 1625852346284.831, "dur": 136.522, + "args": { + "External id": 3723127,"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": 1625852346310.737, "dur": 11.935, + "args": { + "External id": 3723128,"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": 1625852346326.300, "dur": 65.994, + "args": { + "External id": 3723129,"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": 1625852346329.322, "dur": 62.612, + "args": { + "External id": 3723130,"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": 1625852346333.841, "dur": 5.097, + "args": { + "External id": 3723131,"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": 1625852346340.827, "dur": 50.599, + "args": { + "External id": 3723132,"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": 1625852346539.469, "dur": 630.158, + "args": { + "External id": 3723133,"Record function id": 0, "Ev Idx": 2940 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.17)", "pid": 1336756, "tid": 1381189, + "ts": 1625852346556.765, "dur": 599.326, + "args": { + "External id": 3723134,"Record function id": 0, "Ev Idx": 2941 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1625852346612.646, "dur": 4.318, + "args": { + "External id": 3723135,"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": 1625852346631.831, "dur": 38.304, + "args": { + "External id": 3723136,"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": 1625852346636.928, "dur": 1.291, + "args": { + "External id": 3723137,"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": 1625852346640.516, "dur": 2.995, + "args": { + "External id": 3723138,"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": 1625852346645.595, "dur": 0.478, + "args": { + "External id": 3723139,"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": 1625852346648.003, "dur": 0.428, + "args": { + "External id": 3723140,"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": 1625852346650.494, "dur": 0.735, + "args": { + "External id": 3723141,"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": 1625852346652.831, "dur": 0.353, + "args": { + "External id": 3723142,"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": 1625852346659.851, "dur": 0.398, + "args": { + "External id": 3723143,"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": 1625852346662.369, "dur": 0.701, + "args": { + "External id": 3723144,"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": 1625852346665.289, "dur": 0.399, + "args": { + "External id": 3723145,"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": 1625852346696.576, "dur": 38.095, + "args": { + "External id": 3723146,"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": 1625852346772.974, "dur": 107.448, + "args": { + "External id": 3723147,"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": 1625852346783.577, "dur": 5.298, + "args": { + "External id": 3723148,"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": 1625852346794.370, "dur": 11.064, + "args": { + "External id": 3723149,"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": 1625852346798.643, "dur": 6.367, + "args": { + "External id": 3723150,"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": 1625852346802.751, "dur": 0.679, + "args": { + "External id": 3723151,"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": 1625852346813.249, "dur": 26.099, + "args": { + "External id": 3723152,"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": 1625852346815.520, "dur": 0.597, + "args": { + "External id": 3723153,"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": 1625852346817.711, "dur": 0.481, + "args": { + "External id": 3723154,"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": 1625852346820.128, "dur": 0.381, + "args": { + "External id": 3723155,"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": 1625852346822.343, "dur": 0.543, + "args": { + "External id": 3723156,"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": 1625852346824.834, "dur": 0.456, + "args": { + "External id": 3723157,"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": 1625852346826.843, "dur": 0.456, + "args": { + "External id": 3723158,"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": 1625852346829.147, "dur": 1.920, + "args": { + "External id": 3723159,"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": 1625852346832.586, "dur": 0.301, + "args": { + "External id": 3723160,"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": 1625852346834.785, "dur": 0.330, + "args": { + "External id": 3723161,"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": 1625852346853.861, "dur": 18.959, + "args": { + "External id": 3723162,"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": 1625852346926.884, "dur": 155.757, + "args": { + "External id": 3723163,"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": 1625852346952.090, "dur": 126.518, + "args": { + "External id": 3723164,"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": 1625852346962.020, "dur": 111.570, + "args": { + "External id": 3723165,"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": 1625852347101.574, "dur": 1.875, + "args": { + "External id": 3723166,"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": 1625852347185.224, "dur": 1657.009, + "args": { + "External id": 3723167,"Sequence number": 37295110, "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": 1625852347185.224, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1625852347296.682, "dur": 104.795, + "args": { + "External id": 3723168,"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": 1625852347438.442, "dur": 40.975, + "args": { + "External id": 3723169,"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": 1625852347498.567, "dur": 51.382, + "args": { + "External id": 3723170,"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": 1625852347560.265, "dur": 35.109, + "args": { + "External id": 3723171,"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": 1625852347602.470, "dur": 46.668, + "args": { + "External id": 3723172,"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": 1625852347659.544, "dur": 48.322, + "args": { + "External id": 3723173,"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": 1625852347718.962, "dur": 45.726, + "args": { + "External id": 3723174,"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": 1625852347789.862, "dur": 25.475, + "args": { + "External id": 3723175,"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": 1625852347833.499, "dur": 27.707, + "args": { + "External id": 3723176,"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": 1625852347881.051, "dur": 20.260, + "args": { + "External id": 3723177,"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": 1625852347913.259, "dur": 16.170, + "args": { + "External id": 3723178,"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": 1625852347941.738, "dur": 30.338, + "args": { + "External id": 3723179,"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": 1625852347975.028, "dur": 85.714, + "args": { + "External id": 3723180,"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": 1625852348092.821, "dur": 175.520, + "args": { + "External id": 3723181,"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": 1625852348172.402, "dur": 5.972, + "args": { + "External id": 3723182,"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": 1625852348180.983, "dur": 4.069, + "args": { + "External id": 3723183,"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": 1625852348302.331, "dur": 25.422, + "args": { + "External id": 3723184,"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": 1625852348339.429, "dur": 15.104, + "args": { + "External id": 3723185,"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": 1625852348363.507, "dur": 40.035, + "args": { + "External id": 3723186,"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": 1625852348410.930, "dur": 35.454, + "args": { + "External id": 3723187,"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": 1625852348453.717, "dur": 38.091, + "args": { + "External id": 3723188,"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": 1625852348504.611, "dur": 37.752, + "args": { + "External id": 3723189,"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": 1625852348549.928, "dur": 21.892, + "args": { + "External id": 3723190,"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": 1625852348579.258, "dur": 33.216, + "args": { + "External id": 3723191,"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": 1625852348629.780, "dur": 28.314, + "args": { + "External id": 3723192,"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": 1625852348674.710, "dur": 41.925, + "args": { + "External id": 3723193,"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": 1625852348733.452, "dur": 18.901, + "args": { + "External id": 3723194,"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": 1625852348767.716, "dur": 15.023, + "args": { + "External id": 3723195,"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": 1625852348797.335, "dur": 16.716, + "args": { + "External id": 3723196,"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": 1625852348883.494, "dur": 15.363, + "args": { + "External id": 3723197,"Record function id": 0, "Ev Idx": 3004 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852348886.683, "dur": 11.298, + "args": { + "External id": 3723198,"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": 1625852348891.318, "dur": 5.819, + "args": { + "External id": 3723199,"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": 1625852348893.207, "dur": 3.807, + "args": { + "External id": 3723200,"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": 1625852348903.182, "dur": 5.358, + "args": { + "External id": 3723201,"Record function id": 0, "Ev Idx": 3008 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852348904.610, "dur": 3.471, + "args": { + "External id": 3723202,"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": 1625852348905.506, "dur": 2.096, + "args": { + "External id": 3723203,"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": 1625852348906.318, "dur": 1.164, + "args": { + "External id": 3723204,"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": 1625852348911.753, "dur": 4.889, + "args": { + "External id": 3723205,"Record function id": 0, "Ev Idx": 3012 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852348913.174, "dur": 3.075, + "args": { + "External id": 3723206,"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": 1625852348914.095, "dur": 1.713, + "args": { + "External id": 3723207,"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": 1625852348914.683, "dur": 1.039, + "args": { + "External id": 3723208,"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": 1625852348923.389, "dur": 6.427, + "args": { + "External id": 3723209,"Record function id": 0, "Ev Idx": 3016 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852348924.712, "dur": 4.684, + "args": { + "External id": 3723210,"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": 1625852348925.379, "dur": 3.601, + "args": { + "External id": 3723211,"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": 1625852348925.865, "dur": 3.038, + "args": { + "External id": 3723212,"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": 1625852348933.019, "dur": 4.263, + "args": { + "External id": 3723213,"Record function id": 0, "Ev Idx": 3020 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852348934.216, "dur": 2.664, + "args": { + "External id": 3723214,"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": 1625852348934.909, "dur": 1.544, + "args": { + "External id": 3723215,"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": 1625852348935.434, "dur": 0.957, + "args": { + "External id": 3723216,"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": 1625852348940.447, "dur": 3.720, + "args": { + "External id": 3723217,"Record function id": 0, "Ev Idx": 3024 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852348941.593, "dur": 2.155, + "args": { + "External id": 3723218,"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": 1625852348942.061, "dur": 1.285, + "args": { + "External id": 3723219,"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": 1625852348942.633, "dur": 0.592, + "args": { + "External id": 3723220,"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": 1625852348947.256, "dur": 3.483, + "args": { + "External id": 3723221,"Record function id": 0, "Ev Idx": 3028 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852348948.378, "dur": 1.974, + "args": { + "External id": 3723222,"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": 1625852348948.823, "dur": 1.113, + "args": { + "External id": 3723223,"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": 1625852348949.096, "dur": 0.771, + "args": { + "External id": 3723224,"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": 1625852348953.767, "dur": 3.907, + "args": { + "External id": 3723225,"Record function id": 0, "Ev Idx": 3032 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852348954.914, "dur": 2.360, + "args": { + "External id": 3723226,"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": 1625852348955.690, "dur": 1.148, + "args": { + "External id": 3723227,"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": 1625852348956.124, "dur": 0.650, + "args": { + "External id": 3723228,"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": 1625852348960.705, "dur": 3.482, + "args": { + "External id": 3723229,"Record function id": 0, "Ev Idx": 3036 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852348961.878, "dur": 1.920, + "args": { + "External id": 3723230,"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": 1625852348962.321, "dur": 1.066, + "args": { + "External id": 3723231,"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": 1625852348962.767, "dur": 0.530, + "args": { + "External id": 3723232,"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": 1625852348967.671, "dur": 36877.974, + "args": { + "External id": 3723233,"Record function id": 0, "Sequence number": 37295109, "Fwd thread id": 1, "Ev Idx": 3040 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1625852348969.153, "dur": 36868.093, + "args": { + "External id": 3723234,"Sequence number": 37295109, "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": 1625852348969.153, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.18)", "pid": 1336756, "tid": 1381189, + "ts": 1625852349034.723, "dur": 41.306, + "args": { + "External id": 3723235,"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": 1625852349084.524, "dur": 67.978, + "args": { + "External id": 3723236,"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": 1625852349158.548, "dur": 36670.008, + "args": { + "External id": 3723237,"Record function id": 0, "Ev Idx": 3044 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1625852349252.693, "dur": 7.067, + "args": { + "External id": 3723238,"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": 1625852349270.112, "dur": 5.138, + "args": { + "External id": 3723239,"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": 1625852349290.577, "dur": 35795.364, + "args": { + "External id": 3723240,"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": 1625852349342.582, "dur": 35734.443, + "args": { + "External id": 3723241,"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": 1625852349387.144, "dur": 15.721, + "args": { + "External id": 3723242,"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": 1625852349409.431, "dur": 35625.122, + "args": { + "External id": 3723243,"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": 1625852349412.007, "dur": 35621.913, + "args": { + "External id": 3723244,"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": 1625852349416.693, "dur": 4.793, + "args": { + "External id": 3723245,"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": 1625852349423.577, "dur": 35606.559, + "args": { + "External id": 3723246,"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": 1625852385174.482, "dur": 8.933, + "args": { + "External id": 3723247,"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": 1625852385177.840, "dur": 5.186, + "args": { + "External id": 3723248,"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": 1625852385218.718, "dur": 290.738, + "args": { + "External id": 3723249,"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": 1625852385245.004, "dur": 259.828, + "args": { + "External id": 3723250,"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": 1625852385256.316, "dur": 242.415, + "args": { + "External id": 3723251,"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": 1625852385527.849, "dur": 2.116, + "args": { + "External id": 3723252,"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": 1625852385583.844, "dur": 6.351, + "args": { + "External id": 3723253,"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": 1625852385635.983, "dur": 1.380, + "args": { + "External id": 3723254,"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": 1625852385654.256, "dur": 0.907, + "args": { + "External id": 3723255,"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": 1625852385670.846, "dur": 0.845, + "args": { + "External id": 3723256,"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": 1625852385705.500, "dur": 1.748, + "args": { + "External id": 3723257,"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": 1625852385720.649, "dur": 1.066, + "args": { + "External id": 3723258,"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": 1625852385734.737, "dur": 1.435, + "args": { + "External id": 3723259,"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": 1625852385751.211, "dur": 1.693, + "args": { + "External id": 3723260,"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": 1625852385765.523, "dur": 0.861, + "args": { + "External id": 3723261,"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": 1625852385861.594, "dur": 2851.183, + "args": { + "External id": 3723262,"Record function id": 0, "Ev Idx": 3069 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.17)", "pid": 1336756, "tid": 1381189, + "ts": 1625852385879.733, "dur": 1075.490, + "args": { + "External id": 3723263,"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": 1625852385895.710, "dur": 393.978, + "args": { + "External id": 3723264,"Record function id": 0, "Ev Idx": 3071 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1625852386044.555, "dur": 5.302, + "args": { + "External id": 3723265,"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": 1625852386055.487, "dur": 1.170, + "args": { + "External id": 3723266,"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": 1625852386058.558, "dur": 1.006, + "args": { + "External id": 3723267,"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": 1625852386061.435, "dur": 2.784, + "args": { + "External id": 3723268,"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": 1625852386066.052, "dur": 0.872, + "args": { + "External id": 3723269,"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": 1625852386069.767, "dur": 0.905, + "args": { + "External id": 3723270,"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": 1625852386072.466, "dur": 1.671, + "args": { + "External id": 3723271,"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": 1625852386075.588, "dur": 1.003, + "args": { + "External id": 3723272,"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": 1625852386078.200, "dur": 0.695, + "args": { + "External id": 3723273,"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": 1625852386080.373, "dur": 0.895, + "args": { + "External id": 3723274,"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": 1625852386101.134, "dur": 153.713, + "args": { + "External id": 3723275,"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": 1625852386118.424, "dur": 131.728, + "args": { + "External id": 3723276,"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": 1625852386134.968, "dur": 12.115, + "args": { + "External id": 3723277,"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": 1625852386150.474, "dur": 70.511, + "args": { + "External id": 3723278,"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": 1625852386153.061, "dur": 67.575, + "args": { + "External id": 3723279,"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": 1625852386157.339, "dur": 7.472, + "args": { + "External id": 3723280,"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": 1625852386166.650, "dur": 53.410, + "args": { + "External id": 3723281,"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": 1625852386377.445, "dur": 568.815, + "args": { + "External id": 3723282,"Record function id": 0, "Ev Idx": 3089 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.16)", "pid": 1336756, "tid": 1381189, + "ts": 1625852386395.774, "dur": 537.562, + "args": { + "External id": 3723283,"Record function id": 0, "Ev Idx": 3090 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1625852386452.215, "dur": 4.707, + "args": { + "External id": 3723284,"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": 1625852386471.874, "dur": 32.797, + "args": { + "External id": 3723285,"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": 1625852386477.282, "dur": 1.439, + "args": { + "External id": 3723286,"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": 1625852386481.293, "dur": 0.634, + "args": { + "External id": 3723287,"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": 1625852386483.993, "dur": 0.379, + "args": { + "External id": 3723288,"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": 1625852386486.388, "dur": 0.366, + "args": { + "External id": 3723289,"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": 1625852386488.492, "dur": 0.700, + "args": { + "External id": 3723290,"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": 1625852386491.141, "dur": 0.433, + "args": { + "External id": 3723291,"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": 1625852386493.536, "dur": 2.481, + "args": { + "External id": 3723292,"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": 1625852386497.697, "dur": 0.425, + "args": { + "External id": 3723293,"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": 1625852386499.982, "dur": 0.384, + "args": { + "External id": 3723294,"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": 1625852386515.792, "dur": 29.573, + "args": { + "External id": 3723295,"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": 1625852386579.180, "dur": 127.216, + "args": { + "External id": 3723296,"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": 1625852386589.154, "dur": 3.296, + "args": { + "External id": 3723297,"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": 1625852386597.825, "dur": 10.906, + "args": { + "External id": 3723298,"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": 1625852386602.308, "dur": 5.993, + "args": { + "External id": 3723299,"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": 1625852386606.583, "dur": 0.596, + "args": { + "External id": 3723300,"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": 1625852386615.566, "dur": 29.026, + "args": { + "External id": 3723301,"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": 1625852386618.210, "dur": 0.593, + "args": { + "External id": 3723302,"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": 1625852386620.854, "dur": 0.371, + "args": { + "External id": 3723303,"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": 1625852386623.155, "dur": 0.601, + "args": { + "External id": 3723304,"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": 1625852386626.185, "dur": 2.433, + "args": { + "External id": 3723305,"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": 1625852386630.313, "dur": 0.430, + "args": { + "External id": 3723306,"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": 1625852386632.645, "dur": 0.468, + "args": { + "External id": 3723307,"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": 1625852386634.922, "dur": 0.563, + "args": { + "External id": 3723308,"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": 1625852386637.853, "dur": 0.447, + "args": { + "External id": 3723309,"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": 1625852386640.108, "dur": 0.625, + "args": { + "External id": 3723310,"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": 1625852386659.895, "dur": 37.147, + "args": { + "External id": 3723311,"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": 1625852386752.073, "dur": 114.761, + "args": { + "External id": 3723312,"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": 1625852386777.200, "dur": 85.997, + "args": { + "External id": 3723313,"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": 1625852386786.816, "dur": 71.986, + "args": { + "External id": 3723314,"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": 1625852386884.140, "dur": 2.039, + "args": { + "External id": 3723315,"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": 1625852386962.669, "dur": 1709.062, + "args": { + "External id": 3723316,"Sequence number": 37295108, "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": 1625852386962.669, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1625852387112.315, "dur": 106.991, + "args": { + "External id": 3723317,"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": 1625852387259.902, "dur": 43.359, + "args": { + "External id": 3723318,"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": 1625852387322.050, "dur": 51.453, + "args": { + "External id": 3723319,"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": 1625852387383.560, "dur": 33.931, + "args": { + "External id": 3723320,"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": 1625852387425.923, "dur": 46.927, + "args": { + "External id": 3723321,"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": 1625852387480.797, "dur": 30.127, + "args": { + "External id": 3723322,"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": 1625852387518.450, "dur": 44.469, + "args": { + "External id": 3723323,"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": 1625852387588.387, "dur": 22.125, + "args": { + "External id": 3723324,"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": 1625852387629.847, "dur": 31.692, + "args": { + "External id": 3723325,"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": 1625852387695.231, "dur": 23.648, + "args": { + "External id": 3723326,"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": 1625852387733.240, "dur": 16.599, + "args": { + "External id": 3723327,"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": 1625852387759.977, "dur": 34.557, + "args": { + "External id": 3723328,"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": 1625852387798.400, "dur": 34.209, + "args": { + "External id": 3723329,"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": 1625852387861.239, "dur": 211.052, + "args": { + "External id": 3723330,"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": 1625852387938.724, "dur": 5.554, + "args": { + "External id": 3723331,"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": 1625852387946.476, "dur": 2.374, + "args": { + "External id": 3723332,"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": 1625852388107.875, "dur": 31.310, + "args": { + "External id": 3723333,"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": 1625852388165.870, "dur": 16.370, + "args": { + "External id": 3723334,"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": 1625852388192.374, "dur": 47.087, + "args": { + "External id": 3723335,"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": 1625852388246.353, "dur": 40.821, + "args": { + "External id": 3723336,"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": 1625852388296.392, "dur": 38.660, + "args": { + "External id": 3723337,"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": 1625852388345.906, "dur": 41.357, + "args": { + "External id": 3723338,"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": 1625852388395.648, "dur": 22.656, + "args": { + "External id": 3723339,"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": 1625852388425.774, "dur": 33.990, + "args": { + "External id": 3723340,"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": 1625852388477.820, "dur": 28.748, + "args": { + "External id": 3723341,"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": 1625852388522.872, "dur": 23.625, + "args": { + "External id": 3723342,"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": 1625852388564.795, "dur": 17.891, + "args": { + "External id": 3723343,"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": 1625852388597.840, "dur": 15.787, + "args": { + "External id": 3723344,"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": 1625852388628.203, "dur": 16.008, + "args": { + "External id": 3723345,"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": 1625852388736.228, "dur": 15.731, + "args": { + "External id": 3723346,"Record function id": 0, "Ev Idx": 3153 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852388739.896, "dur": 11.160, + "args": { + "External id": 3723347,"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": 1625852388744.191, "dur": 5.974, + "args": { + "External id": 3723348,"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": 1625852388746.002, "dur": 4.030, + "args": { + "External id": 3723349,"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": 1625852388755.992, "dur": 5.272, + "args": { + "External id": 3723350,"Record function id": 0, "Ev Idx": 3157 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852388757.488, "dur": 3.332, + "args": { + "External id": 3723351,"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": 1625852388758.312, "dur": 2.040, + "args": { + "External id": 3723352,"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": 1625852388759.184, "dur": 1.053, + "args": { + "External id": 3723353,"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": 1625852388764.424, "dur": 7.241, + "args": { + "External id": 3723354,"Record function id": 0, "Ev Idx": 3161 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852388765.986, "dur": 5.266, + "args": { + "External id": 3723355,"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": 1625852388766.635, "dur": 4.193, + "args": { + "External id": 3723356,"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": 1625852388767.260, "dur": 3.468, + "args": { + "External id": 3723357,"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": 1625852388774.972, "dur": 4.154, + "args": { + "External id": 3723358,"Record function id": 0, "Ev Idx": 3165 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852388776.306, "dur": 2.420, + "args": { + "External id": 3723359,"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": 1625852388777.091, "dur": 1.225, + "args": { + "External id": 3723360,"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": 1625852388777.384, "dur": 0.867, + "args": { + "External id": 3723361,"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": 1625852388782.164, "dur": 3.756, + "args": { + "External id": 3723362,"Record function id": 0, "Ev Idx": 3169 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852388783.381, "dur": 2.125, + "args": { + "External id": 3723363,"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": 1625852388783.857, "dur": 1.195, + "args": { + "External id": 3723364,"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": 1625852388784.334, "dur": 0.657, + "args": { + "External id": 3723365,"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": 1625852388788.969, "dur": 4.314, + "args": { + "External id": 3723366,"Record function id": 0, "Ev Idx": 3173 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852388790.369, "dur": 2.475, + "args": { + "External id": 3723367,"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": 1625852388790.976, "dur": 1.472, + "args": { + "External id": 3723368,"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": 1625852388791.612, "dur": 0.725, + "args": { + "External id": 3723369,"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": 1625852388796.396, "dur": 3.481, + "args": { + "External id": 3723370,"Record function id": 0, "Ev Idx": 3177 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852388797.666, "dur": 1.807, + "args": { + "External id": 3723371,"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": 1625852388798.126, "dur": 0.938, + "args": { + "External id": 3723372,"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": 1625852388798.387, "dur": 0.568, + "args": { + "External id": 3723373,"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": 1625852388802.900, "dur": 3.949, + "args": { + "External id": 3723374,"Record function id": 0, "Ev Idx": 3181 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852388804.495, "dur": 1.932, + "args": { + "External id": 3723375,"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": 1625852388805.035, "dur": 0.984, + "args": { + "External id": 3723376,"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": 1625852388805.322, "dur": 0.629, + "args": { + "External id": 3723377,"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": 1625852388809.853, "dur": 3.543, + "args": { + "External id": 3723378,"Record function id": 0, "Ev Idx": 3185 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852388810.996, "dur": 1.989, + "args": { + "External id": 3723379,"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": 1625852388811.457, "dur": 1.126, + "args": { + "External id": 3723380,"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": 1625852388811.849, "dur": 0.642, + "args": { + "External id": 3723381,"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": 1625852388817.215, "dur": 38607.380, + "args": { + "External id": 3723382,"Record function id": 0, "Sequence number": 37295107, "Fwd thread id": 1, "Ev Idx": 3189 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1625852388818.959, "dur": 38597.270, + "args": { + "External id": 3723383,"Sequence number": 37295107, "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": 1625852388818.959, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.17)", "pid": 1336756, "tid": 1381189, + "ts": 1625852388851.106, "dur": 35.956, + "args": { + "External id": 3723384,"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": 1625852388894.490, "dur": 64.495, + "args": { + "External id": 3723385,"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": 1625852388964.737, "dur": 38444.148, + "args": { + "External id": 3723386,"Record function id": 0, "Ev Idx": 3193 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1625852389091.859, "dur": 7.077, + "args": { + "External id": 3723387,"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": 1625852389109.197, "dur": 6.856, + "args": { + "External id": 3723388,"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": 1625852389132.492, "dur": 37397.685, + "args": { + "External id": 3723389,"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": 1625852389146.124, "dur": 37375.024, + "args": { + "External id": 3723390,"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": 1625852389191.465, "dur": 17.496, + "args": { + "External id": 3723391,"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": 1625852389215.342, "dur": 37263.130, + "args": { + "External id": 3723392,"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": 1625852389218.060, "dur": 37259.510, + "args": { + "External id": 3723393,"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": 1625852389222.245, "dur": 5.133, + "args": { + "External id": 3723394,"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": 1625852389229.363, "dur": 37244.233, + "args": { + "External id": 3723395,"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": 1625852426616.627, "dur": 9.087, + "args": { + "External id": 3723396,"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": 1625852426619.970, "dur": 5.393, + "args": { + "External id": 3723397,"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": 1625852426656.901, "dur": 441.865, + "args": { + "External id": 3723398,"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": 1625852426694.461, "dur": 398.534, + "args": { + "External id": 3723399,"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": 1625852426706.827, "dur": 379.690, + "args": { + "External id": 3723400,"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": 1625852427121.743, "dur": 2.449, + "args": { + "External id": 3723401,"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": 1625852427188.917, "dur": 6.487, + "args": { + "External id": 3723402,"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": 1625852427242.141, "dur": 1.373, + "args": { + "External id": 3723403,"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": 1625852427260.716, "dur": 2.849, + "args": { + "External id": 3723404,"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": 1625852427277.226, "dur": 0.727, + "args": { + "External id": 3723405,"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": 1625852427290.512, "dur": 1.015, + "args": { + "External id": 3723406,"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": 1625852427304.112, "dur": 0.995, + "args": { + "External id": 3723407,"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": 1625852427317.638, "dur": 2.750, + "args": { + "External id": 3723408,"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": 1625852427332.675, "dur": 2.143, + "args": { + "External id": 3723409,"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": 1625852427345.622, "dur": 0.851, + "args": { + "External id": 3723410,"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": 1625852427439.325, "dur": 2897.423, + "args": { + "External id": 3723411,"Record function id": 0, "Ev Idx": 3218 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.16)", "pid": 1336756, "tid": 1381189, + "ts": 1625852427457.521, "dur": 1051.172, + "args": { + "External id": 3723412,"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": 1625852427472.356, "dur": 346.281, + "args": { + "External id": 3723413,"Record function id": 0, "Ev Idx": 3220 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1625852427552.865, "dur": 3.902, + "args": { + "External id": 3723414,"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": 1625852427559.894, "dur": 1.340, + "args": { + "External id": 3723415,"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": 1625852427563.322, "dur": 3.052, + "args": { + "External id": 3723416,"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": 1625852427568.239, "dur": 0.978, + "args": { + "External id": 3723417,"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": 1625852427570.932, "dur": 1.114, + "args": { + "External id": 3723418,"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": 1625852427573.780, "dur": 0.842, + "args": { + "External id": 3723419,"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": 1625852427576.297, "dur": 1.822, + "args": { + "External id": 3723420,"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": 1625852427579.693, "dur": 0.923, + "args": { + "External id": 3723421,"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": 1625852427582.487, "dur": 1.089, + "args": { + "External id": 3723422,"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": 1625852427585.023, "dur": 0.836, + "args": { + "External id": 3723423,"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": 1625852427604.036, "dur": 179.826, + "args": { + "External id": 3723424,"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": 1625852427621.022, "dur": 157.500, + "args": { + "External id": 3723425,"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": 1625852427644.100, "dur": 14.223, + "args": { + "External id": 3723426,"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": 1625852427661.638, "dur": 87.084, + "args": { + "External id": 3723427,"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": 1625852427664.171, "dur": 84.171, + "args": { + "External id": 3723428,"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": 1625852427668.426, "dur": 5.349, + "args": { + "External id": 3723429,"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": 1625852427675.688, "dur": 71.842, + "args": { + "External id": 3723430,"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": 1625852427907.228, "dur": 592.339, + "args": { + "External id": 3723431,"Record function id": 0, "Ev Idx": 3238 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.15)", "pid": 1336756, "tid": 1381189, + "ts": 1625852427925.461, "dur": 561.436, + "args": { + "External id": 3723432,"Record function id": 0, "Ev Idx": 3239 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1625852428022.663, "dur": 6.624, + "args": { + "External id": 3723433,"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": 1625852428046.089, "dur": 33.375, + "args": { + "External id": 3723434,"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": 1625852428051.771, "dur": 1.816, + "args": { + "External id": 3723435,"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": 1625852428056.182, "dur": 0.666, + "args": { + "External id": 3723436,"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": 1625852428058.723, "dur": 0.545, + "args": { + "External id": 3723437,"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": 1625852428061.148, "dur": 0.439, + "args": { + "External id": 3723438,"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": 1625852428063.164, "dur": 0.943, + "args": { + "External id": 3723439,"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": 1625852428065.850, "dur": 2.377, + "args": { + "External id": 3723440,"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": 1625852428069.659, "dur": 0.504, + "args": { + "External id": 3723441,"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": 1625852428072.169, "dur": 0.668, + "args": { + "External id": 3723442,"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": 1625852428074.837, "dur": 0.424, + "args": { + "External id": 3723443,"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": 1625852428091.482, "dur": 35.636, + "args": { + "External id": 3723444,"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": 1625852428160.353, "dur": 104.757, + "args": { + "External id": 3723445,"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": 1625852428171.702, "dur": 3.131, + "args": { + "External id": 3723446,"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": 1625852428180.364, "dur": 10.447, + "args": { + "External id": 3723447,"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": 1625852428184.555, "dur": 5.833, + "args": { + "External id": 3723448,"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": 1625852428188.701, "dur": 0.588, + "args": { + "External id": 3723449,"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": 1625852428197.788, "dur": 27.775, + "args": { + "External id": 3723450,"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": 1625852428200.598, "dur": 0.430, + "args": { + "External id": 3723451,"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": 1625852428203.512, "dur": 0.336, + "args": { + "External id": 3723452,"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": 1625852428205.511, "dur": 2.130, + "args": { + "External id": 3723453,"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": 1625852428209.590, "dur": 0.352, + "args": { + "External id": 3723454,"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": 1625852428211.687, "dur": 0.811, + "args": { + "External id": 3723455,"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": 1625852428214.223, "dur": 0.410, + "args": { + "External id": 3723456,"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": 1625852428216.462, "dur": 0.538, + "args": { + "External id": 3723457,"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": 1625852428218.707, "dur": 0.653, + "args": { + "External id": 3723458,"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": 1625852428221.443, "dur": 0.560, + "args": { + "External id": 3723459,"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": 1625852428237.030, "dur": 20.718, + "args": { + "External id": 3723460,"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": 1625852428312.071, "dur": 110.956, + "args": { + "External id": 3723461,"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": 1625852428334.640, "dur": 85.151, + "args": { + "External id": 3723462,"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": 1625852428344.891, "dur": 70.226, + "args": { + "External id": 3723463,"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": 1625852428437.170, "dur": 1.938, + "args": { + "External id": 3723464,"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": 1625852428515.990, "dur": 1800.397, + "args": { + "External id": 3723465,"Sequence number": 37295106, "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": 1625852428515.990, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1625852428625.785, "dur": 124.579, + "args": { + "External id": 3723466,"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": 1625852428790.725, "dur": 40.733, + "args": { + "External id": 3723467,"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": 1625852428849.937, "dur": 55.225, + "args": { + "External id": 3723468,"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": 1625852428916.965, "dur": 36.130, + "args": { + "External id": 3723469,"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": 1625852428960.825, "dur": 104.746, + "args": { + "External id": 3723470,"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": 1625852429100.639, "dur": 40.961, + "args": { + "External id": 3723471,"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": 1625852429151.611, "dur": 50.699, + "args": { + "External id": 3723472,"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": 1625852429231.141, "dur": 30.306, + "args": { + "External id": 3723473,"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": 1625852429279.826, "dur": 29.879, + "args": { + "External id": 3723474,"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": 1625852429329.737, "dur": 21.302, + "args": { + "External id": 3723475,"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": 1625852429365.548, "dur": 16.607, + "args": { + "External id": 3723476,"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": 1625852429392.140, "dur": 33.182, + "args": { + "External id": 3723477,"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": 1625852429428.971, "dur": 32.725, + "args": { + "External id": 3723478,"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": 1625852429494.295, "dur": 202.754, + "args": { + "External id": 3723479,"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": 1625852429585.946, "dur": 5.578, + "args": { + "External id": 3723480,"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": 1625852429593.492, "dur": 2.026, + "args": { + "External id": 3723481,"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": 1625852429734.589, "dur": 31.734, + "args": { + "External id": 3723482,"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": 1625852429777.721, "dur": 14.557, + "args": { + "External id": 3723483,"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": 1625852429801.118, "dur": 45.917, + "args": { + "External id": 3723484,"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": 1625852429852.788, "dur": 35.410, + "args": { + "External id": 3723485,"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": 1625852429911.389, "dur": 32.434, + "args": { + "External id": 3723486,"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": 1625852429948.820, "dur": 67.563, + "args": { + "External id": 3723487,"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": 1625852430026.735, "dur": 28.609, + "args": { + "External id": 3723488,"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": 1625852430062.293, "dur": 32.295, + "args": { + "External id": 3723489,"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": 1625852430118.367, "dur": 28.055, + "args": { + "External id": 3723490,"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": 1625852430164.543, "dur": 24.164, + "args": { + "External id": 3723491,"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": 1625852430205.479, "dur": 18.318, + "args": { + "External id": 3723492,"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": 1625852430240.118, "dur": 16.490, + "args": { + "External id": 3723493,"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": 1625852430270.882, "dur": 16.436, + "args": { + "External id": 3723494,"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": 1625852430360.438, "dur": 15.759, + "args": { + "External id": 3723495,"Record function id": 0, "Ev Idx": 3302 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852430363.799, "dur": 11.579, + "args": { + "External id": 3723496,"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": 1625852430368.249, "dur": 6.162, + "args": { + "External id": 3723497,"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": 1625852430370.163, "dur": 4.141, + "args": { + "External id": 3723498,"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": 1625852430380.691, "dur": 7.041, + "args": { + "External id": 3723499,"Record function id": 0, "Ev Idx": 3306 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852430382.172, "dur": 5.098, + "args": { + "External id": 3723500,"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": 1625852430383.097, "dur": 3.663, + "args": { + "External id": 3723501,"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": 1625852430383.716, "dur": 2.959, + "args": { + "External id": 3723502,"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": 1625852430391.417, "dur": 4.446, + "args": { + "External id": 3723503,"Record function id": 0, "Ev Idx": 3310 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852430392.810, "dur": 2.627, + "args": { + "External id": 3723504,"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": 1625852430393.634, "dur": 1.398, + "args": { + "External id": 3723505,"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": 1625852430394.214, "dur": 0.736, + "args": { + "External id": 3723506,"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": 1625852430399.234, "dur": 4.772, + "args": { + "External id": 3723507,"Record function id": 0, "Ev Idx": 3314 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852430400.890, "dur": 2.677, + "args": { + "External id": 3723508,"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": 1625852430401.627, "dur": 1.517, + "args": { + "External id": 3723509,"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": 1625852430402.157, "dur": 0.902, + "args": { + "External id": 3723510,"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": 1625852430407.497, "dur": 4.028, + "args": { + "External id": 3723511,"Record function id": 0, "Ev Idx": 3318 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852430408.771, "dur": 2.358, + "args": { + "External id": 3723512,"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": 1625852430409.489, "dur": 1.198, + "args": { + "External id": 3723513,"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": 1625852430410.041, "dur": 0.558, + "args": { + "External id": 3723514,"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": 1625852430414.989, "dur": 3.929, + "args": { + "External id": 3723515,"Record function id": 0, "Ev Idx": 3322 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852430416.147, "dur": 2.368, + "args": { + "External id": 3723516,"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": 1625852430416.792, "dur": 1.304, + "args": { + "External id": 3723517,"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": 1625852430417.237, "dur": 0.779, + "args": { + "External id": 3723518,"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": 1625852430422.454, "dur": 4.307, + "args": { + "External id": 3723519,"Record function id": 0, "Ev Idx": 3326 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852430423.815, "dur": 2.472, + "args": { + "External id": 3723520,"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": 1625852430424.359, "dur": 1.482, + "args": { + "External id": 3723521,"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": 1625852430425.104, "dur": 0.620, + "args": { + "External id": 3723522,"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": 1625852430430.394, "dur": 3.534, + "args": { + "External id": 3723523,"Record function id": 0, "Ev Idx": 3330 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852430431.519, "dur": 2.012, + "args": { + "External id": 3723524,"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": 1625852430431.940, "dur": 1.174, + "args": { + "External id": 3723525,"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": 1625852430432.375, "dur": 0.675, + "args": { + "External id": 3723526,"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": 1625852430437.194, "dur": 5.430, + "args": { + "External id": 3723527,"Record function id": 0, "Ev Idx": 3334 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852430438.372, "dur": 3.822, + "args": { + "External id": 3723528,"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": 1625852430438.917, "dur": 2.720, + "args": { + "External id": 3723529,"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": 1625852430439.389, "dur": 2.186, + "args": { + "External id": 3723530,"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": 1625852430446.652, "dur": 35361.143, + "args": { + "External id": 3723531,"Record function id": 0, "Sequence number": 37295105, "Fwd thread id": 1, "Ev Idx": 3338 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1625852430448.111, "dur": 35351.794, + "args": { + "External id": 3723532,"Sequence number": 37295105, "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": 1625852430448.111, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.16)", "pid": 1336756, "tid": 1381189, + "ts": 1625852430476.965, "dur": 36.633, + "args": { + "External id": 3723533,"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": 1625852430521.790, "dur": 63.568, + "args": { + "External id": 3723534,"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": 1625852430591.987, "dur": 35199.228, + "args": { + "External id": 3723535,"Record function id": 0, "Ev Idx": 3342 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1625852430698.256, "dur": 8.430, + "args": { + "External id": 3723536,"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": 1625852430718.302, "dur": 5.025, + "args": { + "External id": 3723537,"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": 1625852430742.235, "dur": 34195.858, + "args": { + "External id": 3723538,"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": 1625852430755.925, "dur": 34173.364, + "args": { + "External id": 3723539,"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": 1625852430801.143, "dur": 13.816, + "args": { + "External id": 3723540,"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": 1625852430824.408, "dur": 34062.078, + "args": { + "External id": 3723541,"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": 1625852430827.091, "dur": 34058.788, + "args": { + "External id": 3723542,"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": 1625852430831.268, "dur": 4.610, + "args": { + "External id": 3723543,"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": 1625852430837.906, "dur": 34044.325, + "args": { + "External id": 3723544,"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": 1625852465051.543, "dur": 8.858, + "args": { + "External id": 3723545,"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": 1625852465054.899, "dur": 5.021, + "args": { + "External id": 3723546,"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": 1625852465091.053, "dur": 363.594, + "args": { + "External id": 3723547,"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": 1625852465121.728, "dur": 327.927, + "args": { + "External id": 3723548,"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": 1625852465132.977, "dur": 311.256, + "args": { + "External id": 3723549,"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": 1625852465484.080, "dur": 1.977, + "args": { + "External id": 3723550,"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": 1625852465543.641, "dur": 6.381, + "args": { + "External id": 3723551,"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": 1625852465597.485, "dur": 3.566, + "args": { + "External id": 3723552,"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": 1625852465618.345, "dur": 0.995, + "args": { + "External id": 3723553,"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": 1625852465633.601, "dur": 1.051, + "args": { + "External id": 3723554,"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": 1625852465648.096, "dur": 0.845, + "args": { + "External id": 3723555,"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": 1625852465661.064, "dur": 2.792, + "args": { + "External id": 3723556,"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": 1625852465675.863, "dur": 18.918, + "args": { + "External id": 3723557,"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": 1625852465713.048, "dur": 2.454, + "args": { + "External id": 3723558,"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": 1625852465726.894, "dur": 0.967, + "args": { + "External id": 3723559,"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": 1625852465824.576, "dur": 2801.263, + "args": { + "External id": 3723560,"Record function id": 0, "Ev Idx": 3367 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.15)", "pid": 1336756, "tid": 1381189, + "ts": 1625852465843.755, "dur": 1050.447, + "args": { + "External id": 3723561,"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": 1625852465859.303, "dur": 371.571, + "args": { + "External id": 3723562,"Record function id": 0, "Ev Idx": 3369 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1625852465937.549, "dur": 5.673, + "args": { + "External id": 3723563,"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": 1625852465946.701, "dur": 1.053, + "args": { + "External id": 3723564,"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": 1625852465949.865, "dur": 0.980, + "args": { + "External id": 3723565,"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": 1625852465952.309, "dur": 1.002, + "args": { + "External id": 3723566,"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": 1625852465954.872, "dur": 0.841, + "args": { + "External id": 3723567,"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": 1625852465957.796, "dur": 0.749, + "args": { + "External id": 3723568,"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": 1625852465960.393, "dur": 1.556, + "args": { + "External id": 3723569,"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": 1625852465963.998, "dur": 1.154, + "args": { + "External id": 3723570,"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": 1625852465966.692, "dur": 2.468, + "args": { + "External id": 3723571,"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": 1625852465970.482, "dur": 0.905, + "args": { + "External id": 3723572,"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": 1625852466036.685, "dur": 158.063, + "args": { + "External id": 3723573,"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": 1625852466054.524, "dur": 135.393, + "args": { + "External id": 3723574,"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": 1625852466076.237, "dur": 12.493, + "args": { + "External id": 3723575,"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": 1625852466092.213, "dur": 67.420, + "args": { + "External id": 3723576,"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": 1625852466094.944, "dur": 64.393, + "args": { + "External id": 3723577,"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": 1625852466099.242, "dur": 5.660, + "args": { + "External id": 3723578,"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": 1625852466106.981, "dur": 51.683, + "args": { + "External id": 3723579,"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": 1625852466323.953, "dur": 561.837, + "args": { + "External id": 3723580,"Record function id": 0, "Ev Idx": 3387 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.14)", "pid": 1336756, "tid": 1381189, + "ts": 1625852466343.247, "dur": 529.543, + "args": { + "External id": 3723581,"Record function id": 0, "Ev Idx": 3388 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1625852466401.171, "dur": 4.707, + "args": { + "External id": 3723582,"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": 1625852466420.932, "dur": 31.378, + "args": { + "External id": 3723583,"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": 1625852466426.499, "dur": 1.494, + "args": { + "External id": 3723584,"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": 1625852466430.446, "dur": 0.425, + "args": { + "External id": 3723585,"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": 1625852466432.723, "dur": 0.635, + "args": { + "External id": 3723586,"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": 1625852466435.258, "dur": 2.231, + "args": { + "External id": 3723587,"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": 1625852466439.355, "dur": 0.357, + "args": { + "External id": 3723588,"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": 1625852466441.476, "dur": 0.449, + "args": { + "External id": 3723589,"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": 1625852466443.609, "dur": 0.434, + "args": { + "External id": 3723590,"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": 1625852466445.600, "dur": 0.441, + "args": { + "External id": 3723591,"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": 1625852466447.866, "dur": 0.363, + "args": { + "External id": 3723592,"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": 1625852466462.915, "dur": 32.480, + "args": { + "External id": 3723593,"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": 1625852466526.208, "dur": 106.337, + "args": { + "External id": 3723594,"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": 1625852466536.327, "dur": 2.661, + "args": { + "External id": 3723595,"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": 1625852466544.475, "dur": 10.079, + "args": { + "External id": 3723596,"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": 1625852466548.769, "dur": 5.319, + "args": { + "External id": 3723597,"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": 1625852466552.642, "dur": 0.365, + "args": { + "External id": 3723598,"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": 1625852466561.270, "dur": 28.240, + "args": { + "External id": 3723599,"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": 1625852466563.916, "dur": 2.270, + "args": { + "External id": 3723600,"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": 1625852466568.011, "dur": 0.641, + "args": { + "External id": 3723601,"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": 1625852466570.186, "dur": 0.617, + "args": { + "External id": 3723602,"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": 1625852466572.300, "dur": 0.426, + "args": { + "External id": 3723603,"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": 1625852466574.590, "dur": 0.358, + "args": { + "External id": 3723604,"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": 1625852466576.612, "dur": 0.580, + "args": { + "External id": 3723605,"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": 1625852466579.316, "dur": 0.500, + "args": { + "External id": 3723606,"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": 1625852466581.410, "dur": 0.348, + "args": { + "External id": 3723607,"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": 1625852466583.857, "dur": 2.235, + "args": { + "External id": 3723608,"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": 1625852466599.483, "dur": 25.885, + "args": { + "External id": 3723609,"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": 1625852466692.792, "dur": 114.241, + "args": { + "External id": 3723610,"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": 1625852466716.856, "dur": 86.633, + "args": { + "External id": 3723611,"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": 1625852466727.311, "dur": 71.181, + "args": { + "External id": 3723612,"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": 1625852466821.494, "dur": 1.656, + "args": { + "External id": 3723613,"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": 1625852466901.217, "dur": 1702.608, + "args": { + "External id": 3723614,"Sequence number": 37295104, "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": 1625852466901.217, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1625852467053.096, "dur": 109.331, + "args": { + "External id": 3723615,"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": 1625852467201.175, "dur": 41.874, + "args": { + "External id": 3723616,"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": 1625852467263.310, "dur": 50.757, + "args": { + "External id": 3723617,"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": 1625852467323.503, "dur": 35.102, + "args": { + "External id": 3723618,"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": 1625852467366.395, "dur": 46.556, + "args": { + "External id": 3723619,"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": 1625852467421.524, "dur": 29.193, + "args": { + "External id": 3723620,"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": 1625852467461.073, "dur": 42.581, + "args": { + "External id": 3723621,"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": 1625852467525.522, "dur": 23.317, + "args": { + "External id": 3723622,"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": 1625852467568.047, "dur": 30.672, + "args": { + "External id": 3723623,"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": 1625852467617.051, "dur": 19.338, + "args": { + "External id": 3723624,"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": 1625852467649.328, "dur": 15.759, + "args": { + "External id": 3723625,"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": 1625852467674.388, "dur": 48.206, + "args": { + "External id": 3723626,"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": 1625852467727.882, "dur": 33.741, + "args": { + "External id": 3723627,"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": 1625852467811.590, "dur": 210.166, + "args": { + "External id": 3723628,"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": 1625852467890.297, "dur": 5.319, + "args": { + "External id": 3723629,"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": 1625852467897.936, "dur": 2.105, + "args": { + "External id": 3723630,"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": 1625852468061.435, "dur": 29.685, + "args": { + "External id": 3723631,"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": 1625852468105.868, "dur": 14.880, + "args": { + "External id": 3723632,"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": 1625852468130.362, "dur": 43.948, + "args": { + "External id": 3723633,"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": 1625852468184.098, "dur": 36.208, + "args": { + "External id": 3723634,"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": 1625852468227.370, "dur": 24.131, + "args": { + "External id": 3723635,"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": 1625852468257.524, "dur": 50.752, + "args": { + "External id": 3723636,"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": 1625852468321.082, "dur": 25.652, + "args": { + "External id": 3723637,"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": 1625852468356.644, "dur": 36.336, + "args": { + "External id": 3723638,"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": 1625852468411.318, "dur": 24.673, + "args": { + "External id": 3723639,"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": 1625852468455.786, "dur": 23.088, + "args": { + "External id": 3723640,"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": 1625852468492.615, "dur": 21.326, + "args": { + "External id": 3723641,"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": 1625852468527.441, "dur": 17.062, + "args": { + "External id": 3723642,"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": 1625852468556.371, "dur": 20.161, + "args": { + "External id": 3723643,"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": 1625852468648.479, "dur": 16.899, + "args": { + "External id": 3723644,"Record function id": 0, "Ev Idx": 3451 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852468651.899, "dur": 12.626, + "args": { + "External id": 3723645,"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": 1625852468656.308, "dur": 7.323, + "args": { + "External id": 3723646,"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": 1625852468658.046, "dur": 5.454, + "args": { + "External id": 3723647,"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": 1625852468669.234, "dur": 5.169, + "args": { + "External id": 3723648,"Record function id": 0, "Ev Idx": 3455 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852468670.674, "dur": 3.312, + "args": { + "External id": 3723649,"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": 1625852468671.320, "dur": 2.191, + "args": { + "External id": 3723650,"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": 1625852468672.308, "dur": 1.108, + "args": { + "External id": 3723651,"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": 1625852468701.285, "dur": 7.404, + "args": { + "External id": 3723652,"Record function id": 0, "Ev Idx": 3459 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852468703.274, "dur": 4.789, + "args": { + "External id": 3723653,"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": 1625852468704.565, "dur": 2.677, + "args": { + "External id": 3723654,"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": 1625852468705.404, "dur": 1.631, + "args": { + "External id": 3723655,"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": 1625852468712.444, "dur": 4.738, + "args": { + "External id": 3723656,"Record function id": 0, "Ev Idx": 3463 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852468714.151, "dur": 2.642, + "args": { + "External id": 3723657,"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": 1625852468715.040, "dur": 1.340, + "args": { + "External id": 3723658,"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": 1625852468715.674, "dur": 0.636, + "args": { + "External id": 3723659,"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": 1625852468720.220, "dur": 3.822, + "args": { + "External id": 3723660,"Record function id": 0, "Ev Idx": 3467 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852468721.329, "dur": 2.295, + "args": { + "External id": 3723661,"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": 1625852468721.958, "dur": 1.248, + "args": { + "External id": 3723662,"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": 1625852468722.315, "dur": 0.825, + "args": { + "External id": 3723663,"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": 1625852468727.235, "dur": 4.027, + "args": { + "External id": 3723664,"Record function id": 0, "Ev Idx": 3471 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852468728.440, "dur": 2.434, + "args": { + "External id": 3723665,"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": 1625852468729.233, "dur": 1.174, + "args": { + "External id": 3723666,"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": 1625852468729.635, "dur": 0.663, + "args": { + "External id": 3723667,"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": 1625852468734.613, "dur": 3.681, + "args": { + "External id": 3723668,"Record function id": 0, "Ev Idx": 3475 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852468735.702, "dur": 2.167, + "args": { + "External id": 3723669,"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": 1625852468736.182, "dur": 1.280, + "args": { + "External id": 3723670,"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": 1625852468736.835, "dur": 0.547, + "args": { + "External id": 3723671,"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": 1625852468744.514, "dur": 6.344, + "args": { + "External id": 3723672,"Record function id": 0, "Ev Idx": 3479 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852468745.662, "dur": 4.765, + "args": { + "External id": 3723673,"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": 1625852468746.452, "dur": 3.496, + "args": { + "External id": 3723674,"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": 1625852468746.914, "dur": 2.957, + "args": { + "External id": 3723675,"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": 1625852468754.127, "dur": 3.900, + "args": { + "External id": 3723676,"Record function id": 0, "Ev Idx": 3483 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852468755.248, "dur": 2.338, + "args": { + "External id": 3723677,"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": 1625852468755.700, "dur": 1.443, + "args": { + "External id": 3723678,"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": 1625852468756.298, "dur": 0.740, + "args": { + "External id": 3723679,"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": 1625852468761.793, "dur": 36365.901, + "args": { + "External id": 3723680,"Record function id": 0, "Sequence number": 37295103, "Fwd thread id": 1, "Ev Idx": 3487 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1625852468763.045, "dur": 36356.710, + "args": { + "External id": 3723681,"Sequence number": 37295103, "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": 1625852468763.045, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.15)", "pid": 1336756, "tid": 1381189, + "ts": 1625852468792.331, "dur": 39.191, + "args": { + "External id": 3723682,"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": 1625852468839.065, "dur": 63.854, + "args": { + "External id": 3723683,"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": 1625852468908.622, "dur": 36203.238, + "args": { + "External id": 3723684,"Record function id": 0, "Ev Idx": 3491 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1625852469031.924, "dur": 8.398, + "args": { + "External id": 3723685,"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": 1625852469050.752, "dur": 4.890, + "args": { + "External id": 3723686,"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": 1625852469071.438, "dur": 35210.592, + "args": { + "External id": 3723687,"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": 1625852469085.670, "dur": 35186.950, + "args": { + "External id": 3723688,"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": 1625852469131.819, "dur": 13.189, + "args": { + "External id": 3723689,"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": 1625852469151.563, "dur": 35075.395, + "args": { + "External id": 3723690,"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": 1625852469154.524, "dur": 35071.770, + "args": { + "External id": 3723691,"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": 1625852469158.677, "dur": 4.862, + "args": { + "External id": 3723692,"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": 1625852469165.311, "dur": 35057.274, + "args": { + "External id": 3723693,"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": 1625852504369.027, "dur": 8.447, + "args": { + "External id": 3723694,"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": 1625852504372.096, "dur": 5.042, + "args": { + "External id": 3723695,"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": 1625852504409.864, "dur": 365.686, + "args": { + "External id": 3723696,"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": 1625852504436.839, "dur": 333.880, + "args": { + "External id": 3723697,"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": 1625852504447.719, "dur": 316.721, + "args": { + "External id": 3723698,"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": 1625852504797.613, "dur": 2.078, + "args": { + "External id": 3723699,"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": 1625852504856.432, "dur": 6.266, + "args": { + "External id": 3723700,"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": 1625852504911.453, "dur": 1.194, + "args": { + "External id": 3723701,"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": 1625852504929.119, "dur": 1.116, + "args": { + "External id": 3723702,"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": 1625852504943.260, "dur": 1.231, + "args": { + "External id": 3723703,"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": 1625852504956.776, "dur": 1.140, + "args": { + "External id": 3723704,"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": 1625852504971.260, "dur": 0.845, + "args": { + "External id": 3723705,"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": 1625852505016.577, "dur": 2.022, + "args": { + "External id": 3723706,"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": 1625852505034.953, "dur": 1.816, + "args": { + "External id": 3723707,"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": 1625852505048.191, "dur": 0.946, + "args": { + "External id": 3723708,"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": 1625852505142.838, "dur": 2767.198, + "args": { + "External id": 3723709,"Record function id": 0, "Ev Idx": 3516 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.14)", "pid": 1336756, "tid": 1381189, + "ts": 1625852505161.617, "dur": 1026.162, + "args": { + "External id": 3723710,"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": 1625852505176.166, "dur": 306.588, + "args": { + "External id": 3723711,"Record function id": 0, "Ev Idx": 3518 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1625852505252.107, "dur": 3.910, + "args": { + "External id": 3723712,"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": 1625852505259.173, "dur": 1.151, + "args": { + "External id": 3723713,"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": 1625852505262.635, "dur": 0.794, + "args": { + "External id": 3723714,"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": 1625852505264.991, "dur": 0.770, + "args": { + "External id": 3723715,"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": 1625852505267.176, "dur": 0.964, + "args": { + "External id": 3723716,"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": 1625852505269.992, "dur": 1.131, + "args": { + "External id": 3723717,"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": 1625852505272.668, "dur": 1.831, + "args": { + "External id": 3723718,"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": 1625852505275.976, "dur": 3.103, + "args": { + "External id": 3723719,"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": 1625852505280.417, "dur": 0.954, + "args": { + "External id": 3723720,"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": 1625852505282.855, "dur": 1.195, + "args": { + "External id": 3723721,"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": 1625852505302.088, "dur": 150.109, + "args": { + "External id": 3723722,"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": 1625852505317.969, "dur": 129.980, + "args": { + "External id": 3723723,"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": 1625852505340.662, "dur": 11.486, + "args": { + "External id": 3723724,"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": 1625852505355.717, "dur": 64.287, + "args": { + "External id": 3723725,"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": 1625852505358.287, "dur": 61.355, + "args": { + "External id": 3723726,"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": 1625852505362.537, "dur": 5.380, + "args": { + "External id": 3723727,"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": 1625852505370.179, "dur": 48.923, + "args": { + "External id": 3723728,"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": 1625852505563.528, "dur": 616.256, + "args": { + "External id": 3723729,"Record function id": 0, "Ev Idx": 3536 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.13)", "pid": 1336756, "tid": 1381189, + "ts": 1625852505580.037, "dur": 586.915, + "args": { + "External id": 3723730,"Record function id": 0, "Ev Idx": 3537 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1625852505633.762, "dur": 4.667, + "args": { + "External id": 3723731,"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": 1625852505653.043, "dur": 46.784, + "args": { + "External id": 3723732,"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": 1625852505658.043, "dur": 0.927, + "args": { + "External id": 3723733,"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": 1625852505661.274, "dur": 0.744, + "args": { + "External id": 3723734,"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": 1625852505663.949, "dur": 2.107, + "args": { + "External id": 3723735,"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": 1625852505667.909, "dur": 0.462, + "args": { + "External id": 3723736,"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": 1625852505669.910, "dur": 0.386, + "args": { + "External id": 3723737,"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": 1625852505671.991, "dur": 0.527, + "args": { + "External id": 3723738,"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": 1625852505674.105, "dur": 0.352, + "args": { + "External id": 3723739,"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": 1625852505676.039, "dur": 15.952, + "args": { + "External id": 3723740,"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": 1625852505694.975, "dur": 0.594, + "args": { + "External id": 3723741,"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": 1625852505711.662, "dur": 35.127, + "args": { + "External id": 3723742,"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": 1625852505780.157, "dur": 118.223, + "args": { + "External id": 3723743,"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": 1625852505790.531, "dur": 4.000, + "args": { + "External id": 3723744,"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": 1625852505808.336, "dur": 12.368, + "args": { + "External id": 3723745,"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": 1625852505812.922, "dur": 7.313, + "args": { + "External id": 3723746,"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": 1625852505816.606, "dur": 2.391, + "args": { + "External id": 3723747,"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": 1625852505830.673, "dur": 29.128, + "args": { + "External id": 3723748,"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": 1625852505833.134, "dur": 0.463, + "args": { + "External id": 3723749,"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": 1625852505835.409, "dur": 0.422, + "args": { + "External id": 3723750,"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": 1625852505837.416, "dur": 0.662, + "args": { + "External id": 3723751,"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": 1625852505839.956, "dur": 0.677, + "args": { + "External id": 3723752,"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": 1625852505842.082, "dur": 0.343, + "args": { + "External id": 3723753,"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": 1625852505844.236, "dur": 0.345, + "args": { + "External id": 3723754,"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": 1625852505846.226, "dur": 0.336, + "args": { + "External id": 3723755,"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": 1625852505848.273, "dur": 2.895, + "args": { + "External id": 3723756,"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": 1625852505852.888, "dur": 0.396, + "args": { + "External id": 3723757,"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": 1625852505870.691, "dur": 20.481, + "args": { + "External id": 3723758,"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": 1625852505944.808, "dur": 151.083, + "args": { + "External id": 3723759,"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": 1625852505966.778, "dur": 125.094, + "args": { + "External id": 3723760,"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": 1625852505976.823, "dur": 110.300, + "args": { + "External id": 3723761,"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": 1625852506111.988, "dur": 2.000, + "args": { + "External id": 3723762,"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": 1625852506195.572, "dur": 1694.622, + "args": { + "External id": 3723763,"Sequence number": 37295102, "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": 1625852506195.572, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1625852506305.517, "dur": 103.187, + "args": { + "External id": 3723764,"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": 1625852506445.369, "dur": 40.320, + "args": { + "External id": 3723765,"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": 1625852506506.876, "dur": 50.536, + "args": { + "External id": 3723766,"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": 1625852506567.686, "dur": 34.544, + "args": { + "External id": 3723767,"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": 1625852506609.149, "dur": 46.405, + "args": { + "External id": 3723768,"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": 1625852506663.034, "dur": 47.913, + "args": { + "External id": 3723769,"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": 1625852506723.138, "dur": 45.907, + "args": { + "External id": 3723770,"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": 1625852506793.101, "dur": 24.974, + "args": { + "External id": 3723771,"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": 1625852506836.120, "dur": 27.264, + "args": { + "External id": 3723772,"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": 1625852506881.486, "dur": 19.773, + "args": { + "External id": 3723773,"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": 1625852506916.113, "dur": 15.473, + "args": { + "External id": 3723774,"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": 1625852506940.872, "dur": 31.744, + "args": { + "External id": 3723775,"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": 1625852506975.758, "dur": 81.308, + "args": { + "External id": 3723776,"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": 1625852507110.885, "dur": 178.682, + "args": { + "External id": 3723777,"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": 1625852507193.515, "dur": 5.929, + "args": { + "External id": 3723778,"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": 1625852507201.307, "dur": 2.006, + "args": { + "External id": 3723779,"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": 1625852507322.952, "dur": 28.080, + "args": { + "External id": 3723780,"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": 1625852507362.467, "dur": 14.811, + "args": { + "External id": 3723781,"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": 1625852507391.264, "dur": 41.403, + "args": { + "External id": 3723782,"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": 1625852507439.355, "dur": 36.644, + "args": { + "External id": 3723783,"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": 1625852507483.015, "dur": 22.862, + "args": { + "External id": 3723784,"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": 1625852507511.747, "dur": 31.509, + "args": { + "External id": 3723785,"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": 1625852507554.839, "dur": 22.659, + "args": { + "External id": 3723786,"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": 1625852507584.499, "dur": 33.867, + "args": { + "External id": 3723787,"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": 1625852507650.917, "dur": 50.138, + "args": { + "External id": 3723788,"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": 1625852507730.390, "dur": 26.332, + "args": { + "External id": 3723789,"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": 1625852507773.916, "dur": 18.237, + "args": { + "External id": 3723790,"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": 1625852507809.713, "dur": 19.596, + "args": { + "External id": 3723791,"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": 1625852507841.701, "dur": 15.031, + "args": { + "External id": 3723792,"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": 1625852507933.722, "dur": 17.658, + "args": { + "External id": 3723793,"Record function id": 0, "Ev Idx": 3600 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852507936.728, "dur": 13.755, + "args": { + "External id": 3723794,"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": 1625852507944.193, "dur": 5.499, + "args": { + "External id": 3723795,"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": 1625852507945.845, "dur": 3.727, + "args": { + "External id": 3723796,"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": 1625852507955.001, "dur": 5.051, + "args": { + "External id": 3723797,"Record function id": 0, "Ev Idx": 3604 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852507956.404, "dur": 3.234, + "args": { + "External id": 3723798,"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": 1625852507957.186, "dur": 2.009, + "args": { + "External id": 3723799,"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": 1625852507957.977, "dur": 1.113, + "args": { + "External id": 3723800,"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": 1625852507963.155, "dur": 4.057, + "args": { + "External id": 3723801,"Record function id": 0, "Ev Idx": 3608 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852507964.209, "dur": 2.607, + "args": { + "External id": 3723802,"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": 1625852507964.923, "dur": 1.492, + "args": { + "External id": 3723803,"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": 1625852507965.281, "dur": 1.057, + "args": { + "External id": 3723804,"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": 1625852507970.230, "dur": 3.949, + "args": { + "External id": 3723805,"Record function id": 0, "Ev Idx": 3612 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852507971.334, "dur": 2.457, + "args": { + "External id": 3723806,"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": 1625852507972.089, "dur": 1.318, + "args": { + "External id": 3723807,"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": 1625852507972.451, "dur": 0.875, + "args": { + "External id": 3723808,"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": 1625852507977.101, "dur": 4.009, + "args": { + "External id": 3723809,"Record function id": 0, "Ev Idx": 3616 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852507978.418, "dur": 2.311, + "args": { + "External id": 3723810,"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": 1625852507979.126, "dur": 1.168, + "args": { + "External id": 3723811,"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": 1625852507979.512, "dur": 0.717, + "args": { + "External id": 3723812,"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": 1625852507984.184, "dur": 41.321, + "args": { + "External id": 3723813,"Record function id": 0, "Ev Idx": 3620 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852508020.418, "dur": 4.401, + "args": { + "External id": 3723814,"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": 1625852508021.740, "dur": 2.258, + "args": { + "External id": 3723815,"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": 1625852508022.413, "dur": 1.293, + "args": { + "External id": 3723816,"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": 1625852508030.255, "dur": 5.804, + "args": { + "External id": 3723817,"Record function id": 0, "Ev Idx": 3624 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852508031.580, "dur": 4.036, + "args": { + "External id": 3723818,"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": 1625852508032.062, "dur": 3.142, + "args": { + "External id": 3723819,"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": 1625852508032.472, "dur": 2.657, + "args": { + "External id": 3723820,"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": 1625852508039.060, "dur": 4.364, + "args": { + "External id": 3723821,"Record function id": 0, "Ev Idx": 3628 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852508040.290, "dur": 2.741, + "args": { + "External id": 3723822,"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": 1625852508041.171, "dur": 1.438, + "args": { + "External id": 3723823,"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": 1625852508041.617, "dur": 0.910, + "args": { + "External id": 3723824,"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": 1625852508046.331, "dur": 3.456, + "args": { + "External id": 3723825,"Record function id": 0, "Ev Idx": 3632 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852508047.285, "dur": 2.115, + "args": { + "External id": 3723826,"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": 1625852508047.737, "dur": 1.228, + "args": { + "External id": 3723827,"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": 1625852508048.236, "dur": 0.640, + "args": { + "External id": 3723828,"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": 1625852508053.184, "dur": 36846.340, + "args": { + "External id": 3723829,"Record function id": 0, "Sequence number": 37295101, "Fwd thread id": 1, "Ev Idx": 3636 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1625852508054.519, "dur": 36836.544, + "args": { + "External id": 3723830,"Sequence number": 37295101, "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": 1625852508054.519, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.14)", "pid": 1336756, "tid": 1381189, + "ts": 1625852508087.005, "dur": 40.681, + "args": { + "External id": 3723831,"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": 1625852508135.503, "dur": 68.850, + "args": { + "External id": 3723832,"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": 1625852508209.484, "dur": 36673.538, + "args": { + "External id": 3723833,"Record function id": 0, "Ev Idx": 3640 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1625852508299.778, "dur": 6.389, + "args": { + "External id": 3723834,"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": 1625852508315.998, "dur": 5.075, + "args": { + "External id": 3723835,"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": 1625852508335.681, "dur": 35704.433, + "args": { + "External id": 3723836,"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": 1625852508349.010, "dur": 35681.252, + "args": { + "External id": 3723837,"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": 1625852508387.971, "dur": 13.689, + "args": { + "External id": 3723838,"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": 1625852508408.038, "dur": 35556.452, + "args": { + "External id": 3723839,"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": 1625852508410.731, "dur": 35553.030, + "args": { + "External id": 3723840,"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": 1625852508415.246, "dur": 4.839, + "args": { + "External id": 3723841,"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": 1625852508422.007, "dur": 35537.681, + "args": { + "External id": 3723842,"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": 1625852544131.669, "dur": 9.799, + "args": { + "External id": 3723843,"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": 1625852544135.282, "dur": 5.671, + "args": { + "External id": 3723844,"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": 1625852544173.437, "dur": 388.845, + "args": { + "External id": 3723845,"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": 1625852544200.550, "dur": 356.156, + "args": { + "External id": 3723846,"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": 1625852544212.087, "dur": 339.133, + "args": { + "External id": 3723847,"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": 1625852544582.236, "dur": 2.337, + "args": { + "External id": 3723848,"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": 1625852544643.796, "dur": 8.641, + "args": { + "External id": 3723849,"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": 1625852544717.667, "dur": 2.091, + "args": { + "External id": 3723850,"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": 1625852544736.814, "dur": 1.323, + "args": { + "External id": 3723851,"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": 1625852544751.920, "dur": 0.941, + "args": { + "External id": 3723852,"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": 1625852544765.254, "dur": 3.189, + "args": { + "External id": 3723853,"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": 1625852544779.593, "dur": 1.350, + "args": { + "External id": 3723854,"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": 1625852544792.936, "dur": 1.018, + "args": { + "External id": 3723855,"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": 1625852544806.244, "dur": 2.191, + "args": { + "External id": 3723856,"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": 1625852544818.914, "dur": 2.701, + "args": { + "External id": 3723857,"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": 1625852544915.111, "dur": 2823.518, + "args": { + "External id": 3723858,"Record function id": 0, "Ev Idx": 3665 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.13)", "pid": 1336756, "tid": 1381189, + "ts": 1625852544935.279, "dur": 1029.959, + "args": { + "External id": 3723859,"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": 1625852544950.972, "dur": 371.790, + "args": { + "External id": 3723860,"Record function id": 0, "Ev Idx": 3667 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1625852545069.908, "dur": 4.639, + "args": { + "External id": 3723861,"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": 1625852545078.094, "dur": 1.421, + "args": { + "External id": 3723862,"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": 1625852545081.190, "dur": 1.202, + "args": { + "External id": 3723863,"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": 1625852545083.832, "dur": 1.192, + "args": { + "External id": 3723864,"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": 1625852545086.558, "dur": 0.881, + "args": { + "External id": 3723865,"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": 1625852545089.307, "dur": 1.049, + "args": { + "External id": 3723866,"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": 1625852545091.928, "dur": 3.546, + "args": { + "External id": 3723867,"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": 1625852545096.662, "dur": 0.917, + "args": { + "External id": 3723868,"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": 1625852545099.180, "dur": 0.840, + "args": { + "External id": 3723869,"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": 1625852545101.334, "dur": 0.914, + "args": { + "External id": 3723870,"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": 1625852545125.854, "dur": 162.003, + "args": { + "External id": 3723871,"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": 1625852545142.637, "dur": 140.446, + "args": { + "External id": 3723872,"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": 1625852545170.979, "dur": 12.944, + "args": { + "External id": 3723873,"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": 1625852545187.120, "dur": 66.986, + "args": { + "External id": 3723874,"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": 1625852545189.826, "dur": 63.962, + "args": { + "External id": 3723875,"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": 1625852545193.859, "dur": 5.350, + "args": { + "External id": 3723876,"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": 1625852545200.935, "dur": 51.999, + "args": { + "External id": 3723877,"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": 1625852545407.245, "dur": 549.969, + "args": { + "External id": 3723878,"Record function id": 0, "Ev Idx": 3685 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.12)", "pid": 1336756, "tid": 1381189, + "ts": 1625852545424.318, "dur": 520.148, + "args": { + "External id": 3723879,"Record function id": 0, "Ev Idx": 3686 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1625852545482.751, "dur": 5.151, + "args": { + "External id": 3723880,"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": 1625852545503.074, "dur": 28.652, + "args": { + "External id": 3723881,"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": 1625852545507.678, "dur": 1.362, + "args": { + "External id": 3723882,"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": 1625852545511.133, "dur": 2.300, + "args": { + "External id": 3723883,"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": 1625852545515.228, "dur": 0.525, + "args": { + "External id": 3723884,"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": 1625852545517.499, "dur": 0.532, + "args": { + "External id": 3723885,"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": 1625852545519.548, "dur": 0.551, + "args": { + "External id": 3723886,"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": 1625852545521.837, "dur": 0.485, + "args": { + "External id": 3723887,"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": 1625852545523.973, "dur": 0.451, + "args": { + "External id": 3723888,"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": 1625852545525.928, "dur": 0.363, + "args": { + "External id": 3723889,"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": 1625852545527.835, "dur": 0.358, + "args": { + "External id": 3723890,"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": 1625852545542.429, "dur": 31.390, + "args": { + "External id": 3723891,"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": 1625852545604.253, "dur": 118.376, + "args": { + "External id": 3723892,"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": 1625852545613.934, "dur": 5.599, + "args": { + "External id": 3723893,"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": 1625852545624.392, "dur": 9.622, + "args": { + "External id": 3723894,"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": 1625852545628.575, "dur": 5.017, + "args": { + "External id": 3723895,"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": 1625852545632.050, "dur": 0.413, + "args": { + "External id": 3723896,"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": 1625852545639.924, "dur": 24.869, + "args": { + "External id": 3723897,"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": 1625852545642.000, "dur": 0.623, + "args": { + "External id": 3723898,"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": 1625852545644.766, "dur": 0.624, + "args": { + "External id": 3723899,"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": 1625852545647.564, "dur": 0.369, + "args": { + "External id": 3723900,"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": 1625852545649.166, "dur": 0.357, + "args": { + "External id": 3723901,"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": 1625852545651.206, "dur": 0.473, + "args": { + "External id": 3723902,"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": 1625852545653.202, "dur": 0.581, + "args": { + "External id": 3723903,"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": 1625852545655.273, "dur": 2.777, + "args": { + "External id": 3723904,"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": 1625852545659.464, "dur": 0.333, + "args": { + "External id": 3723905,"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": 1625852545661.112, "dur": 0.330, + "args": { + "External id": 3723906,"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": 1625852545673.294, "dur": 40.290, + "args": { + "External id": 3723907,"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": 1625852545770.263, "dur": 111.221, + "args": { + "External id": 3723908,"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": 1625852545793.653, "dur": 84.340, + "args": { + "External id": 3723909,"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": 1625852545803.398, "dur": 70.560, + "args": { + "External id": 3723910,"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": 1625852545895.349, "dur": 1.972, + "args": { + "External id": 3723911,"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": 1625852545972.467, "dur": 1744.278, + "args": { + "External id": 3723912,"Sequence number": 37295100, "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": 1625852545972.467, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1625852546122.551, "dur": 110.066, + "args": { + "External id": 3723913,"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": 1625852546275.961, "dur": 40.805, + "args": { + "External id": 3723914,"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": 1625852546336.383, "dur": 51.004, + "args": { + "External id": 3723915,"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": 1625852546396.682, "dur": 34.025, + "args": { + "External id": 3723916,"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": 1625852546437.713, "dur": 47.085, + "args": { + "External id": 3723917,"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": 1625852546495.360, "dur": 31.230, + "args": { + "External id": 3723918,"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": 1625852546534.092, "dur": 43.187, + "args": { + "External id": 3723919,"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": 1625852546601.244, "dur": 23.244, + "args": { + "External id": 3723920,"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": 1625852546641.769, "dur": 27.162, + "args": { + "External id": 3723921,"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": 1625852546707.396, "dur": 22.629, + "args": { + "External id": 3723922,"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": 1625852546744.318, "dur": 15.729, + "args": { + "External id": 3723923,"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": 1625852546772.055, "dur": 34.540, + "args": { + "External id": 3723924,"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": 1625852546810.060, "dur": 34.537, + "args": { + "External id": 3723925,"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": 1625852546872.154, "dur": 227.653, + "args": { + "External id": 3723926,"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": 1625852546951.133, "dur": 6.218, + "args": { + "External id": 3723927,"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": 1625852546959.362, "dur": 4.069, + "args": { + "External id": 3723928,"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": 1625852547135.152, "dur": 27.959, + "args": { + "External id": 3723929,"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": 1625852547193.896, "dur": 15.871, + "args": { + "External id": 3723930,"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": 1625852547220.076, "dur": 45.208, + "args": { + "External id": 3723931,"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": 1625852547271.972, "dur": 40.110, + "args": { + "External id": 3723932,"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": 1625852547318.888, "dur": 39.764, + "args": { + "External id": 3723933,"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": 1625852547371.494, "dur": 41.824, + "args": { + "External id": 3723934,"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": 1625852547420.404, "dur": 22.583, + "args": { + "External id": 3723935,"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": 1625852547450.547, "dur": 32.922, + "args": { + "External id": 3723936,"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": 1625852547500.604, "dur": 25.860, + "args": { + "External id": 3723937,"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": 1625852547545.290, "dur": 24.169, + "args": { + "External id": 3723938,"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": 1625852547584.901, "dur": 22.018, + "args": { + "External id": 3723939,"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": 1625852547623.657, "dur": 17.102, + "args": { + "External id": 3723940,"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": 1625852547656.057, "dur": 16.531, + "args": { + "External id": 3723941,"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": 1625852547765.102, "dur": 15.763, + "args": { + "External id": 3723942,"Record function id": 0, "Ev Idx": 3749 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852547768.653, "dur": 11.327, + "args": { + "External id": 3723943,"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": 1625852547773.038, "dur": 5.958, + "args": { + "External id": 3723944,"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": 1625852547774.845, "dur": 4.019, + "args": { + "External id": 3723945,"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": 1625852547784.669, "dur": 5.282, + "args": { + "External id": 3723946,"Record function id": 0, "Ev Idx": 3753 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852547786.195, "dur": 3.327, + "args": { + "External id": 3723947,"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": 1625852547786.956, "dur": 2.128, + "args": { + "External id": 3723948,"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": 1625852547787.850, "dur": 1.142, + "args": { + "External id": 3723949,"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": 1625852547793.086, "dur": 3.995, + "args": { + "External id": 3723950,"Record function id": 0, "Ev Idx": 3757 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852547794.380, "dur": 2.321, + "args": { + "External id": 3723951,"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": 1625852547794.960, "dur": 1.302, + "args": { + "External id": 3723952,"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": 1625852547795.265, "dur": 0.919, + "args": { + "External id": 3723953,"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": 1625852547800.155, "dur": 6.114, + "args": { + "External id": 3723954,"Record function id": 0, "Ev Idx": 3761 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852547801.320, "dur": 4.570, + "args": { + "External id": 3723955,"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": 1625852547801.977, "dur": 3.487, + "args": { + "External id": 3723956,"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": 1625852547802.424, "dur": 2.980, + "args": { + "External id": 3723957,"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": 1625852547809.225, "dur": 7.627, + "args": { + "External id": 3723958,"Record function id": 0, "Ev Idx": 3765 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852547813.860, "dur": 2.604, + "args": { + "External id": 3723959,"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": 1625852547814.596, "dur": 1.474, + "args": { + "External id": 3723960,"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": 1625852547815.316, "dur": 0.678, + "args": { + "External id": 3723961,"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": 1625852547819.927, "dur": 4.359, + "args": { + "External id": 3723962,"Record function id": 0, "Ev Idx": 3769 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852547821.271, "dur": 2.626, + "args": { + "External id": 3723963,"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": 1625852547822.127, "dur": 1.348, + "args": { + "External id": 3723964,"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": 1625852547822.591, "dur": 0.782, + "args": { + "External id": 3723965,"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": 1625852547827.383, "dur": 4.015, + "args": { + "External id": 3723966,"Record function id": 0, "Ev Idx": 3773 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852547828.569, "dur": 2.430, + "args": { + "External id": 3723967,"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": 1625852547829.307, "dur": 1.301, + "args": { + "External id": 3723968,"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": 1625852547829.858, "dur": 0.644, + "args": { + "External id": 3723969,"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": 1625852547834.569, "dur": 3.406, + "args": { + "External id": 3723970,"Record function id": 0, "Ev Idx": 3777 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852547835.604, "dur": 1.945, + "args": { + "External id": 3723971,"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": 1625852547836.089, "dur": 1.062, + "args": { + "External id": 3723972,"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": 1625852547836.344, "dur": 0.741, + "args": { + "External id": 3723973,"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": 1625852547840.995, "dur": 3.958, + "args": { + "External id": 3723974,"Record function id": 0, "Ev Idx": 3781 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852547842.053, "dur": 2.490, + "args": { + "External id": 3723975,"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": 1625852547842.729, "dur": 1.416, + "args": { + "External id": 3723976,"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": 1625852547843.365, "dur": 0.683, + "args": { + "External id": 3723977,"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": 1625852547848.566, "dur": 36080.257, + "args": { + "External id": 3723978,"Record function id": 0, "Sequence number": 37295099, "Fwd thread id": 1, "Ev Idx": 3785 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1625852547849.768, "dur": 36070.205, + "args": { + "External id": 3723979,"Sequence number": 37295099, "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": 1625852547849.768, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.13)", "pid": 1336756, "tid": 1381189, + "ts": 1625852547884.432, "dur": 37.577, + "args": { + "External id": 3723980,"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": 1625852547929.772, "dur": 105.547, + "args": { + "External id": 3723981,"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": 1625852548042.965, "dur": 35869.025, + "args": { + "External id": 3723982,"Record function id": 0, "Ev Idx": 3789 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1625852548132.550, "dur": 6.690, + "args": { + "External id": 3723983,"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": 1625852548149.197, "dur": 5.161, + "args": { + "External id": 3723984,"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": 1625852548169.959, "dur": 34934.445, + "args": { + "External id": 3723985,"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": 1625852548183.799, "dur": 34911.986, + "args": { + "External id": 3723986,"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": 1625852548224.291, "dur": 19.428, + "args": { + "External id": 3723987,"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": 1625852548249.894, "dur": 34804.507, + "args": { + "External id": 3723988,"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": 1625852548252.537, "dur": 34801.215, + "args": { + "External id": 3723989,"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": 1625852548257.078, "dur": 4.708, + "args": { + "External id": 3723990,"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": 1625852548263.637, "dur": 34786.513, + "args": { + "External id": 3723991,"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": 1625852583190.182, "dur": 8.689, + "args": { + "External id": 3723992,"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": 1625852583193.538, "dur": 4.998, + "args": { + "External id": 3723993,"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": 1625852583228.282, "dur": 365.767, + "args": { + "External id": 3723994,"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": 1625852583254.050, "dur": 335.015, + "args": { + "External id": 3723995,"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": 1625852583264.507, "dur": 318.227, + "args": { + "External id": 3723996,"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": 1625852583613.710, "dur": 2.789, + "args": { + "External id": 3723997,"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": 1625852583674.510, "dur": 19.903, + "args": { + "External id": 3723998,"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": 1625852583744.938, "dur": 1.612, + "args": { + "External id": 3723999,"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": 1625852583763.510, "dur": 1.392, + "args": { + "External id": 3724000,"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": 1625852583781.204, "dur": 1.025, + "args": { + "External id": 3724001,"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": 1625852583793.775, "dur": 1.006, + "args": { + "External id": 3724002,"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": 1625852583805.486, "dur": 0.990, + "args": { + "External id": 3724003,"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": 1625852583818.664, "dur": 0.939, + "args": { + "External id": 3724004,"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": 1625852583833.867, "dur": 2.139, + "args": { + "External id": 3724005,"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": 1625852583847.311, "dur": 1.171, + "args": { + "External id": 3724006,"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": 1625852583947.534, "dur": 2711.388, + "args": { + "External id": 3724007,"Record function id": 0, "Ev Idx": 3814 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.12)", "pid": 1336756, "tid": 1381189, + "ts": 1625852583967.201, "dur": 1007.590, + "args": { + "External id": 3724008,"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": 1625852583981.133, "dur": 357.818, + "args": { + "External id": 3724009,"Record function id": 0, "Ev Idx": 3816 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1625852584099.886, "dur": 4.673, + "args": { + "External id": 3724010,"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": 1625852584107.732, "dur": 1.468, + "args": { + "External id": 3724011,"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": 1625852584111.122, "dur": 1.342, + "args": { + "External id": 3724012,"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": 1625852584114.513, "dur": 3.156, + "args": { + "External id": 3724013,"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": 1625852584119.193, "dur": 1.309, + "args": { + "External id": 3724014,"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": 1625852584121.971, "dur": 1.161, + "args": { + "External id": 3724015,"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": 1625852584124.658, "dur": 1.586, + "args": { + "External id": 3724016,"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": 1625852584127.684, "dur": 0.921, + "args": { + "External id": 3724017,"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": 1625852584129.930, "dur": 0.641, + "args": { + "External id": 3724018,"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": 1625852584132.425, "dur": 0.905, + "args": { + "External id": 3724019,"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": 1625852584151.601, "dur": 155.664, + "args": { + "External id": 3724020,"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": 1625852584167.477, "dur": 135.531, + "args": { + "External id": 3724021,"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": 1625852584189.987, "dur": 13.670, + "args": { + "External id": 3724022,"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": 1625852584207.037, "dur": 66.725, + "args": { + "External id": 3724023,"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": 1625852584209.686, "dur": 63.729, + "args": { + "External id": 3724024,"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": 1625852584213.427, "dur": 7.612, + "args": { + "External id": 3724025,"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": 1625852584223.145, "dur": 49.536, + "args": { + "External id": 3724026,"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": 1625852584421.163, "dur": 545.676, + "args": { + "External id": 3724027,"Record function id": 0, "Ev Idx": 3834 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.11)", "pid": 1336756, "tid": 1381189, + "ts": 1625852584436.980, "dur": 517.405, + "args": { + "External id": 3724028,"Record function id": 0, "Ev Idx": 3835 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1625852584493.098, "dur": 4.104, + "args": { + "External id": 3724029,"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": 1625852584512.392, "dur": 29.080, + "args": { + "External id": 3724030,"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": 1625852584518.078, "dur": 1.800, + "args": { + "External id": 3724031,"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": 1625852584521.822, "dur": 0.475, + "args": { + "External id": 3724032,"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": 1625852584523.831, "dur": 0.670, + "args": { + "External id": 3724033,"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": 1625852584525.995, "dur": 0.311, + "args": { + "External id": 3724034,"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": 1625852584527.989, "dur": 0.381, + "args": { + "External id": 3724035,"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": 1625852584529.775, "dur": 0.444, + "args": { + "External id": 3724036,"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": 1625852584531.999, "dur": 2.338, + "args": { + "External id": 3724037,"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": 1625852584535.699, "dur": 0.378, + "args": { + "External id": 3724038,"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": 1625852584537.485, "dur": 0.411, + "args": { + "External id": 3724039,"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": 1625852584551.633, "dur": 31.432, + "args": { + "External id": 3724040,"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": 1625852584614.253, "dur": 120.599, + "args": { + "External id": 3724041,"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": 1625852584623.728, "dur": 3.560, + "args": { + "External id": 3724042,"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": 1625852584632.854, "dur": 10.154, + "args": { + "External id": 3724043,"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": 1625852584637.221, "dur": 5.329, + "args": { + "External id": 3724044,"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": 1625852584641.001, "dur": 0.454, + "args": { + "External id": 3724045,"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": 1625852584649.571, "dur": 24.380, + "args": { + "External id": 3724046,"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": 1625852584651.598, "dur": 0.470, + "args": { + "External id": 3724047,"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": 1625852584653.691, "dur": 0.550, + "args": { + "External id": 3724048,"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": 1625852584656.005, "dur": 0.399, + "args": { + "External id": 3724049,"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": 1625852584657.853, "dur": 2.474, + "args": { + "External id": 3724050,"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": 1625852584662.672, "dur": 0.449, + "args": { + "External id": 3724051,"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": 1625852584664.330, "dur": 0.318, + "args": { + "External id": 3724052,"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": 1625852584666.366, "dur": 0.384, + "args": { + "External id": 3724053,"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": 1625852584668.229, "dur": 0.585, + "args": { + "External id": 3724054,"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": 1625852584670.835, "dur": 0.508, + "args": { + "External id": 3724055,"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": 1625852584703.767, "dur": 23.493, + "args": { + "External id": 3724056,"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": 1625852584780.353, "dur": 108.818, + "args": { + "External id": 3724057,"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": 1625852584802.364, "dur": 83.715, + "args": { + "External id": 3724058,"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": 1625852584812.880, "dur": 69.331, + "args": { + "External id": 3724059,"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": 1625852584902.034, "dur": 1.810, + "args": { + "External id": 3724060,"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": 1625852585021.299, "dur": 1617.331, + "args": { + "External id": 3724061,"Sequence number": 37295098, "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": 1625852585021.299, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1625852585135.229, "dur": 106.699, + "args": { + "External id": 3724062,"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": 1625852585282.445, "dur": 39.892, + "args": { + "External id": 3724063,"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": 1625852585339.541, "dur": 48.879, + "args": { + "External id": 3724064,"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": 1625852585397.298, "dur": 32.230, + "args": { + "External id": 3724065,"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": 1625852585438.650, "dur": 45.751, + "args": { + "External id": 3724066,"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": 1625852585491.958, "dur": 33.342, + "args": { + "External id": 3724067,"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": 1625852585532.773, "dur": 42.138, + "args": { + "External id": 3724068,"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": 1625852585595.645, "dur": 21.925, + "args": { + "External id": 3724069,"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": 1625852585636.288, "dur": 27.408, + "args": { + "External id": 3724070,"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": 1625852585697.541, "dur": 22.932, + "args": { + "External id": 3724071,"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": 1625852585736.003, "dur": 16.180, + "args": { + "External id": 3724072,"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": 1625852585761.649, "dur": 34.482, + "args": { + "External id": 3724073,"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": 1625852585799.882, "dur": 32.769, + "args": { + "External id": 3724074,"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": 1625852585861.651, "dur": 221.054, + "args": { + "External id": 3724075,"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": 1625852585940.730, "dur": 6.138, + "args": { + "External id": 3724076,"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": 1625852585949.097, "dur": 2.433, + "args": { + "External id": 3724077,"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": 1625852586121.875, "dur": 27.552, + "args": { + "External id": 3724078,"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": 1625852586161.248, "dur": 14.870, + "args": { + "External id": 3724079,"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": 1625852586184.865, "dur": 42.114, + "args": { + "External id": 3724080,"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": 1625852586233.812, "dur": 36.231, + "args": { + "External id": 3724081,"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": 1625852586279.278, "dur": 23.016, + "args": { + "External id": 3724082,"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": 1625852586308.200, "dur": 31.070, + "args": { + "External id": 3724083,"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": 1625852586345.345, "dur": 21.775, + "args": { + "External id": 3724084,"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": 1625852586374.271, "dur": 45.332, + "args": { + "External id": 3724085,"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": 1625852586445.476, "dur": 26.524, + "args": { + "External id": 3724086,"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": 1625852586487.951, "dur": 27.346, + "args": { + "External id": 3724087,"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": 1625852586529.344, "dur": 16.961, + "args": { + "External id": 3724088,"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": 1625852586565.110, "dur": 15.616, + "args": { + "External id": 3724089,"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": 1625852586591.675, "dur": 16.420, + "args": { + "External id": 3724090,"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": 1625852586700.412, "dur": 17.793, + "args": { + "External id": 3724091,"Record function id": 0, "Ev Idx": 3898 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852586704.659, "dur": 12.285, + "args": { + "External id": 3724092,"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": 1625852586709.103, "dur": 6.634, + "args": { + "External id": 3724093,"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": 1625852586711.214, "dur": 4.239, + "args": { + "External id": 3724094,"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": 1625852586723.366, "dur": 8.541, + "args": { + "External id": 3724095,"Record function id": 0, "Ev Idx": 3902 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852586724.912, "dur": 6.558, + "args": { + "External id": 3724096,"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": 1625852586726.064, "dur": 1.715, + "args": { + "External id": 3724097,"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": 1625852586726.801, "dur": 0.879, + "args": { + "External id": 3724098,"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": 1625852586735.383, "dur": 7.228, + "args": { + "External id": 3724099,"Record function id": 0, "Ev Idx": 3906 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852586736.665, "dur": 5.529, + "args": { + "External id": 3724100,"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": 1625852586737.659, "dur": 4.064, + "args": { + "External id": 3724101,"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": 1625852586738.143, "dur": 3.515, + "args": { + "External id": 3724102,"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": 1625852586746.017, "dur": 4.659, + "args": { + "External id": 3724103,"Record function id": 0, "Ev Idx": 3910 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852586747.598, "dur": 2.696, + "args": { + "External id": 3724104,"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": 1625852586748.338, "dur": 1.543, + "args": { + "External id": 3724105,"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": 1625852586748.850, "dur": 0.971, + "args": { + "External id": 3724106,"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": 1625852586753.721, "dur": 3.543, + "args": { + "External id": 3724107,"Record function id": 0, "Ev Idx": 3914 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852586755.019, "dur": 1.858, + "args": { + "External id": 3724108,"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": 1625852586755.453, "dur": 1.011, + "args": { + "External id": 3724109,"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": 1625852586755.718, "dur": 0.680, + "args": { + "External id": 3724110,"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": 1625852586760.579, "dur": 3.982, + "args": { + "External id": 3724111,"Record function id": 0, "Ev Idx": 3918 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852586761.718, "dur": 2.402, + "args": { + "External id": 3724112,"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": 1625852586762.458, "dur": 1.253, + "args": { + "External id": 3724113,"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": 1625852586763.075, "dur": 0.528, + "args": { + "External id": 3724114,"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": 1625852586767.717, "dur": 3.450, + "args": { + "External id": 3724115,"Record function id": 0, "Ev Idx": 3922 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852586768.933, "dur": 1.854, + "args": { + "External id": 3724116,"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": 1625852586769.364, "dur": 1.020, + "args": { + "External id": 3724117,"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": 1625852586769.664, "dur": 0.610, + "args": { + "External id": 3724118,"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": 1625852586774.150, "dur": 3.615, + "args": { + "External id": 3724119,"Record function id": 0, "Ev Idx": 3926 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852586775.364, "dur": 2.003, + "args": { + "External id": 3724120,"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": 1625852586776.050, "dur": 0.913, + "args": { + "External id": 3724121,"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": 1625852586776.320, "dur": 0.577, + "args": { + "External id": 3724122,"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": 1625852586780.740, "dur": 30.351, + "args": { + "External id": 3724123,"Record function id": 0, "Ev Idx": 3930 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852586781.764, "dur": 28.844, + "args": { + "External id": 3724124,"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": 1625852586782.320, "dur": 27.743, + "args": { + "External id": 3724125,"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": 1625852586809.215, "dur": 0.738, + "args": { + "External id": 3724126,"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": 1625852586815.230, "dur": 36796.928, + "args": { + "External id": 3724127,"Record function id": 0, "Sequence number": 37295097, "Fwd thread id": 1, "Ev Idx": 3934 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1625852586816.747, "dur": 36787.278, + "args": { + "External id": 3724128,"Sequence number": 37295097, "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": 1625852586816.747, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.12)", "pid": 1336756, "tid": 1381189, + "ts": 1625852586852.111, "dur": 38.240, + "args": { + "External id": 3724129,"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": 1625852586898.075, "dur": 63.586, + "args": { + "External id": 3724130,"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": 1625852586967.345, "dur": 36628.572, + "args": { + "External id": 3724131,"Record function id": 0, "Ev Idx": 3938 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1625852587090.937, "dur": 7.160, + "args": { + "External id": 3724132,"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": 1625852587108.773, "dur": 6.657, + "args": { + "External id": 3724133,"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": 1625852587135.919, "dur": 35590.618, + "args": { + "External id": 3724134,"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": 1625852587150.726, "dur": 35565.687, + "args": { + "External id": 3724135,"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": 1625852587192.340, "dur": 13.793, + "args": { + "External id": 3724136,"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": 1625852587212.215, "dur": 35451.304, + "args": { + "External id": 3724137,"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": 1625852587215.130, "dur": 35447.854, + "args": { + "External id": 3724138,"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": 1625852587219.488, "dur": 5.039, + "args": { + "External id": 3724139,"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": 1625852587226.327, "dur": 35432.988, + "args": { + "External id": 3724140,"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": 1625852622814.160, "dur": 9.500, + "args": { + "External id": 3724141,"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": 1625852622817.749, "dur": 5.635, + "args": { + "External id": 3724142,"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": 1625852622855.522, "dur": 428.219, + "args": { + "External id": 3724143,"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": 1625852622881.755, "dur": 396.363, + "args": { + "External id": 3724144,"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": 1625852622893.025, "dur": 379.044, + "args": { + "External id": 3724145,"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": 1625852623309.748, "dur": 2.711, + "args": { + "External id": 3724146,"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": 1625852623374.456, "dur": 6.301, + "args": { + "External id": 3724147,"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": 1625852623432.357, "dur": 1.432, + "args": { + "External id": 3724148,"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": 1625852623451.098, "dur": 3.267, + "args": { + "External id": 3724149,"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": 1625852623466.973, "dur": 0.940, + "args": { + "External id": 3724150,"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": 1625852623479.447, "dur": 1.065, + "args": { + "External id": 3724151,"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": 1625852623491.872, "dur": 1.308, + "args": { + "External id": 3724152,"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": 1625852623505.109, "dur": 2.683, + "args": { + "External id": 3724153,"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": 1625852623520.957, "dur": 1.674, + "args": { + "External id": 3724154,"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": 1625852623534.782, "dur": 0.670, + "args": { + "External id": 3724155,"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": 1625852623625.605, "dur": 2817.922, + "args": { + "External id": 3724156,"Record function id": 0, "Ev Idx": 3963 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.11)", "pid": 1336756, "tid": 1381189, + "ts": 1625852623644.836, "dur": 1057.791, + "args": { + "External id": 3724157,"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": 1625852623660.589, "dur": 382.960, + "args": { + "External id": 3724158,"Record function id": 0, "Ev Idx": 3965 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1625852623764.231, "dur": 4.969, + "args": { + "External id": 3724159,"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": 1625852623772.667, "dur": 1.223, + "args": { + "External id": 3724160,"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": 1625852623775.876, "dur": 2.795, + "args": { + "External id": 3724161,"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": 1625852623780.293, "dur": 1.109, + "args": { + "External id": 3724162,"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": 1625852623782.919, "dur": 1.120, + "args": { + "External id": 3724163,"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": 1625852623785.704, "dur": 0.943, + "args": { + "External id": 3724164,"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": 1625852623788.036, "dur": 1.669, + "args": { + "External id": 3724165,"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": 1625852623791.362, "dur": 1.077, + "args": { + "External id": 3724166,"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": 1625852623794.091, "dur": 0.912, + "args": { + "External id": 3724167,"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": 1625852623796.557, "dur": 0.791, + "args": { + "External id": 3724168,"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": 1625852623815.817, "dur": 153.698, + "args": { + "External id": 3724169,"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": 1625852623832.267, "dur": 133.037, + "args": { + "External id": 3724170,"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": 1625852623851.710, "dur": 13.808, + "args": { + "External id": 3724171,"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": 1625852623868.989, "dur": 67.122, + "args": { + "External id": 3724172,"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": 1625852623871.869, "dur": 63.940, + "args": { + "External id": 3724173,"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": 1625852623876.151, "dur": 5.520, + "args": { + "External id": 3724174,"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": 1625852623883.728, "dur": 51.287, + "args": { + "External id": 3724175,"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": 1625852624140.507, "dur": 533.554, + "args": { + "External id": 3724176,"Record function id": 0, "Ev Idx": 3983 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.10)", "pid": 1336756, "tid": 1381189, + "ts": 1625852624158.853, "dur": 502.739, + "args": { + "External id": 3724177,"Record function id": 0, "Ev Idx": 3984 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1625852624221.314, "dur": 5.943, + "args": { + "External id": 3724178,"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": 1625852624242.555, "dur": 29.756, + "args": { + "External id": 3724179,"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": 1625852624247.469, "dur": 1.623, + "args": { + "External id": 3724180,"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": 1625852624251.348, "dur": 0.424, + "args": { + "External id": 3724181,"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": 1625852624253.279, "dur": 0.734, + "args": { + "External id": 3724182,"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": 1625852624256.135, "dur": 0.462, + "args": { + "External id": 3724183,"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": 1625852624258.361, "dur": 0.410, + "args": { + "External id": 3724184,"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": 1625852624260.540, "dur": 2.379, + "args": { + "External id": 3724185,"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": 1625852624264.803, "dur": 0.406, + "args": { + "External id": 3724186,"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": 1625852624266.619, "dur": 0.352, + "args": { + "External id": 3724187,"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": 1625852624268.533, "dur": 0.344, + "args": { + "External id": 3724188,"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": 1625852624282.464, "dur": 39.238, + "args": { + "External id": 3724189,"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": 1625852624350.967, "dur": 101.809, + "args": { + "External id": 3724190,"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": 1625852624361.010, "dur": 3.082, + "args": { + "External id": 3724191,"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": 1625852624369.474, "dur": 13.156, + "args": { + "External id": 3724192,"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": 1625852624376.808, "dur": 5.377, + "args": { + "External id": 3724193,"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": 1625852624380.630, "dur": 0.519, + "args": { + "External id": 3724194,"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": 1625852624389.575, "dur": 25.445, + "args": { + "External id": 3724195,"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": 1625852624391.894, "dur": 0.678, + "args": { + "External id": 3724196,"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": 1625852624394.445, "dur": 0.333, + "args": { + "External id": 3724197,"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": 1625852624396.472, "dur": 2.132, + "args": { + "External id": 3724198,"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": 1625852624400.294, "dur": 0.450, + "args": { + "External id": 3724199,"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": 1625852624402.485, "dur": 0.373, + "args": { + "External id": 3724200,"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": 1625852624404.596, "dur": 0.399, + "args": { + "External id": 3724201,"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": 1625852624406.803, "dur": 0.434, + "args": { + "External id": 3724202,"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": 1625852624408.936, "dur": 0.464, + "args": { + "External id": 3724203,"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": 1625852624410.924, "dur": 0.379, + "args": { + "External id": 3724204,"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": 1625852624425.142, "dur": 21.181, + "args": { + "External id": 3724205,"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": 1625852624495.949, "dur": 105.879, + "args": { + "External id": 3724206,"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": 1625852624517.419, "dur": 80.956, + "args": { + "External id": 3724207,"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": 1625852624527.170, "dur": 67.058, + "args": { + "External id": 3724208,"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": 1625852624614.937, "dur": 1.769, + "args": { + "External id": 3724209,"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": 1625852624711.022, "dur": 1713.965, + "args": { + "External id": 3724210,"Sequence number": 37295096, "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": 1625852624711.022, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1625852624822.926, "dur": 104.834, + "args": { + "External id": 3724211,"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": 1625852624965.836, "dur": 82.696, + "args": { + "External id": 3724212,"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": 1625852625069.268, "dur": 58.034, + "args": { + "External id": 3724213,"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": 1625852625139.752, "dur": 34.728, + "args": { + "External id": 3724214,"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": 1625852625181.203, "dur": 46.853, + "args": { + "External id": 3724215,"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": 1625852625236.593, "dur": 30.766, + "args": { + "External id": 3724216,"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": 1625852625275.144, "dur": 43.221, + "args": { + "External id": 3724217,"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": 1625852625344.321, "dur": 24.328, + "args": { + "External id": 3724218,"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": 1625852625389.115, "dur": 29.268, + "args": { + "External id": 3724219,"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": 1625852625439.664, "dur": 19.995, + "args": { + "External id": 3724220,"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": 1625852625471.979, "dur": 16.912, + "args": { + "External id": 3724221,"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": 1625852625497.952, "dur": 30.060, + "args": { + "External id": 3724222,"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": 1625852625531.650, "dur": 33.484, + "args": { + "External id": 3724223,"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": 1625852625597.252, "dur": 203.687, + "args": { + "External id": 3724224,"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": 1625852625696.221, "dur": 7.238, + "args": { + "External id": 3724225,"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": 1625852625705.870, "dur": 5.331, + "args": { + "External id": 3724226,"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": 1625852625839.505, "dur": 27.035, + "args": { + "External id": 3724227,"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": 1625852625877.798, "dur": 18.944, + "args": { + "External id": 3724228,"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": 1625852625905.309, "dur": 43.471, + "args": { + "External id": 3724229,"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": 1625852625955.981, "dur": 73.514, + "args": { + "External id": 3724230,"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": 1625852626042.477, "dur": 41.544, + "args": { + "External id": 3724231,"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": 1625852626098.363, "dur": 38.413, + "args": { + "External id": 3724232,"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": 1625852626145.316, "dur": 26.937, + "args": { + "External id": 3724233,"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": 1625852626180.454, "dur": 33.370, + "args": { + "External id": 3724234,"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": 1625852626235.966, "dur": 25.231, + "args": { + "External id": 3724235,"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": 1625852626281.692, "dur": 24.769, + "args": { + "External id": 3724236,"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": 1625852626321.007, "dur": 18.146, + "args": { + "External id": 3724237,"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": 1625852626352.592, "dur": 15.885, + "args": { + "External id": 3724238,"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": 1625852626380.423, "dur": 16.378, + "args": { + "External id": 3724239,"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": 1625852626464.858, "dur": 14.582, + "args": { + "External id": 3724240,"Record function id": 0, "Ev Idx": 4047 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852626468.049, "dur": 10.604, + "args": { + "External id": 3724241,"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": 1625852626472.158, "dur": 5.591, + "args": { + "External id": 3724242,"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": 1625852626473.844, "dur": 3.782, + "args": { + "External id": 3724243,"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": 1625852626483.272, "dur": 7.707, + "args": { + "External id": 3724244,"Record function id": 0, "Ev Idx": 4051 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852626484.907, "dur": 5.610, + "args": { + "External id": 3724245,"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": 1625852626485.691, "dur": 4.336, + "args": { + "External id": 3724246,"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": 1625852626486.626, "dur": 3.285, + "args": { + "External id": 3724247,"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": 1625852626494.049, "dur": 4.575, + "args": { + "External id": 3724248,"Record function id": 0, "Ev Idx": 4055 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852626495.508, "dur": 2.699, + "args": { + "External id": 3724249,"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": 1625852626496.211, "dur": 1.555, + "args": { + "External id": 3724250,"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": 1625852626496.762, "dur": 0.942, + "args": { + "External id": 3724251,"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": 1625852626501.818, "dur": 4.469, + "args": { + "External id": 3724252,"Record function id": 0, "Ev Idx": 4059 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852626503.276, "dur": 2.610, + "args": { + "External id": 3724253,"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": 1625852626504.158, "dur": 1.341, + "args": { + "External id": 3724254,"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": 1625852626504.675, "dur": 0.761, + "args": { + "External id": 3724255,"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": 1625852626509.336, "dur": 3.901, + "args": { + "External id": 3724256,"Record function id": 0, "Ev Idx": 4063 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852626510.425, "dur": 2.413, + "args": { + "External id": 3724257,"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": 1625852626510.950, "dur": 1.446, + "args": { + "External id": 3724258,"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": 1625852626511.731, "dur": 0.599, + "args": { + "External id": 3724259,"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": 1625852626516.321, "dur": 3.764, + "args": { + "External id": 3724260,"Record function id": 0, "Ev Idx": 4067 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852626517.430, "dur": 2.222, + "args": { + "External id": 3724261,"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": 1625852626518.087, "dur": 1.166, + "args": { + "External id": 3724262,"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": 1625852626518.526, "dur": 0.634, + "args": { + "External id": 3724263,"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": 1625852626523.282, "dur": 3.454, + "args": { + "External id": 3724264,"Record function id": 0, "Ev Idx": 4071 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852626524.293, "dur": 2.043, + "args": { + "External id": 3724265,"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": 1625852626524.745, "dur": 1.220, + "args": { + "External id": 3724266,"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": 1625852626525.214, "dur": 0.628, + "args": { + "External id": 3724267,"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": 1625852626529.736, "dur": 3.534, + "args": { + "External id": 3724268,"Record function id": 0, "Ev Idx": 4075 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852626530.683, "dur": 2.158, + "args": { + "External id": 3724269,"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": 1625852626531.185, "dur": 1.292, + "args": { + "External id": 3724270,"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": 1625852626531.694, "dur": 0.716, + "args": { + "External id": 3724271,"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": 1625852626536.267, "dur": 5.614, + "args": { + "External id": 3724272,"Record function id": 0, "Ev Idx": 4079 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852626537.424, "dur": 4.047, + "args": { + "External id": 3724273,"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": 1625852626537.901, "dur": 3.196, + "args": { + "External id": 3724274,"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": 1625852626538.591, "dur": 2.425, + "args": { + "External id": 3724275,"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": 1625852626545.483, "dur": 35520.310, + "args": { + "External id": 3724276,"Record function id": 0, "Sequence number": 37295095, "Fwd thread id": 1, "Ev Idx": 4083 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1625852626546.940, "dur": 35509.483, + "args": { + "External id": 3724277,"Sequence number": 37295095, "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": 1625852626546.940, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.11)", "pid": 1336756, "tid": 1381189, + "ts": 1625852626574.270, "dur": 36.776, + "args": { + "External id": 3724278,"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": 1625852626618.833, "dur": 75.963, + "args": { + "External id": 3724279,"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": 1625852626703.285, "dur": 35343.967, + "args": { + "External id": 3724280,"Record function id": 0, "Ev Idx": 4087 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1625852626791.240, "dur": 6.402, + "args": { + "External id": 3724281,"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": 1625852626807.349, "dur": 5.047, + "args": { + "External id": 3724282,"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": 1625852626827.195, "dur": 34364.773, + "args": { + "External id": 3724283,"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": 1625852626841.255, "dur": 34341.460, + "args": { + "External id": 3724284,"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": 1625852626903.887, "dur": 14.128, + "args": { + "External id": 3724285,"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": 1625852626924.278, "dur": 34218.086, + "args": { + "External id": 3724286,"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": 1625852626927.304, "dur": 34214.053, + "args": { + "External id": 3724287,"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": 1625852626931.289, "dur": 5.300, + "args": { + "External id": 3724288,"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": 1625852626959.959, "dur": 34177.324, + "args": { + "External id": 3724289,"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": 1625852661281.128, "dur": 9.223, + "args": { + "External id": 3724290,"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": 1625852661284.454, "dur": 5.564, + "args": { + "External id": 3724291,"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": 1625852661322.302, "dur": 390.601, + "args": { + "External id": 3724292,"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": 1625852661348.988, "dur": 358.522, + "args": { + "External id": 3724293,"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": 1625852661360.098, "dur": 341.470, + "args": { + "External id": 3724294,"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": 1625852661735.059, "dur": 2.341, + "args": { + "External id": 3724295,"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": 1625852661797.477, "dur": 6.685, + "args": { + "External id": 3724296,"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": 1625852661849.994, "dur": 3.431, + "args": { + "External id": 3724297,"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": 1625852661870.208, "dur": 0.885, + "args": { + "External id": 3724298,"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": 1625852661883.541, "dur": 0.752, + "args": { + "External id": 3724299,"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": 1625852661896.086, "dur": 0.913, + "args": { + "External id": 3724300,"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": 1625852661908.410, "dur": 2.916, + "args": { + "External id": 3724301,"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": 1625852661927.164, "dur": 1.108, + "args": { + "External id": 3724302,"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": 1625852661940.540, "dur": 2.017, + "args": { + "External id": 3724303,"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": 1625852661953.059, "dur": 0.922, + "args": { + "External id": 3724304,"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": 1625852662082.202, "dur": 2797.439, + "args": { + "External id": 3724305,"Record function id": 0, "Ev Idx": 4112 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.10)", "pid": 1336756, "tid": 1381189, + "ts": 1625852662104.792, "dur": 1061.240, + "args": { + "External id": 3724306,"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": 1625852662121.787, "dur": 325.051, + "args": { + "External id": 3724307,"Record function id": 0, "Ev Idx": 4114 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1625852662210.673, "dur": 7.171, + "args": { + "External id": 3724308,"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": 1625852662221.229, "dur": 1.211, + "args": { + "External id": 3724309,"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": 1625852662224.720, "dur": 1.242, + "args": { + "External id": 3724310,"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": 1625852662227.390, "dur": 0.940, + "args": { + "External id": 3724311,"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": 1625852662229.715, "dur": 1.268, + "args": { + "External id": 3724312,"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": 1625852662232.468, "dur": 0.912, + "args": { + "External id": 3724313,"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": 1625852662234.829, "dur": 1.118, + "args": { + "External id": 3724314,"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": 1625852662237.280, "dur": 1.450, + "args": { + "External id": 3724315,"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": 1625852662240.040, "dur": 3.841, + "args": { + "External id": 3724316,"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": 1625852662245.161, "dur": 1.375, + "args": { + "External id": 3724317,"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": 1625852662265.471, "dur": 149.632, + "args": { + "External id": 3724318,"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": 1625852662281.341, "dur": 129.432, + "args": { + "External id": 3724319,"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": 1625852662300.483, "dur": 13.316, + "args": { + "External id": 3724320,"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": 1625852662317.091, "dur": 64.903, + "args": { + "External id": 3724321,"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": 1625852662319.726, "dur": 61.979, + "args": { + "External id": 3724322,"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": 1625852662324.293, "dur": 5.153, + "args": { + "External id": 3724323,"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": 1625852662331.470, "dur": 49.611, + "args": { + "External id": 3724324,"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": 1625852662529.427, "dur": 628.324, + "args": { + "External id": 3724325,"Record function id": 0, "Ev Idx": 4132 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.9)", "pid": 1336756, "tid": 1381189, + "ts": 1625852662546.540, "dur": 598.906, + "args": { + "External id": 3724326,"Record function id": 0, "Ev Idx": 4133 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1625852662604.067, "dur": 4.402, + "args": { + "External id": 3724327,"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": 1625852662622.773, "dur": 35.416, + "args": { + "External id": 3724328,"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": 1625852662627.796, "dur": 1.190, + "args": { + "External id": 3724329,"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": 1625852662631.066, "dur": 0.549, + "args": { + "External id": 3724330,"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": 1625852662633.115, "dur": 0.578, + "args": { + "External id": 3724331,"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": 1625852662635.866, "dur": 2.626, + "args": { + "External id": 3724332,"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": 1625852662639.868, "dur": 0.598, + "args": { + "External id": 3724333,"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": 1625852662642.021, "dur": 0.353, + "args": { + "External id": 3724334,"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": 1625852662649.074, "dur": 0.780, + "args": { + "External id": 3724335,"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": 1625852662651.292, "dur": 0.344, + "args": { + "External id": 3724336,"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": 1625852662653.324, "dur": 0.661, + "args": { + "External id": 3724337,"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": 1625852662668.893, "dur": 51.005, + "args": { + "External id": 3724338,"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": 1625852662753.742, "dur": 116.027, + "args": { + "External id": 3724339,"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": 1625852662764.966, "dur": 3.751, + "args": { + "External id": 3724340,"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": 1625852662773.921, "dur": 11.471, + "args": { + "External id": 3724341,"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": 1625852662777.948, "dur": 6.974, + "args": { + "External id": 3724342,"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": 1625852662781.527, "dur": 1.454, + "args": { + "External id": 3724343,"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": 1625852662795.287, "dur": 30.456, + "args": { + "External id": 3724344,"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": 1625852662797.798, "dur": 2.448, + "args": { + "External id": 3724345,"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": 1625852662801.893, "dur": 0.493, + "args": { + "External id": 3724346,"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": 1625852662804.084, "dur": 0.973, + "args": { + "External id": 3724347,"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": 1625852662806.519, "dur": 0.557, + "args": { + "External id": 3724348,"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": 1625852662808.371, "dur": 0.362, + "args": { + "External id": 3724349,"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": 1625852662810.277, "dur": 0.350, + "args": { + "External id": 3724350,"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": 1625852662812.085, "dur": 0.359, + "args": { + "External id": 3724351,"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": 1625852662814.119, "dur": 0.367, + "args": { + "External id": 3724352,"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": 1625852662815.896, "dur": 2.219, + "args": { + "External id": 3724353,"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": 1625852662837.021, "dur": 24.856, + "args": { + "External id": 3724354,"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": 1625852662917.882, "dur": 154.717, + "args": { + "External id": 3724355,"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": 1625852662938.114, "dur": 130.633, + "args": { + "External id": 3724356,"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": 1625852662947.767, "dur": 116.309, + "args": { + "External id": 3724357,"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": 1625852663090.698, "dur": 2.123, + "args": { + "External id": 3724358,"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": 1625852663173.747, "dur": 1681.935, + "args": { + "External id": 3724359,"Sequence number": 37295094, "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": 1625852663173.747, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1625852663285.276, "dur": 104.504, + "args": { + "External id": 3724360,"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": 1625852663426.296, "dur": 42.699, + "args": { + "External id": 3724361,"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": 1625852663489.108, "dur": 52.179, + "args": { + "External id": 3724362,"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": 1625852663550.664, "dur": 37.151, + "args": { + "External id": 3724363,"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": 1625852663594.406, "dur": 45.607, + "args": { + "External id": 3724364,"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": 1625852663648.677, "dur": 47.580, + "args": { + "External id": 3724365,"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": 1625852663710.045, "dur": 47.004, + "args": { + "External id": 3724366,"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": 1625852663780.258, "dur": 24.798, + "args": { + "External id": 3724367,"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": 1625852663835.689, "dur": 30.173, + "args": { + "External id": 3724368,"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": 1625852663886.875, "dur": 19.760, + "args": { + "External id": 3724369,"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": 1625852663920.542, "dur": 16.006, + "args": { + "External id": 3724370,"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": 1625852663946.902, "dur": 31.279, + "args": { + "External id": 3724371,"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": 1625852664018.201, "dur": 41.464, + "args": { + "External id": 3724372,"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": 1625852664091.366, "dur": 184.799, + "args": { + "External id": 3724373,"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": 1625852664176.716, "dur": 6.388, + "args": { + "External id": 3724374,"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": 1625852664185.203, "dur": 2.479, + "args": { + "External id": 3724375,"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": 1625852664310.795, "dur": 26.186, + "args": { + "External id": 3724376,"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": 1625852664347.339, "dur": 14.235, + "args": { + "External id": 3724377,"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": 1625852664370.468, "dur": 39.653, + "args": { + "External id": 3724378,"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": 1625852664418.974, "dur": 39.862, + "args": { + "External id": 3724379,"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": 1625852664465.384, "dur": 23.570, + "args": { + "External id": 3724380,"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": 1625852664494.581, "dur": 47.768, + "args": { + "External id": 3724381,"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": 1625852664554.831, "dur": 25.876, + "args": { + "External id": 3724382,"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": 1625852664591.235, "dur": 30.734, + "args": { + "External id": 3724383,"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": 1625852664641.901, "dur": 23.736, + "args": { + "External id": 3724384,"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": 1625852664701.168, "dur": 26.859, + "args": { + "External id": 3724385,"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": 1625852664747.561, "dur": 18.013, + "args": { + "External id": 3724386,"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": 1625852664780.212, "dur": 16.397, + "args": { + "External id": 3724387,"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": 1625852664812.337, "dur": 16.168, + "args": { + "External id": 3724388,"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": 1625852664901.422, "dur": 20.688, + "args": { + "External id": 3724389,"Record function id": 0, "Ev Idx": 4196 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852664905.020, "dur": 16.246, + "args": { + "External id": 3724390,"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": 1625852664909.213, "dur": 11.162, + "args": { + "External id": 3724391,"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": 1625852664910.862, "dur": 9.404, + "args": { + "External id": 3724392,"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": 1625852664925.831, "dur": 5.860, + "args": { + "External id": 3724393,"Record function id": 0, "Ev Idx": 4200 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852664927.582, "dur": 3.716, + "args": { + "External id": 3724394,"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": 1625852664928.431, "dur": 2.350, + "args": { + "External id": 3724395,"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": 1625852664929.645, "dur": 1.027, + "args": { + "External id": 3724396,"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": 1625852664934.962, "dur": 4.721, + "args": { + "External id": 3724397,"Record function id": 0, "Ev Idx": 4204 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852664936.335, "dur": 2.955, + "args": { + "External id": 3724398,"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": 1625852664937.239, "dur": 1.604, + "args": { + "External id": 3724399,"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": 1625852664937.592, "dur": 1.153, + "args": { + "External id": 3724400,"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": 1625852664942.788, "dur": 3.884, + "args": { + "External id": 3724401,"Record function id": 0, "Ev Idx": 4208 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852664944.023, "dur": 2.251, + "args": { + "External id": 3724402,"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": 1625852664944.687, "dur": 1.180, + "args": { + "External id": 3724403,"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": 1625852664945.009, "dur": 0.784, + "args": { + "External id": 3724404,"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": 1625852664949.765, "dur": 3.962, + "args": { + "External id": 3724405,"Record function id": 0, "Ev Idx": 4212 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852664951.039, "dur": 2.302, + "args": { + "External id": 3724406,"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": 1625852664951.997, "dur": 0.958, + "args": { + "External id": 3724407,"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": 1625852664952.268, "dur": 0.624, + "args": { + "External id": 3724408,"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": 1625852664956.742, "dur": 3.644, + "args": { + "External id": 3724409,"Record function id": 0, "Ev Idx": 4216 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852664957.799, "dur": 2.161, + "args": { + "External id": 3724410,"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": 1625852664958.308, "dur": 1.188, + "args": { + "External id": 3724411,"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": 1625852664958.750, "dur": 0.629, + "args": { + "External id": 3724412,"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": 1625852664963.712, "dur": 3.852, + "args": { + "External id": 3724413,"Record function id": 0, "Ev Idx": 4220 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852664965.012, "dur": 2.151, + "args": { + "External id": 3724414,"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": 1625852664965.470, "dur": 1.273, + "args": { + "External id": 3724415,"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": 1625852664965.977, "dur": 0.684, + "args": { + "External id": 3724416,"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": 1625852664970.605, "dur": 9.337, + "args": { + "External id": 3724417,"Record function id": 0, "Ev Idx": 4224 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852664972.118, "dur": 7.418, + "args": { + "External id": 3724418,"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": 1625852664972.760, "dur": 6.375, + "args": { + "External id": 3724419,"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": 1625852664973.048, "dur": 6.008, + "args": { + "External id": 3724420,"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": 1625852665019.310, "dur": 6.913, + "args": { + "External id": 3724421,"Record function id": 0, "Ev Idx": 4228 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852665020.971, "dur": 4.615, + "args": { + "External id": 3724422,"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": 1625852665022.024, "dur": 2.728, + "args": { + "External id": 3724423,"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": 1625852665022.925, "dur": 1.617, + "args": { + "External id": 3724424,"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": 1625852665030.027, "dur": 35318.297, + "args": { + "External id": 3724425,"Record function id": 0, "Sequence number": 37295093, "Fwd thread id": 1, "Ev Idx": 4232 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1625852665031.192, "dur": 35309.055, + "args": { + "External id": 3724426,"Sequence number": 37295093, "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": 1625852665031.192, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.10)", "pid": 1336756, "tid": 1381189, + "ts": 1625852665064.942, "dur": 40.288, + "args": { + "External id": 3724427,"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": 1625852665112.946, "dur": 67.531, + "args": { + "External id": 3724428,"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": 1625852665186.556, "dur": 35145.834, + "args": { + "External id": 3724429,"Record function id": 0, "Ev Idx": 4236 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1625852665277.246, "dur": 6.996, + "args": { + "External id": 3724430,"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": 1625852665293.968, "dur": 4.856, + "args": { + "External id": 3724431,"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": 1625852665313.435, "dur": 34204.935, + "args": { + "External id": 3724432,"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": 1625852665327.575, "dur": 34181.774, + "args": { + "External id": 3724433,"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": 1625852665387.014, "dur": 13.762, + "args": { + "External id": 3724434,"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": 1625852665407.039, "dur": 34061.892, + "args": { + "External id": 3724435,"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": 1625852665409.653, "dur": 34058.633, + "args": { + "External id": 3724436,"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": 1625852665413.597, "dur": 5.258, + "args": { + "External id": 3724437,"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": 1625852665420.702, "dur": 34043.447, + "args": { + "External id": 3724438,"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": 1625852699608.503, "dur": 8.886, + "args": { + "External id": 3724439,"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": 1625852699611.675, "dur": 5.380, + "args": { + "External id": 3724440,"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": 1625852699650.780, "dur": 385.321, + "args": { + "External id": 3724441,"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": 1625852699676.131, "dur": 354.343, + "args": { + "External id": 3724442,"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": 1625852699698.162, "dur": 326.104, + "args": { + "External id": 3724443,"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": 1625852700058.023, "dur": 2.553, + "args": { + "External id": 3724444,"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": 1625852700122.151, "dur": 6.294, + "args": { + "External id": 3724445,"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": 1625852700176.516, "dur": 1.262, + "args": { + "External id": 3724446,"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": 1625852700193.801, "dur": 1.076, + "args": { + "External id": 3724447,"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": 1625852700207.243, "dur": 0.971, + "args": { + "External id": 3724448,"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": 1625852700219.679, "dur": 0.757, + "args": { + "External id": 3724449,"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": 1625852700232.264, "dur": 0.907, + "args": { + "External id": 3724450,"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": 1625852700244.353, "dur": 0.818, + "args": { + "External id": 3724451,"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": 1625852700255.782, "dur": 1.712, + "args": { + "External id": 3724452,"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": 1625852700267.489, "dur": 1.348, + "args": { + "External id": 3724453,"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": 1625852700362.617, "dur": 2819.506, + "args": { + "External id": 3724454,"Record function id": 0, "Ev Idx": 4261 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.9)", "pid": 1336756, "tid": 1381189, + "ts": 1625852700381.852, "dur": 1031.553, + "args": { + "External id": 3724455,"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": 1625852700397.008, "dur": 338.799, + "args": { + "External id": 3724456,"Record function id": 0, "Ev Idx": 4263 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1625852700475.523, "dur": 3.953, + "args": { + "External id": 3724457,"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": 1625852700482.473, "dur": 1.469, + "args": { + "External id": 3724458,"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": 1625852700485.687, "dur": 1.586, + "args": { + "External id": 3724459,"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": 1625852700488.874, "dur": 1.216, + "args": { + "External id": 3724460,"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": 1625852700491.547, "dur": 1.879, + "args": { + "External id": 3724461,"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": 1625852700494.857, "dur": 1.395, + "args": { + "External id": 3724462,"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": 1625852700497.464, "dur": 1.063, + "args": { + "External id": 3724463,"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": 1625852700499.702, "dur": 3.016, + "args": { + "External id": 3724464,"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": 1625852700504.075, "dur": 0.801, + "args": { + "External id": 3724465,"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": 1625852700506.137, "dur": 1.300, + "args": { + "External id": 3724466,"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": 1625852700525.249, "dur": 172.788, + "args": { + "External id": 3724467,"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": 1625852700541.003, "dur": 133.383, + "args": { + "External id": 3724468,"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": 1625852700563.513, "dur": 13.099, + "args": { + "External id": 3724469,"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": 1625852700579.852, "dur": 65.913, + "args": { + "External id": 3724470,"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": 1625852700582.326, "dur": 63.120, + "args": { + "External id": 3724471,"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": 1625852700586.379, "dur": 5.565, + "args": { + "External id": 3724472,"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": 1625852700595.357, "dur": 49.458, + "args": { + "External id": 3724473,"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": 1625852700822.578, "dur": 582.861, + "args": { + "External id": 3724474,"Record function id": 0, "Ev Idx": 4281 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.8)", "pid": 1336756, "tid": 1381189, + "ts": 1625852700839.536, "dur": 552.354, + "args": { + "External id": 3724475,"Record function id": 0, "Ev Idx": 4282 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1625852700897.264, "dur": 5.377, + "args": { + "External id": 3724476,"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": 1625852700917.567, "dur": 33.172, + "args": { + "External id": 3724477,"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": 1625852700922.795, "dur": 1.762, + "args": { + "External id": 3724478,"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": 1625852700926.981, "dur": 0.663, + "args": { + "External id": 3724479,"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": 1625852700929.457, "dur": 2.331, + "args": { + "External id": 3724480,"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": 1625852700933.582, "dur": 0.441, + "args": { + "External id": 3724481,"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": 1625852700935.393, "dur": 0.335, + "args": { + "External id": 3724482,"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": 1625852700937.691, "dur": 0.427, + "args": { + "External id": 3724483,"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": 1625852700939.416, "dur": 0.372, + "args": { + "External id": 3724484,"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": 1625852700941.888, "dur": 0.366, + "args": { + "External id": 3724485,"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": 1625852700943.762, "dur": 0.365, + "args": { + "External id": 3724486,"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": 1625852700960.412, "dur": 73.911, + "args": { + "External id": 3724487,"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": 1625852701068.531, "dur": 108.385, + "args": { + "External id": 3724488,"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": 1625852701082.667, "dur": 3.784, + "args": { + "External id": 3724489,"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": 1625852701091.825, "dur": 12.795, + "args": { + "External id": 3724490,"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": 1625852701096.226, "dur": 7.974, + "args": { + "External id": 3724491,"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": 1625852701099.947, "dur": 2.340, + "args": { + "External id": 3724492,"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": 1625852701112.006, "dur": 25.566, + "args": { + "External id": 3724493,"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": 1625852701114.333, "dur": 0.467, + "args": { + "External id": 3724494,"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": 1625852701116.738, "dur": 0.399, + "args": { + "External id": 3724495,"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": 1625852701118.547, "dur": 0.636, + "args": { + "External id": 3724496,"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": 1625852701120.986, "dur": 0.414, + "args": { + "External id": 3724497,"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": 1625852701122.900, "dur": 0.362, + "args": { + "External id": 3724498,"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": 1625852701124.725, "dur": 0.422, + "args": { + "External id": 3724499,"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": 1625852701126.616, "dur": 0.627, + "args": { + "External id": 3724500,"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": 1625852701128.856, "dur": 2.681, + "args": { + "External id": 3724501,"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": 1625852701132.945, "dur": 0.349, + "args": { + "External id": 3724502,"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": 1625852701147.004, "dur": 22.626, + "args": { + "External id": 3724503,"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": 1625852701224.375, "dur": 106.259, + "args": { + "External id": 3724504,"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": 1625852701244.584, "dur": 82.711, + "args": { + "External id": 3724505,"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": 1625852701254.252, "dur": 68.543, + "args": { + "External id": 3724506,"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": 1625852701342.880, "dur": 1.498, + "args": { + "External id": 3724507,"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": 1625852701420.583, "dur": 1741.953, + "args": { + "External id": 3724508,"Sequence number": 37295092, "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": 1625852701420.583, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1625852701525.700, "dur": 109.010, + "args": { + "External id": 3724509,"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": 1625852701669.727, "dur": 64.386, + "args": { + "External id": 3724510,"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": 1625852701757.882, "dur": 57.343, + "args": { + "External id": 3724511,"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": 1625852701825.123, "dur": 35.424, + "args": { + "External id": 3724512,"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": 1625852701867.031, "dur": 47.240, + "args": { + "External id": 3724513,"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": 1625852701922.033, "dur": 29.708, + "args": { + "External id": 3724514,"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": 1625852701960.981, "dur": 78.399, + "args": { + "External id": 3724515,"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": 1625852702068.152, "dur": 25.738, + "args": { + "External id": 3724516,"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": 1625852702111.376, "dur": 29.338, + "args": { + "External id": 3724517,"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": 1625852702159.048, "dur": 19.803, + "args": { + "External id": 3724518,"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": 1625852702195.445, "dur": 17.086, + "args": { + "External id": 3724519,"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": 1625852702224.123, "dur": 37.590, + "args": { + "External id": 3724520,"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": 1625852702265.361, "dur": 35.166, + "args": { + "External id": 3724521,"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": 1625852702330.709, "dur": 172.102, + "args": { + "External id": 3724522,"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": 1625852702411.112, "dur": 5.723, + "args": { + "External id": 3724523,"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": 1625852702418.891, "dur": 2.031, + "args": { + "External id": 3724524,"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": 1625852702535.531, "dur": 28.114, + "args": { + "External id": 3724525,"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": 1625852702575.497, "dur": 15.245, + "args": { + "External id": 3724526,"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": 1625852702601.515, "dur": 35.941, + "args": { + "External id": 3724527,"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": 1625852702644.793, "dur": 53.441, + "args": { + "External id": 3724528,"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": 1625852702708.242, "dur": 27.435, + "args": { + "External id": 3724529,"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": 1625852702759.328, "dur": 33.820, + "args": { + "External id": 3724530,"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": 1625852702802.366, "dur": 28.313, + "args": { + "External id": 3724531,"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": 1625852702853.158, "dur": 43.315, + "args": { + "External id": 3724532,"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": 1625852702916.331, "dur": 25.634, + "args": { + "External id": 3724533,"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": 1625852702958.718, "dur": 62.910, + "args": { + "External id": 3724534,"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": 1625852703046.815, "dur": 19.688, + "args": { + "External id": 3724535,"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": 1625852703083.299, "dur": 17.135, + "args": { + "External id": 3724536,"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": 1625852703112.766, "dur": 16.718, + "args": { + "External id": 3724537,"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": 1625852703208.139, "dur": 15.887, + "args": { + "External id": 3724538,"Record function id": 0, "Ev Idx": 4345 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852703211.556, "dur": 11.523, + "args": { + "External id": 3724539,"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": 1625852703215.782, "dur": 6.296, + "args": { + "External id": 3724540,"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": 1625852703217.819, "dur": 4.132, + "args": { + "External id": 3724541,"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": 1625852703227.923, "dur": 5.292, + "args": { + "External id": 3724542,"Record function id": 0, "Ev Idx": 4349 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852703229.428, "dur": 3.335, + "args": { + "External id": 3724543,"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": 1625852703230.160, "dur": 1.967, + "args": { + "External id": 3724544,"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": 1625852703230.870, "dur": 1.120, + "args": { + "External id": 3724545,"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": 1625852703236.593, "dur": 4.132, + "args": { + "External id": 3724546,"Record function id": 0, "Ev Idx": 4353 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852703237.803, "dur": 2.514, + "args": { + "External id": 3724547,"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": 1625852703238.290, "dur": 1.547, + "args": { + "External id": 3724548,"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": 1625852703238.650, "dur": 1.120, + "args": { + "External id": 3724549,"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": 1625852703243.811, "dur": 4.669, + "args": { + "External id": 3724550,"Record function id": 0, "Ev Idx": 4357 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852703245.253, "dur": 2.803, + "args": { + "External id": 3724551,"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": 1625852703246.057, "dur": 1.581, + "args": { + "External id": 3724552,"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": 1625852703246.722, "dur": 0.856, + "args": { + "External id": 3724553,"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": 1625852703251.505, "dur": 6.797, + "args": { + "External id": 3724554,"Record function id": 0, "Ev Idx": 4361 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852703252.799, "dur": 1.935, + "args": { + "External id": 3724555,"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": 1625852703253.307, "dur": 0.998, + "args": { + "External id": 3724556,"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": 1625852703253.577, "dur": 0.665, + "args": { + "External id": 3724557,"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": 1625852703261.362, "dur": 3.732, + "args": { + "External id": 3724558,"Record function id": 0, "Ev Idx": 4365 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852703262.329, "dur": 2.334, + "args": { + "External id": 3724559,"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": 1625852703262.933, "dur": 1.296, + "args": { + "External id": 3724560,"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": 1625852703263.489, "dur": 0.610, + "args": { + "External id": 3724561,"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": 1625852703268.271, "dur": 5.893, + "args": { + "External id": 3724562,"Record function id": 0, "Ev Idx": 4369 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852703269.412, "dur": 4.366, + "args": { + "External id": 3724563,"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": 1625852703270.155, "dur": 3.211, + "args": { + "External id": 3724564,"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": 1625852703270.452, "dur": 2.809, + "args": { + "External id": 3724565,"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": 1625852703277.156, "dur": 3.807, + "args": { + "External id": 3724566,"Record function id": 0, "Ev Idx": 4373 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852703278.153, "dur": 2.376, + "args": { + "External id": 3724567,"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": 1625852703278.637, "dur": 1.453, + "args": { + "External id": 3724568,"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": 1625852703279.044, "dur": 0.962, + "args": { + "External id": 3724569,"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": 1625852703283.891, "dur": 4.352, + "args": { + "External id": 3724570,"Record function id": 0, "Ev Idx": 4377 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852703284.933, "dur": 2.924, + "args": { + "External id": 3724571,"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": 1625852703285.519, "dur": 1.854, + "args": { + "External id": 3724572,"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": 1625852703286.542, "dur": 0.744, + "args": { + "External id": 3724573,"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": 1625852703291.536, "dur": 38192.810, + "args": { + "External id": 3724574,"Record function id": 0, "Sequence number": 37295091, "Fwd thread id": 1, "Ev Idx": 4381 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1625852703292.853, "dur": 38183.365, + "args": { + "External id": 3724575,"Sequence number": 37295091, "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": 1625852703292.853, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.9)", "pid": 1336756, "tid": 1381189, + "ts": 1625852703321.739, "dur": 38.533, + "args": { + "External id": 3724576,"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": 1625852703368.572, "dur": 63.710, + "args": { + "External id": 3724577,"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": 1625852703438.396, "dur": 38030.416, + "args": { + "External id": 3724578,"Record function id": 0, "Ev Idx": 4385 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1625852703529.490, "dur": 6.312, + "args": { + "External id": 3724579,"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": 1625852703545.473, "dur": 5.343, + "args": { + "External id": 3724580,"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": 1625852703564.632, "dur": 37039.772, + "args": { + "External id": 3724581,"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": 1625852703577.333, "dur": 37017.375, + "args": { + "External id": 3724582,"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": 1625852703625.949, "dur": 14.027, + "args": { + "External id": 3724583,"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": 1625852703646.407, "dur": 36905.415, + "args": { + "External id": 3724584,"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": 1625852703648.972, "dur": 36901.909, + "args": { + "External id": 3724585,"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": 1625852703653.047, "dur": 4.622, + "args": { + "External id": 3724586,"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": 1625852703659.866, "dur": 36886.886, + "args": { + "External id": 3724587,"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": 1625852740703.499, "dur": 9.878, + "args": { + "External id": 3724588,"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": 1625852740706.917, "dur": 5.854, + "args": { + "External id": 3724589,"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": 1625852740745.919, "dur": 424.588, + "args": { + "External id": 3724590,"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": 1625852740772.275, "dur": 392.909, + "args": { + "External id": 3724591,"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": 1625852740783.866, "dur": 374.693, + "args": { + "External id": 3724592,"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": 1625852741192.222, "dur": 2.626, + "args": { + "External id": 3724593,"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": 1625852741257.780, "dur": 9.312, + "args": { + "External id": 3724594,"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": 1625852741313.419, "dur": 1.299, + "args": { + "External id": 3724595,"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": 1625852741330.496, "dur": 1.183, + "args": { + "External id": 3724596,"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": 1625852741344.827, "dur": 1.098, + "args": { + "External id": 3724597,"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": 1625852741358.445, "dur": 3.209, + "args": { + "External id": 3724598,"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": 1625852741372.908, "dur": 1.451, + "args": { + "External id": 3724599,"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": 1625852741385.121, "dur": 1.072, + "args": { + "External id": 3724600,"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": 1625852741397.354, "dur": 0.739, + "args": { + "External id": 3724601,"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": 1625852741407.710, "dur": 2.621, + "args": { + "External id": 3724602,"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": 1625852741497.441, "dur": 2772.337, + "args": { + "External id": 3724603,"Record function id": 0, "Ev Idx": 4410 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.8)", "pid": 1336756, "tid": 1381189, + "ts": 1625852741516.165, "dur": 1017.222, + "args": { + "External id": 3724604,"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": 1625852741531.345, "dur": 328.368, + "args": { + "External id": 3724605,"Record function id": 0, "Ev Idx": 4412 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1625852741609.573, "dur": 3.856, + "args": { + "External id": 3724606,"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": 1625852741616.273, "dur": 1.056, + "args": { + "External id": 3724607,"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": 1625852741618.910, "dur": 1.225, + "args": { + "External id": 3724608,"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": 1625852741622.303, "dur": 1.268, + "args": { + "External id": 3724609,"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": 1625852741624.941, "dur": 1.187, + "args": { + "External id": 3724610,"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": 1625852741627.943, "dur": 1.330, + "args": { + "External id": 3724611,"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": 1625852741630.825, "dur": 3.031, + "args": { + "External id": 3724612,"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": 1625852741636.042, "dur": 1.084, + "args": { + "External id": 3724613,"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": 1625852741640.621, "dur": 0.886, + "args": { + "External id": 3724614,"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": 1625852741642.867, "dur": 0.949, + "args": { + "External id": 3724615,"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": 1625852741661.538, "dur": 166.748, + "args": { + "External id": 3724616,"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": 1625852741693.284, "dur": 130.239, + "args": { + "External id": 3724617,"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": 1625852741712.639, "dur": 12.262, + "args": { + "External id": 3724618,"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": 1625852741728.135, "dur": 65.865, + "args": { + "External id": 3724619,"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": 1625852741730.776, "dur": 62.861, + "args": { + "External id": 3724620,"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": 1625852741734.779, "dur": 5.480, + "args": { + "External id": 3724621,"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": 1625852741743.875, "dur": 49.241, + "args": { + "External id": 3724622,"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": 1625852741941.762, "dur": 583.607, + "args": { + "External id": 3724623,"Record function id": 0, "Ev Idx": 4430 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.7)", "pid": 1336756, "tid": 1381189, + "ts": 1625852741958.326, "dur": 554.848, + "args": { + "External id": 3724624,"Record function id": 0, "Ev Idx": 4431 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1625852742059.220, "dur": 5.934, + "args": { + "External id": 3724625,"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": 1625852742080.259, "dur": 32.821, + "args": { + "External id": 3724626,"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": 1625852742088.984, "dur": 1.527, + "args": { + "External id": 3724627,"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": 1625852742091.987, "dur": 2.395, + "args": { + "External id": 3724628,"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": 1625852742096.045, "dur": 0.607, + "args": { + "External id": 3724629,"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": 1625852742098.057, "dur": 0.545, + "args": { + "External id": 3724630,"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": 1625852742100.151, "dur": 0.605, + "args": { + "External id": 3724631,"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": 1625852742102.540, "dur": 0.704, + "args": { + "External id": 3724632,"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": 1625852742104.521, "dur": 0.504, + "args": { + "External id": 3724633,"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": 1625852742106.552, "dur": 0.425, + "args": { + "External id": 3724634,"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": 1625852742108.814, "dur": 0.522, + "args": { + "External id": 3724635,"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": 1625852742124.190, "dur": 34.491, + "args": { + "External id": 3724636,"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": 1625852742190.713, "dur": 99.776, + "args": { + "External id": 3724637,"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": 1625852742200.812, "dur": 4.817, + "args": { + "External id": 3724638,"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": 1625852742210.377, "dur": 10.112, + "args": { + "External id": 3724639,"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": 1625852742214.452, "dur": 5.594, + "args": { + "External id": 3724640,"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": 1625852742218.399, "dur": 0.550, + "args": { + "External id": 3724641,"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": 1625852742226.811, "dur": 24.067, + "args": { + "External id": 3724642,"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": 1625852742228.823, "dur": 0.497, + "args": { + "External id": 3724643,"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": 1625852742230.662, "dur": 0.562, + "args": { + "External id": 3724644,"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": 1625852742232.607, "dur": 0.599, + "args": { + "External id": 3724645,"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": 1625852742234.696, "dur": 0.611, + "args": { + "External id": 3724646,"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": 1625852742236.659, "dur": 0.545, + "args": { + "External id": 3724647,"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": 1625852742238.372, "dur": 0.645, + "args": { + "External id": 3724648,"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": 1625852742240.496, "dur": 2.367, + "args": { + "External id": 3724649,"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": 1625852742244.397, "dur": 0.507, + "args": { + "External id": 3724650,"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": 1625852742246.303, "dur": 0.470, + "args": { + "External id": 3724651,"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": 1625852742263.779, "dur": 19.860, + "args": { + "External id": 3724652,"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": 1625852742333.050, "dur": 111.457, + "args": { + "External id": 3724653,"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": 1625852742361.516, "dur": 79.851, + "args": { + "External id": 3724654,"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": 1625852742371.176, "dur": 66.342, + "args": { + "External id": 3724655,"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": 1625852742463.719, "dur": 2.006, + "args": { + "External id": 3724656,"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": 1625852742540.986, "dur": 1709.605, + "args": { + "External id": 3724657,"Sequence number": 37295090, "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": 1625852742540.986, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1625852742653.710, "dur": 123.530, + "args": { + "External id": 3724658,"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": 1625852742824.331, "dur": 41.248, + "args": { + "External id": 3724659,"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": 1625852742885.512, "dur": 50.047, + "args": { + "External id": 3724660,"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": 1625852742944.981, "dur": 32.227, + "args": { + "External id": 3724661,"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": 1625852743022.906, "dur": 55.421, + "args": { + "External id": 3724662,"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": 1625852743089.304, "dur": 28.375, + "args": { + "External id": 3724663,"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": 1625852743128.390, "dur": 41.161, + "args": { + "External id": 3724664,"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": 1625852743196.441, "dur": 26.606, + "args": { + "External id": 3724665,"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": 1625852743241.215, "dur": 31.191, + "args": { + "External id": 3724666,"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": 1625852743295.155, "dur": 23.330, + "args": { + "External id": 3724667,"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": 1625852743333.334, "dur": 17.247, + "args": { + "External id": 3724668,"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": 1625852743360.501, "dur": 29.667, + "args": { + "External id": 3724669,"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": 1625852743392.929, "dur": 32.634, + "args": { + "External id": 3724670,"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": 1625852743457.744, "dur": 173.533, + "args": { + "External id": 3724671,"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": 1625852743539.405, "dur": 5.837, + "args": { + "External id": 3724672,"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": 1625852743547.549, "dur": 3.557, + "args": { + "External id": 3724673,"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": 1625852743663.364, "dur": 41.787, + "args": { + "External id": 3724674,"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": 1625852743720.779, "dur": 15.668, + "args": { + "External id": 3724675,"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": 1625852743746.232, "dur": 49.079, + "args": { + "External id": 3724676,"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": 1625852743801.655, "dur": 34.776, + "args": { + "External id": 3724677,"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": 1625852743842.843, "dur": 22.365, + "args": { + "External id": 3724678,"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": 1625852743872.214, "dur": 30.927, + "args": { + "External id": 3724679,"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": 1625852743909.462, "dur": 22.547, + "args": { + "External id": 3724680,"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": 1625852743939.769, "dur": 29.881, + "args": { + "External id": 3724681,"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": 1625852744038.425, "dur": 34.832, + "args": { + "External id": 3724682,"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": 1625852744093.065, "dur": 24.736, + "args": { + "External id": 3724683,"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": 1625852744135.981, "dur": 18.262, + "args": { + "External id": 3724684,"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": 1625852744171.652, "dur": 19.228, + "args": { + "External id": 3724685,"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": 1625852744204.892, "dur": 16.452, + "args": { + "External id": 3724686,"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": 1625852744292.145, "dur": 15.525, + "args": { + "External id": 3724687,"Record function id": 0, "Ev Idx": 4494 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852744295.646, "dur": 11.089, + "args": { + "External id": 3724688,"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": 1625852744300.265, "dur": 5.653, + "args": { + "External id": 3724689,"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": 1625852744301.874, "dur": 3.924, + "args": { + "External id": 3724690,"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": 1625852744311.469, "dur": 5.805, + "args": { + "External id": 3724691,"Record function id": 0, "Ev Idx": 4498 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852744312.906, "dur": 3.889, + "args": { + "External id": 3724692,"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": 1625852744313.867, "dur": 2.390, + "args": { + "External id": 3724693,"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": 1625852744314.887, "dur": 1.288, + "args": { + "External id": 3724694,"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": 1625852744320.549, "dur": 4.704, + "args": { + "External id": 3724695,"Record function id": 0, "Ev Idx": 4502 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852744321.878, "dur": 2.961, + "args": { + "External id": 3724696,"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": 1625852744322.873, "dur": 1.541, + "args": { + "External id": 3724697,"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": 1625852744323.302, "dur": 1.049, + "args": { + "External id": 3724698,"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": 1625852744328.628, "dur": 4.662, + "args": { + "External id": 3724699,"Record function id": 0, "Ev Idx": 4506 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852744329.988, "dur": 2.892, + "args": { + "External id": 3724700,"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": 1625852744330.841, "dur": 1.648, + "args": { + "External id": 3724701,"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": 1625852744331.586, "dur": 0.838, + "args": { + "External id": 3724702,"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": 1625852744336.451, "dur": 6.252, + "args": { + "External id": 3724703,"Record function id": 0, "Ev Idx": 4510 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852744337.708, "dur": 4.582, + "args": { + "External id": 3724704,"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": 1625852744338.490, "dur": 3.416, + "args": { + "External id": 3724705,"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": 1625852744338.782, "dur": 3.028, + "args": { + "External id": 3724706,"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": 1625852744345.714, "dur": 3.869, + "args": { + "External id": 3724707,"Record function id": 0, "Ev Idx": 4514 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852744346.794, "dur": 2.320, + "args": { + "External id": 3724708,"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": 1625852744347.250, "dur": 1.396, + "args": { + "External id": 3724709,"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": 1625852744347.690, "dur": 0.846, + "args": { + "External id": 3724710,"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": 1625852744352.770, "dur": 3.566, + "args": { + "External id": 3724711,"Record function id": 0, "Ev Idx": 4518 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852744354.063, "dur": 1.874, + "args": { + "External id": 3724712,"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": 1625852744354.552, "dur": 0.981, + "args": { + "External id": 3724713,"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": 1625852744354.820, "dur": 0.649, + "args": { + "External id": 3724714,"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": 1625852744359.283, "dur": 4.015, + "args": { + "External id": 3724715,"Record function id": 0, "Ev Idx": 4522 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852744360.468, "dur": 2.414, + "args": { + "External id": 3724716,"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": 1625852744361.082, "dur": 1.388, + "args": { + "External id": 3724717,"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": 1625852744361.523, "dur": 0.855, + "args": { + "External id": 3724718,"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": 1625852744366.262, "dur": 3.757, + "args": { + "External id": 3724719,"Record function id": 0, "Ev Idx": 4526 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852744367.310, "dur": 2.298, + "args": { + "External id": 3724720,"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": 1625852744367.939, "dur": 1.290, + "args": { + "External id": 3724721,"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": 1625852744368.481, "dur": 0.636, + "args": { + "External id": 3724722,"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": 1625852744373.506, "dur": 35709.242, + "args": { + "External id": 3724723,"Record function id": 0, "Sequence number": 37295089, "Fwd thread id": 1, "Ev Idx": 4530 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1625852744375.011, "dur": 35698.792, + "args": { + "External id": 3724724,"Sequence number": 37295089, "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": 1625852744375.011, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.8)", "pid": 1336756, "tid": 1381189, + "ts": 1625852744403.503, "dur": 37.127, + "args": { + "External id": 3724725,"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": 1625852744448.778, "dur": 61.591, + "args": { + "External id": 3724726,"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": 1625852744515.556, "dur": 35549.437, + "args": { + "External id": 3724727,"Record function id": 0, "Ev Idx": 4534 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1625852744600.004, "dur": 6.029, + "args": { + "External id": 3724728,"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": 1625852744615.175, "dur": 4.645, + "args": { + "External id": 3724729,"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": 1625852744633.994, "dur": 34580.628, + "args": { + "External id": 3724730,"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": 1625852744647.291, "dur": 34557.785, + "args": { + "External id": 3724731,"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": 1625852744716.287, "dur": 14.931, + "args": { + "External id": 3724732,"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": 1625852744740.957, "dur": 34425.442, + "args": { + "External id": 3724733,"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": 1625852744743.576, "dur": 34422.005, + "args": { + "External id": 3724734,"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": 1625852744747.496, "dur": 8.901, + "args": { + "External id": 3724735,"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": 1625852744758.033, "dur": 34403.894, + "args": { + "External id": 3724736,"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": 1625852779302.217, "dur": 10.480, + "args": { + "External id": 3724737,"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": 1625852779305.163, "dur": 7.165, + "args": { + "External id": 3724738,"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": 1625852779343.105, "dur": 374.416, + "args": { + "External id": 3724739,"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": 1625852779371.162, "dur": 341.086, + "args": { + "External id": 3724740,"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": 1625852779381.843, "dur": 323.875, + "args": { + "External id": 3724741,"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": 1625852779741.748, "dur": 2.929, + "args": { + "External id": 3724742,"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": 1625852779802.447, "dur": 6.672, + "args": { + "External id": 3724743,"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": 1625852779853.916, "dur": 1.888, + "args": { + "External id": 3724744,"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": 1625852779870.506, "dur": 1.241, + "args": { + "External id": 3724745,"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": 1625852779882.751, "dur": 2.752, + "args": { + "External id": 3724746,"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": 1625852779905.015, "dur": 1.333, + "args": { + "External id": 3724747,"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": 1625852779916.424, "dur": 0.949, + "args": { + "External id": 3724748,"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": 1625852779928.007, "dur": 0.862, + "args": { + "External id": 3724749,"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": 1625852779939.893, "dur": 2.485, + "args": { + "External id": 3724750,"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": 1625852779954.506, "dur": 0.881, + "args": { + "External id": 3724751,"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": 1625852780099.123, "dur": 2757.116, + "args": { + "External id": 3724752,"Record function id": 0, "Ev Idx": 4559 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.7)", "pid": 1336756, "tid": 1381189, + "ts": 1625852780118.357, "dur": 1042.477, + "args": { + "External id": 3724753,"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": 1625852780132.624, "dur": 308.309, + "args": { + "External id": 3724754,"Record function id": 0, "Ev Idx": 4561 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1625852780213.876, "dur": 4.797, + "args": { + "External id": 3724755,"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": 1625852780221.620, "dur": 1.162, + "args": { + "External id": 3724756,"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": 1625852780226.168, "dur": 1.353, + "args": { + "External id": 3724757,"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": 1625852780229.141, "dur": 0.939, + "args": { + "External id": 3724758,"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": 1625852780231.872, "dur": 0.934, + "args": { + "External id": 3724759,"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": 1625852780234.146, "dur": 2.536, + "args": { + "External id": 3724760,"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": 1625852780239.406, "dur": 1.032, + "args": { + "External id": 3724761,"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": 1625852780241.853, "dur": 0.917, + "args": { + "External id": 3724762,"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": 1625852780244.546, "dur": 1.039, + "args": { + "External id": 3724763,"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": 1625852780246.795, "dur": 0.802, + "args": { + "External id": 3724764,"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": 1625852780266.424, "dur": 146.299, + "args": { + "External id": 3724765,"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": 1625852780282.738, "dur": 125.765, + "args": { + "External id": 3724766,"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": 1625852780298.894, "dur": 12.930, + "args": { + "External id": 3724767,"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": 1625852780314.622, "dur": 65.695, + "args": { + "External id": 3724768,"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": 1625852780317.178, "dur": 62.855, + "args": { + "External id": 3724769,"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": 1625852780321.375, "dur": 6.018, + "args": { + "External id": 3724770,"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": 1625852780328.949, "dur": 50.513, + "args": { + "External id": 3724771,"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": 1625852780520.808, "dur": 632.066, + "args": { + "External id": 3724772,"Record function id": 0, "Ev Idx": 4579 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.6)", "pid": 1336756, "tid": 1381189, + "ts": 1625852780535.921, "dur": 604.255, + "args": { + "External id": 3724773,"Record function id": 0, "Ev Idx": 4580 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1625852780590.453, "dur": 4.748, + "args": { + "External id": 3724774,"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": 1625852780614.064, "dur": 31.818, + "args": { + "External id": 3724775,"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": 1625852780619.139, "dur": 4.030, + "args": { + "External id": 3724776,"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": 1625852780625.159, "dur": 0.573, + "args": { + "External id": 3724777,"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": 1625852780627.336, "dur": 0.348, + "args": { + "External id": 3724778,"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": 1625852780630.142, "dur": 0.353, + "args": { + "External id": 3724779,"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": 1625852780631.803, "dur": 0.594, + "args": { + "External id": 3724780,"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": 1625852780633.942, "dur": 0.561, + "args": { + "External id": 3724781,"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": 1625852780636.498, "dur": 0.744, + "args": { + "External id": 3724782,"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": 1625852780638.629, "dur": 0.389, + "args": { + "External id": 3724783,"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": 1625852780640.484, "dur": 3.005, + "args": { + "External id": 3724784,"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": 1625852780656.183, "dur": 49.052, + "args": { + "External id": 3724785,"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": 1625852780737.707, "dur": 129.106, + "args": { + "External id": 3724786,"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": 1625852780748.210, "dur": 4.061, + "args": { + "External id": 3724787,"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": 1625852780757.356, "dur": 10.505, + "args": { + "External id": 3724788,"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": 1625852780761.400, "dur": 6.020, + "args": { + "External id": 3724789,"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": 1625852780765.388, "dur": 0.675, + "args": { + "External id": 3724790,"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": 1625852780774.814, "dur": 28.033, + "args": { + "External id": 3724791,"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": 1625852780776.732, "dur": 0.736, + "args": { + "External id": 3724792,"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": 1625852780779.289, "dur": 0.539, + "args": { + "External id": 3724793,"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": 1625852780781.252, "dur": 0.692, + "args": { + "External id": 3724794,"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": 1625852780783.492, "dur": 0.415, + "args": { + "External id": 3724795,"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": 1625852780785.141, "dur": 0.500, + "args": { + "External id": 3724796,"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": 1625852780787.838, "dur": 1.804, + "args": { + "External id": 3724797,"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": 1625852780791.300, "dur": 0.652, + "args": { + "External id": 3724798,"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": 1625852780793.494, "dur": 0.577, + "args": { + "External id": 3724799,"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": 1625852780795.632, "dur": 0.545, + "args": { + "External id": 3724800,"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": 1625852780835.135, "dur": 24.370, + "args": { + "External id": 3724801,"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": 1625852780912.376, "dur": 153.793, + "args": { + "External id": 3724802,"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": 1625852780940.005, "dur": 122.038, + "args": { + "External id": 3724803,"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": 1625852780949.078, "dur": 107.834, + "args": { + "External id": 3724804,"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": 1625852781085.277, "dur": 2.130, + "args": { + "External id": 3724805,"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": 1625852781168.708, "dur": 1665.404, + "args": { + "External id": 3724806,"Sequence number": 37295088, "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": 1625852781168.708, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1625852781277.920, "dur": 103.490, + "args": { + "External id": 3724807,"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": 1625852781426.011, "dur": 39.999, + "args": { + "External id": 3724808,"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": 1625852781483.146, "dur": 52.160, + "args": { + "External id": 3724809,"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": 1625852781544.282, "dur": 32.347, + "args": { + "External id": 3724810,"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": 1625852781587.635, "dur": 49.305, + "args": { + "External id": 3724811,"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": 1625852781645.707, "dur": 28.130, + "args": { + "External id": 3724812,"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": 1625852781704.027, "dur": 46.964, + "args": { + "External id": 3724813,"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": 1625852781777.364, "dur": 24.122, + "args": { + "External id": 3724814,"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": 1625852781820.258, "dur": 31.247, + "args": { + "External id": 3724815,"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": 1625852781872.186, "dur": 20.994, + "args": { + "External id": 3724816,"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": 1625852781912.534, "dur": 15.906, + "args": { + "External id": 3724817,"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": 1625852781937.402, "dur": 29.826, + "args": { + "External id": 3724818,"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": 1625852781970.312, "dur": 68.585, + "args": { + "External id": 3724819,"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": 1625852782071.729, "dur": 172.165, + "args": { + "External id": 3724820,"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": 1625852782151.230, "dur": 7.899, + "args": { + "External id": 3724821,"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": 1625852782160.893, "dur": 2.278, + "args": { + "External id": 3724822,"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": 1625852782282.401, "dur": 27.540, + "args": { + "External id": 3724823,"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": 1625852782325.023, "dur": 17.023, + "args": { + "External id": 3724824,"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": 1625852782350.097, "dur": 43.602, + "args": { + "External id": 3724825,"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": 1625852782399.764, "dur": 34.911, + "args": { + "External id": 3724826,"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": 1625852782440.897, "dur": 22.059, + "args": { + "External id": 3724827,"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": 1625852782468.966, "dur": 29.145, + "args": { + "External id": 3724828,"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": 1625852782503.484, "dur": 35.031, + "args": { + "External id": 3724829,"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": 1625852782552.628, "dur": 36.358, + "args": { + "External id": 3724830,"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": 1625852782610.656, "dur": 24.281, + "args": { + "External id": 3724831,"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": 1625852782653.115, "dur": 42.154, + "args": { + "External id": 3724832,"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": 1625852782719.721, "dur": 19.584, + "args": { + "External id": 3724833,"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": 1625852782756.476, "dur": 18.737, + "args": { + "External id": 3724834,"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": 1625852782788.636, "dur": 17.701, + "args": { + "External id": 3724835,"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": 1625852782877.838, "dur": 14.373, + "args": { + "External id": 3724836,"Record function id": 0, "Ev Idx": 4643 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852782880.938, "dur": 10.493, + "args": { + "External id": 3724837,"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": 1625852782885.390, "dur": 5.088, + "args": { + "External id": 3724838,"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": 1625852782886.667, "dur": 3.716, + "args": { + "External id": 3724839,"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": 1625852782896.004, "dur": 4.342, + "args": { + "External id": 3724840,"Record function id": 0, "Ev Idx": 4647 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852782897.371, "dur": 2.564, + "args": { + "External id": 3724841,"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": 1625852782898.052, "dur": 1.369, + "args": { + "External id": 3724842,"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": 1625852782898.467, "dur": 0.852, + "args": { + "External id": 3724843,"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": 1625852782903.686, "dur": 4.570, + "args": { + "External id": 3724844,"Record function id": 0, "Ev Idx": 4651 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852782904.934, "dur": 2.879, + "args": { + "External id": 3724845,"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": 1625852782905.662, "dur": 1.735, + "args": { + "External id": 3724846,"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": 1625852782906.569, "dur": 0.735, + "args": { + "External id": 3724847,"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": 1625852782911.424, "dur": 3.814, + "args": { + "External id": 3724848,"Record function id": 0, "Ev Idx": 4655 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852782912.821, "dur": 2.017, + "args": { + "External id": 3724849,"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": 1625852782913.441, "dur": 0.969, + "args": { + "External id": 3724850,"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": 1625852782913.744, "dur": 0.581, + "args": { + "External id": 3724851,"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": 1625852782918.310, "dur": 5.937, + "args": { + "External id": 3724852,"Record function id": 0, "Ev Idx": 4659 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852782919.578, "dur": 4.249, + "args": { + "External id": 3724853,"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": 1625852782920.081, "dur": 3.295, + "args": { + "External id": 3724854,"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": 1625852782920.383, "dur": 2.934, + "args": { + "External id": 3724855,"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": 1625852782927.283, "dur": 3.595, + "args": { + "External id": 3724856,"Record function id": 0, "Ev Idx": 4663 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852782928.447, "dur": 2.015, + "args": { + "External id": 3724857,"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": 1625852782928.878, "dur": 1.150, + "args": { + "External id": 3724858,"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": 1625852782929.253, "dur": 0.701, + "args": { + "External id": 3724859,"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": 1625852782934.074, "dur": 3.544, + "args": { + "External id": 3724860,"Record function id": 0, "Ev Idx": 4667 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852782934.987, "dur": 2.225, + "args": { + "External id": 3724861,"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": 1625852782935.674, "dur": 1.160, + "args": { + "External id": 3724862,"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": 1625852782935.931, "dur": 0.826, + "args": { + "External id": 3724863,"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": 1625852782940.700, "dur": 5.070, + "args": { + "External id": 3724864,"Record function id": 0, "Ev Idx": 4671 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852782941.810, "dur": 3.545, + "args": { + "External id": 3724865,"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": 1625852782942.248, "dur": 2.703, + "args": { + "External id": 3724866,"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": 1625852782944.122, "dur": 0.762, + "args": { + "External id": 3724867,"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": 1625852782948.853, "dur": 3.809, + "args": { + "External id": 3724868,"Record function id": 0, "Ev Idx": 4675 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852782950.033, "dur": 2.229, + "args": { + "External id": 3724869,"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": 1625852782950.521, "dur": 1.319, + "args": { + "External id": 3724870,"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": 1625852782950.986, "dur": 0.787, + "args": { + "External id": 3724871,"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": 1625852782956.074, "dur": 35843.199, + "args": { + "External id": 3724872,"Record function id": 0, "Sequence number": 37295087, "Fwd thread id": 1, "Ev Idx": 4679 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1625852782957.642, "dur": 35833.648, + "args": { + "External id": 3724873,"Sequence number": 37295087, "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": 1625852782957.642, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.7)", "pid": 1336756, "tid": 1381189, + "ts": 1625852783020.450, "dur": 39.793, + "args": { + "External id": 3724874,"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": 1625852783068.490, "dur": 62.101, + "args": { + "External id": 3724875,"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": 1625852783136.132, "dur": 35647.120, + "args": { + "External id": 3724876,"Record function id": 0, "Ev Idx": 4683 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1625852783223.529, "dur": 6.694, + "args": { + "External id": 3724877,"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": 1625852783243.507, "dur": 5.042, + "args": { + "External id": 3724878,"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": 1625852783263.637, "dur": 34695.020, + "args": { + "External id": 3724879,"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": 1625852783277.033, "dur": 34672.240, + "args": { + "External id": 3724880,"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": 1625852783327.776, "dur": 13.983, + "args": { + "External id": 3724881,"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": 1625852783348.117, "dur": 34560.092, + "args": { + "External id": 3724882,"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": 1625852783350.881, "dur": 34556.470, + "args": { + "External id": 3724883,"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": 1625852783354.908, "dur": 6.372, + "args": { + "External id": 3724884,"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": 1625852783363.044, "dur": 34540.341, + "args": { + "External id": 3724885,"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": 1625852818070.019, "dur": 8.336, + "args": { + "External id": 3724886,"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": 1625852818072.765, "dur": 5.081, + "args": { + "External id": 3724887,"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": 1625852818108.128, "dur": 366.384, + "args": { + "External id": 3724888,"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": 1625852818139.343, "dur": 330.137, + "args": { + "External id": 3724889,"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": 1625852818150.050, "dur": 313.522, + "args": { + "External id": 3724890,"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": 1625852818498.108, "dur": 2.233, + "args": { + "External id": 3724891,"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": 1625852818558.554, "dur": 6.621, + "args": { + "External id": 3724892,"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": 1625852818608.160, "dur": 1.655, + "args": { + "External id": 3724893,"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": 1625852818625.170, "dur": 1.432, + "args": { + "External id": 3724894,"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": 1625852818638.670, "dur": 2.806, + "args": { + "External id": 3724895,"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": 1625852818653.667, "dur": 0.996, + "args": { + "External id": 3724896,"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": 1625852818664.586, "dur": 0.897, + "args": { + "External id": 3724897,"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": 1625852818691.941, "dur": 1.975, + "args": { + "External id": 3724898,"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": 1625852818709.092, "dur": 3.402, + "args": { + "External id": 3724899,"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": 1625852818722.626, "dur": 0.920, + "args": { + "External id": 3724900,"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": 1625852818814.463, "dur": 2777.232, + "args": { + "External id": 3724901,"Record function id": 0, "Ev Idx": 4708 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.6)", "pid": 1336756, "tid": 1381189, + "ts": 1625852818832.667, "dur": 1045.341, + "args": { + "External id": 3724902,"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": 1625852818847.506, "dur": 358.743, + "args": { + "External id": 3724903,"Record function id": 0, "Ev Idx": 4710 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1625852818924.766, "dur": 3.908, + "args": { + "External id": 3724904,"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": 1625852818931.713, "dur": 1.015, + "args": { + "External id": 3724905,"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": 1625852818935.591, "dur": 0.953, + "args": { + "External id": 3724906,"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": 1625852818938.171, "dur": 0.821, + "args": { + "External id": 3724907,"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": 1625852818940.680, "dur": 0.930, + "args": { + "External id": 3724908,"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": 1625852818943.222, "dur": 2.646, + "args": { + "External id": 3724909,"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": 1625852818948.607, "dur": 1.100, + "args": { + "External id": 3724910,"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": 1625852818951.013, "dur": 0.718, + "args": { + "External id": 3724911,"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": 1625852818953.422, "dur": 1.084, + "args": { + "External id": 3724912,"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": 1625852818956.372, "dur": 1.406, + "args": { + "External id": 3724913,"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": 1625852818979.755, "dur": 194.299, + "args": { + "External id": 3724914,"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": 1625852819034.088, "dur": 135.062, + "args": { + "External id": 3724915,"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": 1625852819054.080, "dur": 13.750, + "args": { + "External id": 3724916,"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": 1625852819071.040, "dur": 69.747, + "args": { + "External id": 3724917,"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": 1625852819073.582, "dur": 66.894, + "args": { + "External id": 3724918,"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": 1625852819080.236, "dur": 6.527, + "args": { + "External id": 3724919,"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": 1625852819088.507, "dur": 51.448, + "args": { + "External id": 3724920,"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": 1625852819291.628, "dur": 578.578, + "args": { + "External id": 3724921,"Record function id": 0, "Ev Idx": 4728 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.5)", "pid": 1336756, "tid": 1381189, + "ts": 1625852819308.593, "dur": 549.214, + "args": { + "External id": 3724922,"Record function id": 0, "Ev Idx": 4729 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1625852819366.092, "dur": 4.256, + "args": { + "External id": 3724923,"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": 1625852819388.942, "dur": 30.187, + "args": { + "External id": 3724924,"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": 1625852819393.784, "dur": 3.298, + "args": { + "External id": 3724925,"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": 1625852819399.408, "dur": 0.712, + "args": { + "External id": 3724926,"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": 1625852819401.391, "dur": 1.184, + "args": { + "External id": 3724927,"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": 1625852819403.990, "dur": 0.446, + "args": { + "External id": 3724928,"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": 1625852819405.579, "dur": 0.245, + "args": { + "External id": 3724929,"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": 1625852819408.246, "dur": 0.507, + "args": { + "External id": 3724930,"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": 1625852819410.001, "dur": 0.261, + "args": { + "External id": 3724931,"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": 1625852819411.695, "dur": 0.597, + "args": { + "External id": 3724932,"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": 1625852819413.886, "dur": 2.601, + "args": { + "External id": 3724933,"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": 1625852819429.726, "dur": 30.900, + "args": { + "External id": 3724934,"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": 1625852819490.249, "dur": 116.967, + "args": { + "External id": 3724935,"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": 1625852819499.634, "dur": 2.795, + "args": { + "External id": 3724936,"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": 1625852819507.388, "dur": 9.836, + "args": { + "External id": 3724937,"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": 1625852819511.394, "dur": 5.393, + "args": { + "External id": 3724938,"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": 1625852819515.215, "dur": 0.414, + "args": { + "External id": 3724939,"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": 1625852819523.806, "dur": 31.835, + "args": { + "External id": 3724940,"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": 1625852819526.444, "dur": 0.655, + "args": { + "External id": 3724941,"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": 1625852819529.149, "dur": 0.499, + "args": { + "External id": 3724942,"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": 1625852819534.618, "dur": 0.427, + "args": { + "External id": 3724943,"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": 1625852819536.469, "dur": 0.687, + "args": { + "External id": 3724944,"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": 1625852819538.675, "dur": 0.620, + "args": { + "External id": 3724945,"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": 1625852819540.522, "dur": 2.199, + "args": { + "External id": 3724946,"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": 1625852819543.974, "dur": 0.492, + "args": { + "External id": 3724947,"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": 1625852819546.003, "dur": 0.393, + "args": { + "External id": 3724948,"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": 1625852819547.915, "dur": 0.693, + "args": { + "External id": 3724949,"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": 1625852819575.356, "dur": 24.885, + "args": { + "External id": 3724950,"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": 1625852819650.676, "dur": 138.458, + "args": { + "External id": 3724951,"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": 1625852819675.481, "dur": 109.551, + "args": { + "External id": 3724952,"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": 1625852819702.037, "dur": 78.831, + "args": { + "External id": 3724953,"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": 1625852819805.675, "dur": 1.738, + "args": { + "External id": 3724954,"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": 1625852819885.158, "dur": 1685.859, + "args": { + "External id": 3724955,"Sequence number": 37295086, "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": 1625852819885.158, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1625852820033.530, "dur": 107.006, + "args": { + "External id": 3724956,"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": 1625852820183.600, "dur": 43.327, + "args": { + "External id": 3724957,"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": 1625852820243.409, "dur": 48.649, + "args": { + "External id": 3724958,"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": 1625852820301.381, "dur": 32.325, + "args": { + "External id": 3724959,"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": 1625852820339.566, "dur": 45.889, + "args": { + "External id": 3724960,"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": 1625852820394.518, "dur": 28.891, + "args": { + "External id": 3724961,"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": 1625852820431.073, "dur": 41.012, + "args": { + "External id": 3724962,"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": 1625852820494.136, "dur": 24.583, + "args": { + "External id": 3724963,"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": 1625852820538.913, "dur": 28.217, + "args": { + "External id": 3724964,"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": 1625852820588.838, "dur": 19.344, + "args": { + "External id": 3724965,"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": 1625852820625.358, "dur": 18.735, + "args": { + "External id": 3724966,"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": 1625852820651.515, "dur": 48.752, + "args": { + "External id": 3724967,"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": 1625852820705.517, "dur": 37.371, + "args": { + "External id": 3724968,"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": 1625852820781.481, "dur": 174.890, + "args": { + "External id": 3724969,"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": 1625852820863.862, "dur": 8.050, + "args": { + "External id": 3724970,"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": 1625852820873.775, "dur": 2.265, + "args": { + "External id": 3724971,"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": 1625852821029.920, "dur": 30.372, + "args": { + "External id": 3724972,"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": 1625852821073.277, "dur": 14.755, + "args": { + "External id": 3724973,"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": 1625852821097.703, "dur": 45.930, + "args": { + "External id": 3724974,"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": 1625852821149.634, "dur": 35.300, + "args": { + "External id": 3724975,"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": 1625852821191.248, "dur": 26.055, + "args": { + "External id": 3724976,"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": 1625852821223.745, "dur": 47.829, + "args": { + "External id": 3724977,"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": 1625852821284.031, "dur": 30.180, + "args": { + "External id": 3724978,"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": 1625852821320.865, "dur": 29.617, + "args": { + "External id": 3724979,"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": 1625852821373.159, "dur": 23.806, + "args": { + "External id": 3724980,"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": 1625852821418.022, "dur": 29.039, + "args": { + "External id": 3724981,"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": 1625852821461.058, "dur": 20.871, + "args": { + "External id": 3724982,"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": 1625852821498.143, "dur": 14.511, + "args": { + "External id": 3724983,"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": 1625852821526.029, "dur": 16.651, + "args": { + "External id": 3724984,"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": 1625852821613.343, "dur": 14.207, + "args": { + "External id": 3724985,"Record function id": 0, "Ev Idx": 4792 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852821616.390, "dur": 10.281, + "args": { + "External id": 3724986,"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": 1625852821620.590, "dur": 5.238, + "args": { + "External id": 3724987,"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": 1625852821621.963, "dur": 3.779, + "args": { + "External id": 3724988,"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": 1625852821631.442, "dur": 4.415, + "args": { + "External id": 3724989,"Record function id": 0, "Ev Idx": 4796 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852821632.914, "dur": 2.510, + "args": { + "External id": 3724990,"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": 1625852821633.497, "dur": 1.387, + "args": { + "External id": 3724991,"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": 1625852821633.973, "dur": 0.797, + "args": { + "External id": 3724992,"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": 1625852821639.255, "dur": 4.334, + "args": { + "External id": 3724993,"Record function id": 0, "Ev Idx": 4800 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852821640.582, "dur": 2.613, + "args": { + "External id": 3724994,"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": 1625852821641.305, "dur": 1.442, + "args": { + "External id": 3724995,"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": 1625852821641.957, "dur": 0.723, + "args": { + "External id": 3724996,"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": 1625852821646.723, "dur": 3.962, + "args": { + "External id": 3724997,"Record function id": 0, "Ev Idx": 4804 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852821648.302, "dur": 1.938, + "args": { + "External id": 3724998,"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": 1625852821648.802, "dur": 0.985, + "args": { + "External id": 3724999,"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": 1625852821649.115, "dur": 0.607, + "args": { + "External id": 3725000,"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": 1625852821653.715, "dur": 5.822, + "args": { + "External id": 3725001,"Record function id": 0, "Ev Idx": 4808 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852821655.014, "dur": 4.134, + "args": { + "External id": 3725002,"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": 1625852821655.527, "dur": 3.196, + "args": { + "External id": 3725003,"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": 1625852821656.061, "dur": 2.594, + "args": { + "External id": 3725004,"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": 1625852821662.514, "dur": 4.913, + "args": { + "External id": 3725005,"Record function id": 0, "Ev Idx": 4812 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852821663.666, "dur": 3.285, + "args": { + "External id": 3725006,"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": 1625852821664.383, "dur": 2.054, + "args": { + "External id": 3725007,"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": 1625852821665.604, "dur": 0.735, + "args": { + "External id": 3725008,"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": 1625852821670.720, "dur": 3.394, + "args": { + "External id": 3725009,"Record function id": 0, "Ev Idx": 4816 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852821671.796, "dur": 1.928, + "args": { + "External id": 3725010,"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": 1625852821672.288, "dur": 0.934, + "args": { + "External id": 3725011,"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": 1625852821672.542, "dur": 0.613, + "args": { + "External id": 3725012,"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": 1625852821693.764, "dur": 6.822, + "args": { + "External id": 3725013,"Record function id": 0, "Ev Idx": 4820 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852821695.711, "dur": 4.222, + "args": { + "External id": 3725014,"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": 1625852821696.895, "dur": 2.051, + "args": { + "External id": 3725015,"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": 1625852821697.431, "dur": 1.304, + "args": { + "External id": 3725016,"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": 1625852821704.537, "dur": 3.789, + "args": { + "External id": 3725017,"Record function id": 0, "Ev Idx": 4824 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852821705.688, "dur": 2.238, + "args": { + "External id": 3725018,"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": 1625852821706.418, "dur": 1.075, + "args": { + "External id": 3725019,"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": 1625852821706.823, "dur": 0.602, + "args": { + "External id": 3725020,"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": 1625852821711.726, "dur": 36087.919, + "args": { + "External id": 3725021,"Record function id": 0, "Sequence number": 37295085, "Fwd thread id": 1, "Ev Idx": 4828 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1625852821713.571, "dur": 36076.434, + "args": { + "External id": 3725022,"Sequence number": 37295085, "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": 1625852821713.571, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.6)", "pid": 1336756, "tid": 1381189, + "ts": 1625852821743.146, "dur": 39.028, + "args": { + "External id": 3725023,"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": 1625852821789.561, "dur": 64.656, + "args": { + "External id": 3725024,"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": 1625852821859.897, "dur": 35922.070, + "args": { + "External id": 3725025,"Record function id": 0, "Ev Idx": 4832 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1625852821952.771, "dur": 6.716, + "args": { + "External id": 3725026,"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": 1625852821968.760, "dur": 4.600, + "args": { + "External id": 3725027,"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": 1625852822024.775, "dur": 34864.225, + "args": { + "External id": 3725028,"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": 1625852822043.120, "dur": 34837.014, + "args": { + "External id": 3725029,"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": 1625852822084.713, "dur": 18.970, + "args": { + "External id": 3725030,"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": 1625852822109.952, "dur": 34731.847, + "args": { + "External id": 3725031,"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": 1625852822112.448, "dur": 34728.722, + "args": { + "External id": 3725032,"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": 1625852822116.761, "dur": 7.516, + "args": { + "External id": 3725033,"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": 1625852822127.125, "dur": 34710.311, + "args": { + "External id": 3725034,"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": 1625852856976.569, "dur": 43.873, + "args": { + "External id": 3725035,"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": 1625852856979.366, "dur": 40.368, + "args": { + "External id": 3725036,"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": 1625852857051.587, "dur": 412.596, + "args": { + "External id": 3725037,"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": 1625852857080.023, "dur": 379.115, + "args": { + "External id": 3725038,"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": 1625852857090.999, "dur": 362.027, + "args": { + "External id": 3725039,"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": 1625852857487.313, "dur": 2.303, + "args": { + "External id": 3725040,"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": 1625852857550.174, "dur": 6.696, + "args": { + "External id": 3725041,"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": 1625852857603.338, "dur": 1.397, + "args": { + "External id": 3725042,"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": 1625852857620.135, "dur": 1.248, + "args": { + "External id": 3725043,"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": 1625852857633.182, "dur": 2.792, + "args": { + "External id": 3725044,"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": 1625852857648.758, "dur": 0.822, + "args": { + "External id": 3725045,"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": 1625852857660.886, "dur": 0.760, + "args": { + "External id": 3725046,"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": 1625852857674.077, "dur": 0.961, + "args": { + "External id": 3725047,"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": 1625852857705.809, "dur": 4.005, + "args": { + "External id": 3725048,"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": 1625852857720.412, "dur": 0.741, + "args": { + "External id": 3725049,"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": 1625852857814.418, "dur": 2719.443, + "args": { + "External id": 3725050,"Record function id": 0, "Ev Idx": 4857 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.5)", "pid": 1336756, "tid": 1381189, + "ts": 1625852857832.989, "dur": 1012.911, + "args": { + "External id": 3725051,"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": 1625852857846.317, "dur": 345.664, + "args": { + "External id": 3725052,"Record function id": 0, "Ev Idx": 4859 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1625852857926.779, "dur": 4.234, + "args": { + "External id": 3725053,"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": 1625852857934.187, "dur": 1.051, + "args": { + "External id": 3725054,"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": 1625852857938.321, "dur": 0.996, + "args": { + "External id": 3725055,"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": 1625852857941.051, "dur": 0.684, + "args": { + "External id": 3725056,"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": 1625852857943.297, "dur": 0.734, + "args": { + "External id": 3725057,"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": 1625852857945.579, "dur": 2.601, + "args": { + "External id": 3725058,"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": 1625852857951.189, "dur": 0.931, + "args": { + "External id": 3725059,"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": 1625852857953.560, "dur": 0.711, + "args": { + "External id": 3725060,"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": 1625852857955.890, "dur": 1.233, + "args": { + "External id": 3725061,"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": 1625852857958.570, "dur": 1.354, + "args": { + "External id": 3725062,"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": 1625852857979.843, "dur": 182.344, + "args": { + "External id": 3725063,"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": 1625852858030.111, "dur": 127.393, + "args": { + "External id": 3725064,"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": 1625852858049.091, "dur": 12.453, + "args": { + "External id": 3725065,"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": 1625852858064.586, "dur": 64.846, + "args": { + "External id": 3725066,"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": 1625852858066.948, "dur": 62.156, + "args": { + "External id": 3725067,"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": 1625852858071.224, "dur": 6.653, + "args": { + "External id": 3725068,"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": 1625852858079.297, "dur": 49.266, + "args": { + "External id": 3725069,"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": 1625852858284.498, "dur": 554.025, + "args": { + "External id": 3725070,"Record function id": 0, "Ev Idx": 4877 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.4)", "pid": 1336756, "tid": 1381189, + "ts": 1625852858299.785, "dur": 526.781, + "args": { + "External id": 3725071,"Record function id": 0, "Ev Idx": 4878 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1625852858357.169, "dur": 4.339, + "args": { + "External id": 3725072,"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": 1625852858379.769, "dur": 32.459, + "args": { + "External id": 3725073,"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": 1625852858384.708, "dur": 4.053, + "args": { + "External id": 3725074,"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": 1625852858390.785, "dur": 0.514, + "args": { + "External id": 3725075,"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": 1625852858392.710, "dur": 0.594, + "args": { + "External id": 3725076,"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": 1625852858396.681, "dur": 0.581, + "args": { + "External id": 3725077,"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": 1625852858398.507, "dur": 0.339, + "args": { + "External id": 3725078,"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": 1625852858400.326, "dur": 0.368, + "args": { + "External id": 3725079,"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": 1625852858403.169, "dur": 0.449, + "args": { + "External id": 3725080,"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": 1625852858405.066, "dur": 0.359, + "args": { + "External id": 3725081,"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": 1625852858406.686, "dur": 2.772, + "args": { + "External id": 3725082,"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": 1625852858423.750, "dur": 29.625, + "args": { + "External id": 3725083,"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": 1625852858481.820, "dur": 101.003, + "args": { + "External id": 3725084,"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": 1625852858491.648, "dur": 3.023, + "args": { + "External id": 3725085,"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": 1625852858499.888, "dur": 9.801, + "args": { + "External id": 3725086,"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": 1625852858503.704, "dur": 5.566, + "args": { + "External id": 3725087,"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": 1625852858507.502, "dur": 0.634, + "args": { + "External id": 3725088,"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": 1625852858516.137, "dur": 27.475, + "args": { + "External id": 3725089,"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": 1625852858518.393, "dur": 0.438, + "args": { + "External id": 3725090,"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": 1625852858520.959, "dur": 0.443, + "args": { + "External id": 3725091,"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": 1625852858522.612, "dur": 0.652, + "args": { + "External id": 3725092,"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": 1625852858524.886, "dur": 0.468, + "args": { + "External id": 3725093,"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": 1625852858526.789, "dur": 0.510, + "args": { + "External id": 3725094,"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": 1625852858529.449, "dur": 2.285, + "args": { + "External id": 3725095,"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": 1625852858532.790, "dur": 0.256, + "args": { + "External id": 3725096,"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": 1625852858534.226, "dur": 0.358, + "args": { + "External id": 3725097,"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": 1625852858536.372, "dur": 0.517, + "args": { + "External id": 3725098,"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": 1625852858555.066, "dur": 21.018, + "args": { + "External id": 3725099,"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": 1625852858623.707, "dur": 131.875, + "args": { + "External id": 3725100,"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": 1625852858649.820, "dur": 101.856, + "args": { + "External id": 3725101,"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": 1625852858658.743, "dur": 88.386, + "args": { + "External id": 3725102,"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": 1625852858773.220, "dur": 1.761, + "args": { + "External id": 3725103,"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": 1625852858852.485, "dur": 1656.067, + "args": { + "External id": 3725104,"Sequence number": 37295084, "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": 1625852858852.485, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1625852858963.758, "dur": 143.903, + "args": { + "External id": 3725105,"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": 1625852859155.967, "dur": 40.825, + "args": { + "External id": 3725106,"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": 1625852859213.392, "dur": 50.212, + "args": { + "External id": 3725107,"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": 1625852859272.809, "dur": 32.005, + "args": { + "External id": 3725108,"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": 1625852859311.007, "dur": 43.724, + "args": { + "External id": 3725109,"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": 1625852859363.052, "dur": 27.823, + "args": { + "External id": 3725110,"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": 1625852859399.563, "dur": 41.691, + "args": { + "External id": 3725111,"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": 1625852859464.293, "dur": 21.700, + "args": { + "External id": 3725112,"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": 1625852859505.478, "dur": 29.727, + "args": { + "External id": 3725113,"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": 1625852859557.337, "dur": 19.844, + "args": { + "External id": 3725114,"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": 1625852859593.132, "dur": 18.695, + "args": { + "External id": 3725115,"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": 1625852859619.278, "dur": 28.488, + "args": { + "External id": 3725116,"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": 1625852859650.599, "dur": 47.522, + "args": { + "External id": 3725117,"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": 1625852859730.989, "dur": 178.755, + "args": { + "External id": 3725118,"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": 1625852859810.115, "dur": 7.849, + "args": { + "External id": 3725119,"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": 1625852859820.051, "dur": 2.468, + "args": { + "External id": 3725120,"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": 1625852859944.687, "dur": 31.025, + "args": { + "External id": 3725121,"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": 1625852860034.058, "dur": 18.991, + "args": { + "External id": 3725122,"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": 1625852860063.366, "dur": 43.340, + "args": { + "External id": 3725123,"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": 1625852860112.327, "dur": 35.592, + "args": { + "External id": 3725124,"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": 1625852860155.237, "dur": 21.589, + "args": { + "External id": 3725125,"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": 1625852860183.770, "dur": 28.487, + "args": { + "External id": 3725126,"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": 1625852860217.745, "dur": 21.329, + "args": { + "External id": 3725127,"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": 1625852860245.448, "dur": 43.010, + "args": { + "External id": 3725128,"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": 1625852860314.817, "dur": 26.114, + "args": { + "External id": 3725129,"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": 1625852860360.776, "dur": 26.864, + "args": { + "External id": 3725130,"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": 1625852860404.279, "dur": 16.114, + "args": { + "External id": 3725131,"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": 1625852860435.742, "dur": 14.594, + "args": { + "External id": 3725132,"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": 1625852860466.368, "dur": 15.304, + "args": { + "External id": 3725133,"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": 1625852860555.258, "dur": 17.837, + "args": { + "External id": 3725134,"Record function id": 0, "Ev Idx": 4941 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852860558.531, "dur": 13.676, + "args": { + "External id": 3725135,"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": 1625852860562.785, "dur": 8.690, + "args": { + "External id": 3725136,"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": 1625852860564.217, "dur": 3.770, + "args": { + "External id": 3725137,"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": 1625852860576.976, "dur": 4.702, + "args": { + "External id": 3725138,"Record function id": 0, "Ev Idx": 4945 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852860578.427, "dur": 2.836, + "args": { + "External id": 3725139,"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": 1625852860579.316, "dur": 1.531, + "args": { + "External id": 3725140,"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": 1625852860579.863, "dur": 0.863, + "args": { + "External id": 3725141,"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": 1625852860584.954, "dur": 4.120, + "args": { + "External id": 3725142,"Record function id": 0, "Ev Idx": 4949 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852860586.059, "dur": 2.624, + "args": { + "External id": 3725143,"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": 1625852860586.551, "dur": 1.719, + "args": { + "External id": 3725144,"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": 1625852860587.320, "dur": 0.868, + "args": { + "External id": 3725145,"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": 1625852860592.239, "dur": 3.433, + "args": { + "External id": 3725146,"Record function id": 0, "Ev Idx": 4953 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852860593.148, "dur": 2.118, + "args": { + "External id": 3725147,"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": 1625852860593.656, "dur": 1.209, + "args": { + "External id": 3725148,"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": 1625852860594.147, "dur": 0.653, + "args": { + "External id": 3725149,"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": 1625852860598.617, "dur": 5.809, + "args": { + "External id": 3725150,"Record function id": 0, "Ev Idx": 4957 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852860599.629, "dur": 4.406, + "args": { + "External id": 3725151,"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": 1625852860600.102, "dur": 3.505, + "args": { + "External id": 3725152,"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": 1625852860600.528, "dur": 3.009, + "args": { + "External id": 3725153,"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": 1625852860607.366, "dur": 3.818, + "args": { + "External id": 3725154,"Record function id": 0, "Ev Idx": 4961 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852860608.457, "dur": 2.343, + "args": { + "External id": 3725155,"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": 1625852860608.909, "dur": 1.495, + "args": { + "External id": 3725156,"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": 1625852860609.467, "dur": 0.871, + "args": { + "External id": 3725157,"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": 1625852860614.249, "dur": 5.259, + "args": { + "External id": 3725158,"Record function id": 0, "Ev Idx": 4965 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852860615.464, "dur": 3.640, + "args": { + "External id": 3725159,"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": 1625852860616.135, "dur": 2.575, + "args": { + "External id": 3725160,"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": 1625852860618.095, "dur": 0.550, + "args": { + "External id": 3725161,"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": 1625852860622.648, "dur": 4.033, + "args": { + "External id": 3725162,"Record function id": 0, "Ev Idx": 4969 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852860623.836, "dur": 2.446, + "args": { + "External id": 3725163,"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": 1625852860624.881, "dur": 0.988, + "args": { + "External id": 3725164,"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": 1625852860625.260, "dur": 0.542, + "args": { + "External id": 3725165,"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": 1625852860629.698, "dur": 3.764, + "args": { + "External id": 3725166,"Record function id": 0, "Ev Idx": 4973 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852860630.955, "dur": 2.110, + "args": { + "External id": 3725167,"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": 1625852860631.655, "dur": 1.014, + "args": { + "External id": 3725168,"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": 1625852860631.909, "dur": 0.696, + "args": { + "External id": 3725169,"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": 1625852860637.078, "dur": 35678.130, + "args": { + "External id": 3725170,"Record function id": 0, "Sequence number": 37295083, "Fwd thread id": 1, "Ev Idx": 4977 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1625852860638.842, "dur": 35668.537, + "args": { + "External id": 3725171,"Sequence number": 37295083, "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": 1625852860638.842, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.5)", "pid": 1336756, "tid": 1381189, + "ts": 1625852860667.135, "dur": 56.130, + "args": { + "External id": 3725172,"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": 1625852860731.683, "dur": 69.336, + "args": { + "External id": 3725173,"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": 1625852860808.427, "dur": 35491.268, + "args": { + "External id": 3725174,"Record function id": 0, "Ev Idx": 4981 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1625852860892.154, "dur": 6.474, + "args": { + "External id": 3725175,"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": 1625852860908.902, "dur": 4.940, + "args": { + "External id": 3725176,"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": 1625852860927.573, "dur": 34633.397, + "args": { + "External id": 3725177,"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": 1625852860941.500, "dur": 34609.449, + "args": { + "External id": 3725178,"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": 1625852861022.355, "dur": 18.123, + "args": { + "External id": 3725179,"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": 1625852861047.210, "dur": 34462.410, + "args": { + "External id": 3725180,"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": 1625852861049.857, "dur": 34459.150, + "args": { + "External id": 3725181,"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": 1625852861053.935, "dur": 6.215, + "args": { + "External id": 3725182,"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": 1625852861061.783, "dur": 34443.575, + "args": { + "External id": 3725183,"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": 1625852895651.294, "dur": 8.492, + "args": { + "External id": 3725184,"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": 1625852895654.009, "dur": 5.376, + "args": { + "External id": 3725185,"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": 1625852895701.970, "dur": 278.673, + "args": { + "External id": 3725186,"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": 1625852895731.914, "dur": 244.212, + "args": { + "External id": 3725187,"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": 1625852895743.187, "dur": 227.384, + "args": { + "External id": 3725188,"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": 1625852896034.975, "dur": 3.196, + "args": { + "External id": 3725189,"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": 1625852896096.039, "dur": 7.951, + "args": { + "External id": 3725190,"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": 1625852896150.616, "dur": 1.534, + "args": { + "External id": 3725191,"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": 1625852896166.383, "dur": 1.331, + "args": { + "External id": 3725192,"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": 1625852896179.623, "dur": 0.990, + "args": { + "External id": 3725193,"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": 1625852896192.553, "dur": 2.607, + "args": { + "External id": 3725194,"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": 1625852896204.676, "dur": 0.866, + "args": { + "External id": 3725195,"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": 1625852896217.686, "dur": 0.966, + "args": { + "External id": 3725196,"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": 1625852896229.109, "dur": 1.191, + "args": { + "External id": 3725197,"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": 1625852896239.802, "dur": 2.403, + "args": { + "External id": 3725198,"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": 1625852896329.624, "dur": 2759.255, + "args": { + "External id": 3725199,"Record function id": 0, "Ev Idx": 5006 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.4)", "pid": 1336756, "tid": 1381189, + "ts": 1625852896349.250, "dur": 1025.724, + "args": { + "External id": 3725200,"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": 1625852896363.913, "dur": 300.184, + "args": { + "External id": 3725201,"Record function id": 0, "Ev Idx": 5008 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1625852896441.134, "dur": 4.020, + "args": { + "External id": 3725202,"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": 1625852896448.630, "dur": 0.944, + "args": { + "External id": 3725203,"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": 1625852896453.510, "dur": 0.937, + "args": { + "External id": 3725204,"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": 1625852896456.061, "dur": 0.842, + "args": { + "External id": 3725205,"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": 1625852896458.342, "dur": 1.049, + "args": { + "External id": 3725206,"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": 1625852896460.848, "dur": 0.765, + "args": { + "External id": 3725207,"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": 1625852896464.501, "dur": 0.707, + "args": { + "External id": 3725208,"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": 1625852896466.779, "dur": 2.709, + "args": { + "External id": 3725209,"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": 1625852896471.223, "dur": 1.109, + "args": { + "External id": 3725210,"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": 1625852896474.223, "dur": 1.405, + "args": { + "External id": 3725211,"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": 1625852896494.684, "dur": 143.209, + "args": { + "External id": 3725212,"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": 1625852896510.714, "dur": 123.322, + "args": { + "External id": 3725213,"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": 1625852896527.600, "dur": 12.483, + "args": { + "External id": 3725214,"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": 1625852896543.043, "dur": 62.976, + "args": { + "External id": 3725215,"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": 1625852896545.521, "dur": 60.222, + "args": { + "External id": 3725216,"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": 1625852896549.582, "dur": 5.840, + "args": { + "External id": 3725217,"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": 1625852896557.145, "dur": 47.736, + "args": { + "External id": 3725218,"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": 1625852896771.041, "dur": 595.983, + "args": { + "External id": 3725219,"Record function id": 0, "Ev Idx": 5026 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.3)", "pid": 1336756, "tid": 1381189, + "ts": 1625852896787.863, "dur": 566.271, + "args": { + "External id": 3725220,"Record function id": 0, "Ev Idx": 5027 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1625852896849.507, "dur": 5.361, + "args": { + "External id": 3725221,"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": 1625852896872.950, "dur": 28.340, + "args": { + "External id": 3725222,"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": 1625852896877.994, "dur": 1.338, + "args": { + "External id": 3725223,"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": 1625852896882.099, "dur": 0.359, + "args": { + "External id": 3725224,"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": 1625852896883.960, "dur": 2.486, + "args": { + "External id": 3725225,"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": 1625852896887.715, "dur": 0.993, + "args": { + "External id": 3725226,"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": 1625852896889.947, "dur": 0.566, + "args": { + "External id": 3725227,"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": 1625852896892.118, "dur": 0.608, + "args": { + "External id": 3725228,"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": 1625852896894.580, "dur": 0.462, + "args": { + "External id": 3725229,"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": 1625852896896.557, "dur": 0.313, + "args": { + "External id": 3725230,"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": 1625852896898.183, "dur": 0.280, + "args": { + "External id": 3725231,"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": 1625852896912.125, "dur": 37.740, + "args": { + "External id": 3725232,"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": 1625852896978.102, "dur": 149.136, + "args": { + "External id": 3725233,"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": 1625852897023.818, "dur": 4.551, + "args": { + "External id": 3725234,"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": 1625852897034.222, "dur": 13.026, + "args": { + "External id": 3725235,"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": 1625852897038.573, "dur": 8.257, + "args": { + "External id": 3725236,"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": 1625852897042.469, "dur": 2.841, + "args": { + "External id": 3725237,"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": 1625852897054.895, "dur": 28.049, + "args": { + "External id": 3725238,"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": 1625852897057.465, "dur": 0.269, + "args": { + "External id": 3725239,"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": 1625852897059.292, "dur": 0.537, + "args": { + "External id": 3725240,"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": 1625852897061.084, "dur": 0.439, + "args": { + "External id": 3725241,"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": 1625852897063.362, "dur": 0.479, + "args": { + "External id": 3725242,"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": 1625852897065.138, "dur": 0.519, + "args": { + "External id": 3725243,"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": 1625852897067.060, "dur": 1.079, + "args": { + "External id": 3725244,"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": 1625852897069.576, "dur": 0.578, + "args": { + "External id": 3725245,"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": 1625852897071.466, "dur": 2.505, + "args": { + "External id": 3725246,"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": 1625852897075.644, "dur": 0.250, + "args": { + "External id": 3725247,"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": 1625852897095.927, "dur": 24.262, + "args": { + "External id": 3725248,"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": 1625852897170.314, "dur": 115.680, + "args": { + "External id": 3725249,"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": 1625852897197.341, "dur": 85.558, + "args": { + "External id": 3725250,"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": 1625852897206.556, "dur": 72.499, + "args": { + "External id": 3725251,"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": 1625852897305.416, "dur": 1.966, + "args": { + "External id": 3725252,"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": 1625852897381.746, "dur": 1686.146, + "args": { + "External id": 3725253,"Sequence number": 37295082, "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": 1625852897381.746, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1625852897489.226, "dur": 101.653, + "args": { + "External id": 3725254,"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": 1625852897630.807, "dur": 40.076, + "args": { + "External id": 3725255,"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": 1625852897712.503, "dur": 55.930, + "args": { + "External id": 3725256,"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": 1625852897778.237, "dur": 33.508, + "args": { + "External id": 3725257,"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": 1625852897818.128, "dur": 44.481, + "args": { + "External id": 3725258,"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": 1625852897869.038, "dur": 27.554, + "args": { + "External id": 3725259,"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": 1625852897905.572, "dur": 40.321, + "args": { + "External id": 3725260,"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": 1625852897969.618, "dur": 61.770, + "args": { + "External id": 3725261,"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": 1625852898054.759, "dur": 29.420, + "args": { + "External id": 3725262,"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": 1625852898105.546, "dur": 20.117, + "args": { + "External id": 3725263,"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": 1625852898140.725, "dur": 15.998, + "args": { + "External id": 3725264,"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": 1625852898166.779, "dur": 35.832, + "args": { + "External id": 3725265,"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": 1625852898205.693, "dur": 33.116, + "args": { + "External id": 3725266,"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": 1625852898268.022, "dur": 162.951, + "args": { + "External id": 3725267,"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": 1625852898341.947, "dur": 6.022, + "args": { + "External id": 3725268,"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": 1625852898349.863, "dur": 3.120, + "args": { + "External id": 3725269,"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": 1625852898464.382, "dur": 28.695, + "args": { + "External id": 3725270,"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": 1625852898505.079, "dur": 14.989, + "args": { + "External id": 3725271,"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": 1625852898527.498, "dur": 36.416, + "args": { + "External id": 3725272,"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": 1625852898571.583, "dur": 36.666, + "args": { + "External id": 3725273,"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": 1625852898614.424, "dur": 22.637, + "args": { + "External id": 3725274,"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": 1625852898641.654, "dur": 32.456, + "args": { + "External id": 3725275,"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": 1625852898699.066, "dur": 26.143, + "args": { + "External id": 3725276,"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": 1625852898734.068, "dur": 29.225, + "args": { + "External id": 3725277,"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": 1625852898785.114, "dur": 37.693, + "args": { + "External id": 3725278,"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": 1625852898849.825, "dur": 28.058, + "args": { + "External id": 3725279,"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": 1625852898902.312, "dur": 17.675, + "args": { + "External id": 3725280,"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": 1625852898935.949, "dur": 18.354, + "args": { + "External id": 3725281,"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": 1625852898966.615, "dur": 66.398, + "args": { + "External id": 3725282,"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": 1625852899111.831, "dur": 14.827, + "args": { + "External id": 3725283,"Record function id": 0, "Ev Idx": 5090 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852899114.869, "dur": 10.896, + "args": { + "External id": 3725284,"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": 1625852899119.344, "dur": 5.455, + "args": { + "External id": 3725285,"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": 1625852899120.870, "dur": 3.839, + "args": { + "External id": 3725286,"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": 1625852899130.538, "dur": 7.187, + "args": { + "External id": 3725287,"Record function id": 0, "Ev Idx": 5094 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852899132.144, "dur": 5.123, + "args": { + "External id": 3725288,"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": 1625852899133.277, "dur": 3.584, + "args": { + "External id": 3725289,"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": 1625852899133.770, "dur": 3.027, + "args": { + "External id": 3725290,"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": 1625852899141.004, "dur": 4.466, + "args": { + "External id": 3725291,"Record function id": 0, "Ev Idx": 5098 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852899142.486, "dur": 2.559, + "args": { + "External id": 3725292,"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": 1625852899143.175, "dur": 1.473, + "args": { + "External id": 3725293,"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": 1625852899143.622, "dur": 0.945, + "args": { + "External id": 3725294,"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": 1625852899148.563, "dur": 3.590, + "args": { + "External id": 3725295,"Record function id": 0, "Ev Idx": 5102 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852899149.617, "dur": 2.085, + "args": { + "External id": 3725296,"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": 1625852899150.165, "dur": 1.165, + "args": { + "External id": 3725297,"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": 1625852899150.617, "dur": 0.646, + "args": { + "External id": 3725298,"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": 1625852899155.161, "dur": 3.809, + "args": { + "External id": 3725299,"Record function id": 0, "Ev Idx": 5106 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852899156.559, "dur": 1.998, + "args": { + "External id": 3725300,"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": 1625852899157.090, "dur": 1.079, + "args": { + "External id": 3725301,"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": 1625852899157.401, "dur": 0.705, + "args": { + "External id": 3725302,"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": 1625852899161.876, "dur": 4.856, + "args": { + "External id": 3725303,"Record function id": 0, "Ev Idx": 5110 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852899162.836, "dur": 3.500, + "args": { + "External id": 3725304,"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": 1625852899163.447, "dur": 2.467, + "args": { + "External id": 3725305,"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": 1625852899165.228, "dur": 0.611, + "args": { + "External id": 3725306,"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": 1625852899169.869, "dur": 3.760, + "args": { + "External id": 3725307,"Record function id": 0, "Ev Idx": 5114 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852899171.119, "dur": 2.099, + "args": { + "External id": 3725308,"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": 1625852899171.675, "dur": 1.149, + "args": { + "External id": 3725309,"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": 1625852899172.154, "dur": 0.603, + "args": { + "External id": 3725310,"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": 1625852899176.759, "dur": 27.021, + "args": { + "External id": 3725311,"Record function id": 0, "Ev Idx": 5118 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852899177.936, "dur": 25.398, + "args": { + "External id": 3725312,"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": 1625852899201.538, "dur": 1.409, + "args": { + "External id": 3725313,"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": 1625852899202.155, "dur": 0.728, + "args": { + "External id": 3725314,"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": 1625852899206.819, "dur": 6.865, + "args": { + "External id": 3725315,"Record function id": 0, "Ev Idx": 5122 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852899208.155, "dur": 5.083, + "args": { + "External id": 3725316,"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": 1625852899208.641, "dur": 4.198, + "args": { + "External id": 3725317,"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": 1625852899210.160, "dur": 2.576, + "args": { + "External id": 3725318,"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": 1625852899217.381, "dur": 36296.644, + "args": { + "External id": 3725319,"Record function id": 0, "Sequence number": 37295081, "Fwd thread id": 1, "Ev Idx": 5126 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1625852899218.901, "dur": 36287.060, + "args": { + "External id": 3725320,"Sequence number": 37295081, "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": 1625852899218.901, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.4)", "pid": 1336756, "tid": 1381189, + "ts": 1625852899248.250, "dur": 38.798, + "args": { + "External id": 3725321,"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": 1625852899294.609, "dur": 64.181, + "args": { + "External id": 3725322,"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": 1625852899365.261, "dur": 36132.382, + "args": { + "External id": 3725323,"Record function id": 0, "Ev Idx": 5130 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1625852899458.537, "dur": 6.981, + "args": { + "External id": 3725324,"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": 1625852899474.751, "dur": 4.483, + "args": { + "External id": 3725325,"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": 1625852899492.733, "dur": 35150.367, + "args": { + "External id": 3725326,"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": 1625852899505.258, "dur": 35128.861, + "args": { + "External id": 3725327,"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": 1625852899542.646, "dur": 13.023, + "args": { + "External id": 3725328,"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": 1625852899563.540, "dur": 35024.347, + "args": { + "External id": 3725329,"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": 1625852899566.213, "dur": 35020.667, + "args": { + "External id": 3725330,"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": 1625852899570.279, "dur": 4.729, + "args": { + "External id": 3725331,"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": 1625852899576.685, "dur": 35006.884, + "args": { + "External id": 3725332,"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": 1625852934745.548, "dur": 9.092, + "args": { + "External id": 3725333,"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": 1625852934748.291, "dur": 5.757, + "args": { + "External id": 3725334,"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": 1625852934785.485, "dur": 416.049, + "args": { + "External id": 3725335,"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": 1625852934815.163, "dur": 381.377, + "args": { + "External id": 3725336,"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": 1625852934825.717, "dur": 365.193, + "args": { + "External id": 3725337,"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": 1625852935223.956, "dur": 2.445, + "args": { + "External id": 3725338,"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": 1625852935289.440, "dur": 6.437, + "args": { + "External id": 3725339,"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": 1625852935338.819, "dur": 1.752, + "args": { + "External id": 3725340,"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": 1625852935355.853, "dur": 1.676, + "args": { + "External id": 3725341,"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": 1625852935371.676, "dur": 0.997, + "args": { + "External id": 3725342,"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": 1625852935384.062, "dur": 0.746, + "args": { + "External id": 3725343,"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": 1625852935395.122, "dur": 0.816, + "args": { + "External id": 3725344,"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": 1625852935408.311, "dur": 1.086, + "args": { + "External id": 3725345,"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": 1625852935422.535, "dur": 1.295, + "args": { + "External id": 3725346,"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": 1625852935436.873, "dur": 0.920, + "args": { + "External id": 3725347,"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": 1625852935527.846, "dur": 2758.863, + "args": { + "External id": 3725348,"Record function id": 0, "Ev Idx": 5155 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.3)", "pid": 1336756, "tid": 1381189, + "ts": 1625852935547.050, "dur": 1036.491, + "args": { + "External id": 3725349,"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": 1625852935560.716, "dur": 334.341, + "args": { + "External id": 3725350,"Record function id": 0, "Ev Idx": 5157 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1625852935641.182, "dur": 4.382, + "args": { + "External id": 3725351,"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": 1625852935649.051, "dur": 0.837, + "args": { + "External id": 3725352,"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": 1625852935652.980, "dur": 0.906, + "args": { + "External id": 3725353,"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": 1625852935655.897, "dur": 0.912, + "args": { + "External id": 3725354,"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": 1625852935658.486, "dur": 2.213, + "args": { + "External id": 3725355,"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": 1625852935662.413, "dur": 0.751, + "args": { + "External id": 3725356,"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": 1625852935666.215, "dur": 0.813, + "args": { + "External id": 3725357,"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": 1625852935668.575, "dur": 0.950, + "args": { + "External id": 3725358,"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": 1625852935671.329, "dur": 1.265, + "args": { + "External id": 3725359,"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": 1625852935674.319, "dur": 1.114, + "args": { + "External id": 3725360,"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": 1625852935715.207, "dur": 151.510, + "args": { + "External id": 3725361,"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": 1625852935732.263, "dur": 130.461, + "args": { + "External id": 3725362,"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": 1625852935751.039, "dur": 14.056, + "args": { + "External id": 3725363,"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": 1625852935768.334, "dur": 65.838, + "args": { + "External id": 3725364,"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": 1625852935770.940, "dur": 62.812, + "args": { + "External id": 3725365,"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": 1625852935775.037, "dur": 6.539, + "args": { + "External id": 3725366,"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": 1625852935783.162, "dur": 50.018, + "args": { + "External id": 3725367,"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": 1625852935980.591, "dur": 595.406, + "args": { + "External id": 3725368,"Record function id": 0, "Ev Idx": 5175 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.2)", "pid": 1336756, "tid": 1381189, + "ts": 1625852936038.988, "dur": 524.850, + "args": { + "External id": 3725369,"Record function id": 0, "Ev Idx": 5176 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1625852936103.786, "dur": 8.402, + "args": { + "External id": 3725370,"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": 1625852936131.583, "dur": 33.132, + "args": { + "External id": 3725371,"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": 1625852936137.034, "dur": 2.531, + "args": { + "External id": 3725372,"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": 1625852936141.694, "dur": 0.632, + "args": { + "External id": 3725373,"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": 1625852936143.939, "dur": 0.491, + "args": { + "External id": 3725374,"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": 1625852936147.906, "dur": 0.363, + "args": { + "External id": 3725375,"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": 1625852936149.360, "dur": 0.401, + "args": { + "External id": 3725376,"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": 1625852936151.514, "dur": 0.620, + "args": { + "External id": 3725377,"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": 1625852936154.827, "dur": 0.335, + "args": { + "External id": 3725378,"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": 1625852936156.344, "dur": 2.498, + "args": { + "External id": 3725379,"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": 1625852936160.457, "dur": 1.285, + "args": { + "External id": 3725380,"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": 1625852936176.501, "dur": 35.115, + "args": { + "External id": 3725381,"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": 1625852936241.152, "dur": 103.179, + "args": { + "External id": 3725382,"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": 1625852936250.910, "dur": 3.142, + "args": { + "External id": 3725383,"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": 1625852936259.014, "dur": 9.618, + "args": { + "External id": 3725384,"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": 1625852936262.891, "dur": 5.318, + "args": { + "External id": 3725385,"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": 1625852936266.583, "dur": 0.505, + "args": { + "External id": 3725386,"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": 1625852936275.421, "dur": 30.568, + "args": { + "External id": 3725387,"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": 1625852936277.770, "dur": 0.500, + "args": { + "External id": 3725388,"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": 1625852936280.459, "dur": 0.482, + "args": { + "External id": 3725389,"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": 1625852936282.332, "dur": 1.929, + "args": { + "External id": 3725390,"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": 1625852936285.934, "dur": 0.395, + "args": { + "External id": 3725391,"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": 1625852936287.604, "dur": 2.746, + "args": { + "External id": 3725392,"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": 1625852936292.325, "dur": 0.518, + "args": { + "External id": 3725393,"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": 1625852936294.433, "dur": 0.586, + "args": { + "External id": 3725394,"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": 1625852936296.402, "dur": 0.463, + "args": { + "External id": 3725395,"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": 1625852936298.371, "dur": 0.698, + "args": { + "External id": 3725396,"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": 1625852936317.601, "dur": 19.956, + "args": { + "External id": 3725397,"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": 1625852936387.354, "dur": 112.627, + "args": { + "External id": 3725398,"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": 1625852936413.684, "dur": 83.161, + "args": { + "External id": 3725399,"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": 1625852936423.004, "dur": 69.522, + "args": { + "External id": 3725400,"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": 1625852936516.077, "dur": 2.133, + "args": { + "External id": 3725401,"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": 1625852936590.235, "dur": 1677.068, + "args": { + "External id": 3725402,"Sequence number": 37295080, "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": 1625852936590.235, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1625852936723.701, "dur": 107.111, + "args": { + "External id": 3725403,"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": 1625852936875.970, "dur": 44.608, + "args": { + "External id": 3725404,"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": 1625852936935.946, "dur": 91.332, + "args": { + "External id": 3725405,"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": 1625852937044.559, "dur": 38.596, + "args": { + "External id": 3725406,"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": 1625852937089.826, "dur": 45.719, + "args": { + "External id": 3725407,"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": 1625852937144.077, "dur": 27.513, + "args": { + "External id": 3725408,"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": 1625852937178.933, "dur": 41.618, + "args": { + "External id": 3725409,"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": 1625852937244.883, "dur": 25.737, + "args": { + "External id": 3725410,"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": 1625852937288.753, "dur": 29.730, + "args": { + "External id": 3725411,"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": 1625852937336.526, "dur": 19.783, + "args": { + "External id": 3725412,"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": 1625852937371.310, "dur": 16.123, + "args": { + "External id": 3725413,"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": 1625852937396.895, "dur": 29.516, + "args": { + "External id": 3725414,"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": 1625852937429.339, "dur": 32.227, + "args": { + "External id": 3725415,"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": 1625852937490.181, "dur": 167.336, + "args": { + "External id": 3725416,"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": 1625852937567.806, "dur": 6.232, + "args": { + "External id": 3725417,"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": 1625852937575.883, "dur": 2.490, + "args": { + "External id": 3725418,"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": 1625852937708.450, "dur": 27.713, + "args": { + "External id": 3725419,"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": 1625852937747.662, "dur": 15.021, + "args": { + "External id": 3725420,"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": 1625852937774.331, "dur": 40.556, + "args": { + "External id": 3725421,"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": 1625852937820.127, "dur": 33.341, + "args": { + "External id": 3725422,"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": 1625852937859.806, "dur": 22.090, + "args": { + "External id": 3725423,"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": 1625852937886.501, "dur": 28.989, + "args": { + "External id": 3725424,"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": 1625852937923.286, "dur": 21.907, + "args": { + "External id": 3725425,"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": 1625852937951.796, "dur": 79.691, + "args": { + "External id": 3725426,"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": 1625852938064.853, "dur": 27.391, + "args": { + "External id": 3725427,"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": 1625852938111.587, "dur": 28.799, + "args": { + "External id": 3725428,"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": 1625852938155.306, "dur": 18.972, + "args": { + "External id": 3725429,"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": 1625852938190.429, "dur": 18.345, + "args": { + "External id": 3725430,"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": 1625852938220.142, "dur": 16.128, + "args": { + "External id": 3725431,"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": 1625852938308.197, "dur": 19.168, + "args": { + "External id": 3725432,"Record function id": 0, "Ev Idx": 5239 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852938311.161, "dur": 15.359, + "args": { + "External id": 3725433,"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": 1625852938318.720, "dur": 7.064, + "args": { + "External id": 3725434,"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": 1625852938320.246, "dur": 5.454, + "args": { + "External id": 3725435,"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": 1625852938330.942, "dur": 5.113, + "args": { + "External id": 3725436,"Record function id": 0, "Ev Idx": 5243 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852938332.566, "dur": 3.081, + "args": { + "External id": 3725437,"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": 1625852938333.309, "dur": 1.853, + "args": { + "External id": 3725438,"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": 1625852938333.966, "dur": 1.124, + "args": { + "External id": 3725439,"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": 1625852938339.325, "dur": 5.032, + "args": { + "External id": 3725440,"Record function id": 0, "Ev Idx": 5247 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852938340.779, "dur": 3.154, + "args": { + "External id": 3725441,"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": 1625852938341.700, "dur": 1.782, + "args": { + "External id": 3725442,"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": 1625852938342.449, "dur": 0.926, + "args": { + "External id": 3725443,"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": 1625852938347.475, "dur": 4.105, + "args": { + "External id": 3725444,"Record function id": 0, "Ev Idx": 5251 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852938348.845, "dur": 2.333, + "args": { + "External id": 3725445,"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": 1625852938349.679, "dur": 1.086, + "args": { + "External id": 3725446,"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": 1625852938350.042, "dur": 0.658, + "args": { + "External id": 3725447,"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": 1625852938354.611, "dur": 4.218, + "args": { + "External id": 3725448,"Record function id": 0, "Ev Idx": 5255 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852938355.971, "dur": 2.442, + "args": { + "External id": 3725449,"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": 1625852938356.651, "dur": 1.307, + "args": { + "External id": 3725450,"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": 1625852938357.085, "dur": 0.807, + "args": { + "External id": 3725451,"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": 1625852938361.814, "dur": 3.768, + "args": { + "External id": 3725452,"Record function id": 0, "Ev Idx": 5259 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852938362.900, "dur": 2.293, + "args": { + "External id": 3725453,"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": 1625852938363.457, "dur": 1.307, + "args": { + "External id": 3725454,"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": 1625852938363.985, "dur": 0.704, + "args": { + "External id": 3725455,"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": 1625852938368.690, "dur": 8.367, + "args": { + "External id": 3725456,"Record function id": 0, "Ev Idx": 5263 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852938369.779, "dur": 6.870, + "args": { + "External id": 3725457,"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": 1625852938373.553, "dur": 2.684, + "args": { + "External id": 3725458,"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": 1625852938375.481, "dur": 0.655, + "args": { + "External id": 3725459,"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": 1625852938380.071, "dur": 8.701, + "args": { + "External id": 3725460,"Record function id": 0, "Ev Idx": 5267 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852938381.255, "dur": 7.108, + "args": { + "External id": 3725461,"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": 1625852938385.183, "dur": 2.617, + "args": { + "External id": 3725462,"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": 1625852938385.583, "dur": 2.154, + "args": { + "External id": 3725463,"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": 1625852938391.714, "dur": 4.448, + "args": { + "External id": 3725464,"Record function id": 0, "Ev Idx": 5271 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852938392.969, "dur": 2.792, + "args": { + "External id": 3725465,"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": 1625852938393.540, "dur": 1.785, + "args": { + "External id": 3725466,"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": 1625852938394.217, "dur": 1.027, + "args": { + "External id": 3725467,"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": 1625852938399.605, "dur": 36392.427, + "args": { + "External id": 3725468,"Record function id": 0, "Sequence number": 37295079, "Fwd thread id": 1, "Ev Idx": 5275 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1625852938401.232, "dur": 36382.347, + "args": { + "External id": 3725469,"Sequence number": 37295079, "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": 1625852938401.232, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.3)", "pid": 1336756, "tid": 1381189, + "ts": 1625852938433.174, "dur": 36.021, + "args": { + "External id": 3725470,"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": 1625852938476.724, "dur": 63.992, + "args": { + "External id": 3725471,"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": 1625852938546.835, "dur": 36228.736, + "args": { + "External id": 3725472,"Record function id": 0, "Ev Idx": 5279 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1625852938635.043, "dur": 6.313, + "args": { + "External id": 3725473,"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": 1625852938653.862, "dur": 4.681, + "args": { + "External id": 3725474,"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": 1625852938671.507, "dur": 35283.995, + "args": { + "External id": 3725475,"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": 1625852938707.118, "dur": 35239.528, + "args": { + "External id": 3725476,"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": 1625852938746.768, "dur": 13.367, + "args": { + "External id": 3725477,"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": 1625852938769.310, "dur": 35138.041, + "args": { + "External id": 3725478,"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": 1625852938771.893, "dur": 35134.804, + "args": { + "External id": 3725479,"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": 1625852938775.836, "dur": 5.758, + "args": { + "External id": 3725480,"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": 1625852938785.197, "dur": 35118.030, + "args": { + "External id": 3725481,"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": 1625852974064.825, "dur": 8.701, + "args": { + "External id": 3725482,"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": 1625852974067.424, "dur": 5.599, + "args": { + "External id": 3725483,"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": 1625852974104.417, "dur": 362.933, + "args": { + "External id": 3725484,"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": 1625852974133.600, "dur": 328.942, + "args": { + "External id": 3725485,"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": 1625852974144.804, "dur": 311.580, + "args": { + "External id": 3725486,"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": 1625852974489.953, "dur": 2.347, + "args": { + "External id": 3725487,"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": 1625852974550.334, "dur": 6.642, + "args": { + "External id": 3725488,"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": 1625852974601.532, "dur": 1.492, + "args": { + "External id": 3725489,"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": 1625852974617.774, "dur": 3.259, + "args": { + "External id": 3725490,"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": 1625852974632.820, "dur": 1.274, + "args": { + "External id": 3725491,"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": 1625852974645.333, "dur": 0.947, + "args": { + "External id": 3725492,"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": 1625852974655.593, "dur": 0.877, + "args": { + "External id": 3725493,"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": 1625852974668.133, "dur": 3.065, + "args": { + "External id": 3725494,"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": 1625852974702.800, "dur": 1.800, + "args": { + "External id": 3725495,"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": 1625852974716.033, "dur": 1.107, + "args": { + "External id": 3725496,"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": 1625852974806.818, "dur": 2702.009, + "args": { + "External id": 3725497,"Record function id": 0, "Ev Idx": 5304 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.2)", "pid": 1336756, "tid": 1381189, + "ts": 1625852974825.713, "dur": 1026.578, + "args": { + "External id": 3725498,"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": 1625852974840.023, "dur": 348.286, + "args": { + "External id": 3725499,"Record function id": 0, "Ev Idx": 5306 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1625852974923.038, "dur": 4.132, + "args": { + "External id": 3725500,"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": 1625852974930.168, "dur": 0.953, + "args": { + "External id": 3725501,"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": 1625852974934.411, "dur": 0.981, + "args": { + "External id": 3725502,"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": 1625852974936.966, "dur": 2.566, + "args": { + "External id": 3725503,"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": 1625852974941.197, "dur": 0.972, + "args": { + "External id": 3725504,"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": 1625852974943.629, "dur": 1.242, + "args": { + "External id": 3725505,"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": 1625852974948.177, "dur": 0.634, + "args": { + "External id": 3725506,"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": 1625852974950.658, "dur": 0.745, + "args": { + "External id": 3725507,"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": 1625852974952.636, "dur": 1.445, + "args": { + "External id": 3725508,"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": 1625852974955.724, "dur": 1.061, + "args": { + "External id": 3725509,"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": 1625852974976.582, "dur": 183.559, + "args": { + "External id": 3725510,"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": 1625852975028.440, "dur": 127.357, + "args": { + "External id": 3725511,"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": 1625852975046.060, "dur": 12.043, + "args": { + "External id": 3725512,"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": 1625852975061.384, "dur": 66.703, + "args": { + "External id": 3725513,"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": 1625852975063.883, "dur": 63.852, + "args": { + "External id": 3725514,"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": 1625852975067.596, "dur": 8.929, + "args": { + "External id": 3725515,"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": 1625852975078.185, "dur": 48.977, + "args": { + "External id": 3725516,"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": 1625852975281.385, "dur": 562.652, + "args": { + "External id": 3725517,"Record function id": 0, "Ev Idx": 5324 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.1)", "pid": 1336756, "tid": 1381189, + "ts": 1625852975297.213, "dur": 534.521, + "args": { + "External id": 3725518,"Record function id": 0, "Ev Idx": 5325 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1625852975359.289, "dur": 4.456, + "args": { + "External id": 3725519,"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": 1625852975388.547, "dur": 29.761, + "args": { + "External id": 3725520,"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": 1625852975395.779, "dur": 2.236, + "args": { + "External id": 3725521,"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": 1625852975399.854, "dur": 0.442, + "args": { + "External id": 3725522,"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": 1625852975401.475, "dur": 0.601, + "args": { + "External id": 3725523,"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": 1625852975403.828, "dur": 0.583, + "args": { + "External id": 3725524,"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": 1625852975405.970, "dur": 0.462, + "args": { + "External id": 3725525,"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": 1625852975407.541, "dur": 0.326, + "args": { + "External id": 3725526,"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": 1625852975409.369, "dur": 2.459, + "args": { + "External id": 3725527,"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": 1625852975412.876, "dur": 0.557, + "args": { + "External id": 3725528,"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": 1625852975414.746, "dur": 0.900, + "args": { + "External id": 3725529,"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": 1625852975428.798, "dur": 30.924, + "args": { + "External id": 3725530,"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": 1625852975489.515, "dur": 99.187, + "args": { + "External id": 3725531,"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": 1625852975499.703, "dur": 3.052, + "args": { + "External id": 3725532,"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": 1625852975508.049, "dur": 9.873, + "args": { + "External id": 3725533,"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": 1625852975512.207, "dur": 5.320, + "args": { + "External id": 3725534,"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": 1625852975515.826, "dur": 0.536, + "args": { + "External id": 3725535,"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": 1625852975524.323, "dur": 27.425, + "args": { + "External id": 3725536,"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": 1625852975526.234, "dur": 0.642, + "args": { + "External id": 3725537,"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": 1625852975528.026, "dur": 0.584, + "args": { + "External id": 3725538,"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": 1625852975529.578, "dur": 1.088, + "args": { + "External id": 3725539,"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": 1625852975531.699, "dur": 2.202, + "args": { + "External id": 3725540,"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": 1625852975534.907, "dur": 0.323, + "args": { + "External id": 3725541,"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": 1625852975536.762, "dur": 0.357, + "args": { + "External id": 3725542,"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": 1625852975540.072, "dur": 0.430, + "args": { + "External id": 3725543,"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": 1625852975541.393, "dur": 0.347, + "args": { + "External id": 3725544,"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": 1625852975543.721, "dur": 0.618, + "args": { + "External id": 3725545,"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": 1625852975562.747, "dur": 19.293, + "args": { + "External id": 3725546,"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": 1625852975630.302, "dur": 133.171, + "args": { + "External id": 3725547,"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": 1625852975657.309, "dur": 102.489, + "args": { + "External id": 3725548,"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": 1625852975666.390, "dur": 89.067, + "args": { + "External id": 3725549,"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": 1625852975780.694, "dur": 2.293, + "args": { + "External id": 3725550,"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": 1625852975859.061, "dur": 1625.139, + "args": { + "External id": 3725551,"Sequence number": 37295078, "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": 1625852975859.061, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1625852975970.014, "dur": 144.314, + "args": { + "External id": 3725552,"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": 1625852976158.527, "dur": 37.850, + "args": { + "External id": 3725553,"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": 1625852976213.036, "dur": 50.447, + "args": { + "External id": 3725554,"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": 1625852976273.137, "dur": 32.711, + "args": { + "External id": 3725555,"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": 1625852976314.195, "dur": 44.178, + "args": { + "External id": 3725556,"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": 1625852976365.045, "dur": 27.286, + "args": { + "External id": 3725557,"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": 1625852976399.289, "dur": 40.841, + "args": { + "External id": 3725558,"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": 1625852976461.777, "dur": 22.467, + "args": { + "External id": 3725559,"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": 1625852976502.559, "dur": 27.168, + "args": { + "External id": 3725560,"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": 1625852976550.623, "dur": 17.985, + "args": { + "External id": 3725561,"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": 1625852976586.680, "dur": 15.560, + "args": { + "External id": 3725562,"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": 1625852976609.927, "dur": 32.105, + "args": { + "External id": 3725563,"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": 1625852976645.133, "dur": 31.036, + "args": { + "External id": 3725564,"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": 1625852976724.948, "dur": 170.300, + "args": { + "External id": 3725565,"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": 1625852976804.117, "dur": 6.303, + "args": { + "External id": 3725566,"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": 1625852976812.412, "dur": 2.011, + "args": { + "External id": 3725567,"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": 1625852976929.080, "dur": 25.936, + "args": { + "External id": 3725568,"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": 1625852976966.031, "dur": 14.563, + "args": { + "External id": 3725569,"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": 1625852977025.650, "dur": 45.046, + "args": { + "External id": 3725570,"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": 1625852977076.241, "dur": 39.031, + "args": { + "External id": 3725571,"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": 1625852977121.648, "dur": 21.602, + "args": { + "External id": 3725572,"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": 1625852977152.553, "dur": 28.545, + "args": { + "External id": 3725573,"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": 1625852977186.279, "dur": 25.061, + "args": { + "External id": 3725574,"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": 1625852977217.649, "dur": 42.016, + "args": { + "External id": 3725575,"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": 1625852977290.857, "dur": 25.667, + "args": { + "External id": 3725576,"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": 1625852977333.998, "dur": 27.300, + "args": { + "External id": 3725577,"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": 1625852977376.048, "dur": 18.040, + "args": { + "External id": 3725578,"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": 1625852977410.033, "dur": 14.920, + "args": { + "External id": 3725579,"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": 1625852977440.846, "dur": 16.468, + "args": { + "External id": 3725580,"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": 1625852977530.537, "dur": 14.282, + "args": { + "External id": 3725581,"Record function id": 0, "Ev Idx": 5388 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852977533.633, "dur": 10.308, + "args": { + "External id": 3725582,"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": 1625852977537.724, "dur": 5.413, + "args": { + "External id": 3725583,"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": 1625852977539.309, "dur": 3.738, + "args": { + "External id": 3725584,"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": 1625852977552.028, "dur": 5.591, + "args": { + "External id": 3725585,"Record function id": 0, "Ev Idx": 5392 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852977553.631, "dur": 3.545, + "args": { + "External id": 3725586,"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": 1625852977554.768, "dur": 1.941, + "args": { + "External id": 3725587,"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": 1625852977555.437, "dur": 1.185, + "args": { + "External id": 3725588,"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": 1625852977560.988, "dur": 3.991, + "args": { + "External id": 3725589,"Record function id": 0, "Ev Idx": 5396 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852977561.910, "dur": 2.669, + "args": { + "External id": 3725590,"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": 1625852977562.583, "dur": 1.574, + "args": { + "External id": 3725591,"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": 1625852977563.232, "dur": 0.842, + "args": { + "External id": 3725592,"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": 1625852977568.238, "dur": 3.882, + "args": { + "External id": 3725593,"Record function id": 0, "Ev Idx": 5400 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852977569.403, "dur": 2.312, + "args": { + "External id": 3725594,"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": 1625852977570.085, "dur": 1.230, + "args": { + "External id": 3725595,"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": 1625852977570.619, "dur": 0.628, + "args": { + "External id": 3725596,"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": 1625852977575.128, "dur": 3.593, + "args": { + "External id": 3725597,"Record function id": 0, "Ev Idx": 5404 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852977576.177, "dur": 2.120, + "args": { + "External id": 3725598,"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": 1625852977576.804, "dur": 1.064, + "args": { + "External id": 3725599,"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": 1625852977577.105, "dur": 0.700, + "args": { + "External id": 3725600,"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": 1625852977581.720, "dur": 5.749, + "args": { + "External id": 3725601,"Record function id": 0, "Ev Idx": 5408 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852977582.832, "dur": 4.224, + "args": { + "External id": 3725602,"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": 1625852977583.323, "dur": 3.320, + "args": { + "External id": 3725603,"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": 1625852977585.859, "dur": 0.685, + "args": { + "External id": 3725604,"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": 1625852977590.605, "dur": 5.962, + "args": { + "External id": 3725605,"Record function id": 0, "Ev Idx": 5412 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852977591.637, "dur": 4.511, + "args": { + "External id": 3725606,"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": 1625852977592.667, "dur": 3.080, + "args": { + "External id": 3725607,"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": 1625852977592.946, "dur": 2.738, + "args": { + "External id": 3725608,"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": 1625852977599.864, "dur": 3.910, + "args": { + "External id": 3725609,"Record function id": 0, "Ev Idx": 5416 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852977601.054, "dur": 2.318, + "args": { + "External id": 3725610,"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": 1625852977601.507, "dur": 1.464, + "args": { + "External id": 3725611,"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": 1625852977602.102, "dur": 0.788, + "args": { + "External id": 3725612,"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": 1625852977610.147, "dur": 4.072, + "args": { + "External id": 3725613,"Record function id": 0, "Ev Idx": 5420 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625852977611.371, "dur": 2.448, + "args": { + "External id": 3725614,"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": 1625852977611.941, "dur": 1.501, + "args": { + "External id": 3725615,"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": 1625852977612.590, "dur": 0.790, + "args": { + "External id": 3725616,"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": 1625852977617.771, "dur": 36326.681, + "args": { + "External id": 3725617,"Record function id": 0, "Sequence number": 37295077, "Fwd thread id": 1, "Ev Idx": 5424 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1625852977619.453, "dur": 36316.535, + "args": { + "External id": 3725618,"Sequence number": 37295077, "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": 1625852977619.453, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.2)", "pid": 1336756, "tid": 1381189, + "ts": 1625852977646.698, "dur": 52.816, + "args": { + "External id": 3725619,"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": 1625852977708.683, "dur": 68.758, + "args": { + "External id": 3725620,"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": 1625852977783.528, "dur": 36144.909, + "args": { + "External id": 3725621,"Record function id": 0, "Ev Idx": 5428 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1625852977872.474, "dur": 6.695, + "args": { + "External id": 3725622,"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": 1625852977889.385, "dur": 4.759, + "args": { + "External id": 3725623,"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": 1625852977909.614, "dur": 35255.091, + "args": { + "External id": 3725624,"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": 1625852977922.929, "dur": 35232.962, + "args": { + "External id": 3725625,"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": 1625852977970.311, "dur": 52.073, + "args": { + "External id": 3725626,"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": 1625852978029.711, "dur": 35087.293, + "args": { + "External id": 3725627,"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": 1625852978032.262, "dur": 35084.135, + "args": { + "External id": 3725628,"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": 1625852978037.380, "dur": 9.092, + "args": { + "External id": 3725629,"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": 1625852978049.958, "dur": 35062.841, + "args": { + "External id": 3725630,"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": 1625853013250.146, "dur": 8.111, + "args": { + "External id": 3725631,"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": 1625853013252.771, "dur": 5.176, + "args": { + "External id": 3725632,"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": 1625853013289.152, "dur": 343.761, + "args": { + "External id": 3725633,"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": 1625853013320.175, "dur": 308.403, + "args": { + "External id": 3725634,"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": 1625853013331.111, "dur": 292.541, + "args": { + "External id": 3725635,"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": 1625853013651.660, "dur": 2.152, + "args": { + "External id": 3725636,"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": 1625853013725.734, "dur": 6.728, + "args": { + "External id": 3725637,"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": 1625853013776.135, "dur": 3.387, + "args": { + "External id": 3725638,"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": 1625853013794.832, "dur": 1.378, + "args": { + "External id": 3725639,"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": 1625853013807.889, "dur": 0.849, + "args": { + "External id": 3725640,"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": 1625853013821.157, "dur": 0.869, + "args": { + "External id": 3725641,"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": 1625853013832.562, "dur": 2.393, + "args": { + "External id": 3725642,"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": 1625853013845.836, "dur": 0.950, + "args": { + "External id": 3725643,"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": 1625853013856.967, "dur": 1.723, + "args": { + "External id": 3725644,"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": 1625853013868.414, "dur": 0.752, + "args": { + "External id": 3725645,"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": 1625853013959.137, "dur": 2800.035, + "args": { + "External id": 3725646,"Record function id": 0, "Ev Idx": 5453 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.1)", "pid": 1336756, "tid": 1381189, + "ts": 1625853013978.613, "dur": 1067.679, + "args": { + "External id": 3725647,"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": 1625853014028.052, "dur": 325.702, + "args": { + "External id": 3725648,"Record function id": 0, "Ev Idx": 5455 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1625853014121.520, "dur": 4.821, + "args": { + "External id": 3725649,"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": 1625853014129.621, "dur": 2.952, + "args": { + "External id": 3725650,"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": 1625853014134.340, "dur": 0.844, + "args": { + "External id": 3725651,"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": 1625853014136.708, "dur": 0.967, + "args": { + "External id": 3725652,"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": 1625853014138.953, "dur": 1.049, + "args": { + "External id": 3725653,"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": 1625853014142.697, "dur": 0.894, + "args": { + "External id": 3725654,"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": 1625853014144.978, "dur": 1.091, + "args": { + "External id": 3725655,"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": 1625853014147.451, "dur": 0.791, + "args": { + "External id": 3725656,"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": 1625853014149.799, "dur": 1.000, + "args": { + "External id": 3725657,"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": 1625853014154.304, "dur": 3.161, + "args": { + "External id": 3725658,"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": 1625853014175.020, "dur": 150.679, + "args": { + "External id": 3725659,"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": 1625853014190.490, "dur": 131.086, + "args": { + "External id": 3725660,"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": 1625853014206.860, "dur": 11.953, + "args": { + "External id": 3725661,"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": 1625853014221.647, "dur": 71.549, + "args": { + "External id": 3725662,"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": 1625853014224.451, "dur": 68.414, + "args": { + "External id": 3725663,"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": 1625853014228.248, "dur": 12.039, + "args": { + "External id": 3725664,"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": 1625853014241.813, "dur": 50.554, + "args": { + "External id": 3725665,"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": 1625853014447.738, "dur": 590.511, + "args": { + "External id": 3725666,"Record function id": 0, "Ev Idx": 5473 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.0)", "pid": 1336756, "tid": 1381189, + "ts": 1625853014462.802, "dur": 559.849, + "args": { + "External id": 3725667,"Record function id": 0, "Ev Idx": 5474 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1625853014526.504, "dur": 5.091, + "args": { + "External id": 3725668,"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": 1625853014550.821, "dur": 26.915, + "args": { + "External id": 3725669,"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": 1625853014555.330, "dur": 1.740, + "args": { + "External id": 3725670,"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": 1625853014558.706, "dur": 0.610, + "args": { + "External id": 3725671,"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": 1625853014560.712, "dur": 0.664, + "args": { + "External id": 3725672,"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": 1625853014562.511, "dur": 0.688, + "args": { + "External id": 3725673,"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": 1625853014564.997, "dur": 2.609, + "args": { + "External id": 3725674,"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": 1625853014569.706, "dur": 0.366, + "args": { + "External id": 3725675,"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": 1625853014571.316, "dur": 0.387, + "args": { + "External id": 3725676,"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": 1625853014573.051, "dur": 0.577, + "args": { + "External id": 3725677,"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": 1625853014575.026, "dur": 0.349, + "args": { + "External id": 3725678,"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": 1625853014587.285, "dur": 31.798, + "args": { + "External id": 3725679,"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": 1625853014646.423, "dur": 121.138, + "args": { + "External id": 3725680,"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": 1625853014655.901, "dur": 2.866, + "args": { + "External id": 3725681,"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": 1625853014663.157, "dur": 10.056, + "args": { + "External id": 3725682,"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": 1625853014667.487, "dur": 5.329, + "args": { + "External id": 3725683,"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": 1625853014670.966, "dur": 0.699, + "args": { + "External id": 3725684,"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": 1625853014698.138, "dur": 26.154, + "args": { + "External id": 3725685,"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": 1625853014700.487, "dur": 0.733, + "args": { + "External id": 3725686,"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": 1625853014703.032, "dur": 2.381, + "args": { + "External id": 3725687,"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": 1625853014707.157, "dur": 0.664, + "args": { + "External id": 3725688,"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": 1625853014708.912, "dur": 0.637, + "args": { + "External id": 3725689,"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": 1625853014710.683, "dur": 0.451, + "args": { + "External id": 3725690,"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": 1625853014712.597, "dur": 0.550, + "args": { + "External id": 3725691,"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": 1625853014714.230, "dur": 0.612, + "args": { + "External id": 3725692,"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": 1625853014716.391, "dur": 0.282, + "args": { + "External id": 3725693,"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": 1625853014718.547, "dur": 0.437, + "args": { + "External id": 3725694,"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": 1625853014735.344, "dur": 23.316, + "args": { + "External id": 3725695,"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": 1625853014810.610, "dur": 109.358, + "args": { + "External id": 3725696,"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": 1625853014835.171, "dur": 81.501, + "args": { + "External id": 3725697,"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": 1625853014844.420, "dur": 68.303, + "args": { + "External id": 3725698,"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": 1625853014936.262, "dur": 2.166, + "args": { + "External id": 3725699,"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": 1625853015053.800, "dur": 1681.950, + "args": { + "External id": 3725700,"Sequence number": 37295076, "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": 1625853015053.800, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1625853015165.773, "dur": 105.555, + "args": { + "External id": 3725701,"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": 1625853015314.136, "dur": 39.659, + "args": { + "External id": 3725702,"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": 1625853015370.096, "dur": 48.149, + "args": { + "External id": 3725703,"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": 1625853015429.742, "dur": 41.513, + "args": { + "External id": 3725704,"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": 1625853015485.596, "dur": 52.273, + "args": { + "External id": 3725705,"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": 1625853015544.257, "dur": 27.748, + "args": { + "External id": 3725706,"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": 1625853015578.551, "dur": 41.727, + "args": { + "External id": 3725707,"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": 1625853015646.347, "dur": 22.908, + "args": { + "External id": 3725708,"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": 1625853015704.294, "dur": 32.411, + "args": { + "External id": 3725709,"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": 1625853015758.601, "dur": 20.321, + "args": { + "External id": 3725710,"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": 1625853015791.803, "dur": 15.385, + "args": { + "External id": 3725711,"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": 1625853015815.702, "dur": 34.565, + "args": { + "External id": 3725712,"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": 1625853015853.243, "dur": 32.876, + "args": { + "External id": 3725713,"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": 1625853015915.351, "dur": 222.044, + "args": { + "External id": 3725714,"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": 1625853016039.017, "dur": 7.015, + "args": { + "External id": 3725715,"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": 1625853016048.260, "dur": 3.094, + "args": { + "External id": 3725716,"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": 1625853016171.615, "dur": 35.424, + "args": { + "External id": 3725717,"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": 1625853016217.630, "dur": 15.559, + "args": { + "External id": 3725718,"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": 1625853016242.281, "dur": 47.303, + "args": { + "External id": 3725719,"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": 1625853016296.111, "dur": 37.195, + "args": { + "External id": 3725720,"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": 1625853016342.242, "dur": 23.165, + "args": { + "External id": 3725721,"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": 1625853016370.780, "dur": 29.816, + "args": { + "External id": 3725722,"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": 1625853016406.223, "dur": 22.426, + "args": { + "External id": 3725723,"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": 1625853016447.497, "dur": 41.924, + "args": { + "External id": 3725724,"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": 1625853016509.494, "dur": 24.998, + "args": { + "External id": 3725725,"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": 1625853016558.088, "dur": 28.434, + "args": { + "External id": 3725726,"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": 1625853016601.375, "dur": 18.220, + "args": { + "External id": 3725727,"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": 1625853016638.305, "dur": 15.726, + "args": { + "External id": 3725728,"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": 1625853016666.625, "dur": 36.389, + "args": { + "External id": 3725729,"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": 1625853016781.627, "dur": 16.505, + "args": { + "External id": 3725730,"Record function id": 0, "Ev Idx": 5537 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625853016785.257, "dur": 12.075, + "args": { + "External id": 3725731,"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": 1625853016789.799, "dur": 6.676, + "args": { + "External id": 3725732,"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": 1625853016792.119, "dur": 4.247, + "args": { + "External id": 3725733,"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": 1625853016802.151, "dur": 5.673, + "args": { + "External id": 3725734,"Record function id": 0, "Ev Idx": 5541 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625853016803.315, "dur": 4.071, + "args": { + "External id": 3725735,"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": 1625853016804.352, "dur": 2.564, + "args": { + "External id": 3725736,"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": 1625853016805.345, "dur": 1.474, + "args": { + "External id": 3725737,"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": 1625853016811.232, "dur": 5.167, + "args": { + "External id": 3725738,"Record function id": 0, "Ev Idx": 5545 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625853016812.703, "dur": 3.250, + "args": { + "External id": 3725739,"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": 1625853016813.711, "dur": 1.797, + "args": { + "External id": 3725740,"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": 1625853016814.474, "dur": 0.963, + "args": { + "External id": 3725741,"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": 1625853016819.648, "dur": 4.129, + "args": { + "External id": 3725742,"Record function id": 0, "Ev Idx": 5549 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625853016820.999, "dur": 2.378, + "args": { + "External id": 3725743,"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": 1625853016821.744, "dur": 1.210, + "args": { + "External id": 3725744,"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": 1625853016822.224, "dur": 0.669, + "args": { + "External id": 3725745,"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": 1625853016826.804, "dur": 3.911, + "args": { + "External id": 3725746,"Record function id": 0, "Ev Idx": 5553 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625853016828.143, "dur": 2.143, + "args": { + "External id": 3725747,"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": 1625853016828.637, "dur": 1.231, + "args": { + "External id": 3725748,"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": 1625853016828.942, "dur": 0.860, + "args": { + "External id": 3725749,"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": 1625853016833.828, "dur": 7.774, + "args": { + "External id": 3725750,"Record function id": 0, "Ev Idx": 5557 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625853016835.049, "dur": 6.114, + "args": { + "External id": 3725751,"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": 1625853016838.963, "dur": 1.767, + "args": { + "External id": 3725752,"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": 1625853016839.688, "dur": 0.945, + "args": { + "External id": 3725753,"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": 1625853016844.854, "dur": 6.430, + "args": { + "External id": 3725754,"Record function id": 0, "Ev Idx": 5561 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625853016846.258, "dur": 4.613, + "args": { + "External id": 3725755,"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": 1625853016846.775, "dur": 3.664, + "args": { + "External id": 3725756,"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": 1625853016847.074, "dur": 3.303, + "args": { + "External id": 3725757,"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": 1625853016854.294, "dur": 4.038, + "args": { + "External id": 3725758,"Record function id": 0, "Ev Idx": 5565 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625853016855.570, "dur": 2.346, + "args": { + "External id": 3725759,"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": 1625853016856.091, "dur": 1.358, + "args": { + "External id": 3725760,"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": 1625853016856.399, "dur": 0.916, + "args": { + "External id": 3725761,"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": 1625853016861.322, "dur": 4.326, + "args": { + "External id": 3725762,"Record function id": 0, "Ev Idx": 5569 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625853016862.480, "dur": 2.741, + "args": { + "External id": 3725763,"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": 1625853016863.182, "dur": 1.611, + "args": { + "External id": 3725764,"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": 1625853016863.774, "dur": 0.902, + "args": { + "External id": 3725765,"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": 1625853016869.681, "dur": 38068.014, + "args": { + "External id": 3725766,"Record function id": 0, "Sequence number": 37295075, "Fwd thread id": 1, "Ev Idx": 5573 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1625853016871.052, "dur": 38058.031, + "args": { + "External id": 3725767,"Sequence number": 37295075, "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": 1625853016871.052, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.1)", "pid": 1336756, "tid": 1381189, + "ts": 1625853016902.002, "dur": 37.321, + "args": { + "External id": 3725768,"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": 1625853016946.766, "dur": 111.730, + "args": { + "External id": 3725769,"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": 1625853017066.066, "dur": 37854.848, + "args": { + "External id": 3725770,"Record function id": 0, "Ev Idx": 5577 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1625853017162.744, "dur": 6.902, + "args": { + "External id": 3725771,"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": 1625853017179.709, "dur": 5.483, + "args": { + "External id": 3725772,"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": 1625853017202.618, "dur": 36732.640, + "args": { + "External id": 3725773,"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": 1625853017215.776, "dur": 36710.898, + "args": { + "External id": 3725774,"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": 1625853017266.777, "dur": 14.463, + "args": { + "External id": 3725775,"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": 1625853017288.605, "dur": 36598.833, + "args": { + "External id": 3725776,"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": 1625853017291.274, "dur": 36595.354, + "args": { + "External id": 3725777,"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": 1625853017295.670, "dur": 4.843, + "args": { + "External id": 3725778,"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": 1625853017302.263, "dur": 36580.635, + "args": { + "External id": 3725779,"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": 1625853054048.627, "dur": 9.071, + "args": { + "External id": 3725780,"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": 1625853054051.658, "dur": 5.489, + "args": { + "External id": 3725781,"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": 1625853054088.084, "dur": 525.880, + "args": { + "External id": 3725782,"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": 1625853054117.782, "dur": 491.029, + "args": { + "External id": 3725783,"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": 1625853054129.029, "dur": 473.728, + "args": { + "External id": 3725784,"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": 1625853054637.482, "dur": 2.295, + "args": { + "External id": 3725785,"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": 1625853054719.824, "dur": 6.913, + "args": { + "External id": 3725786,"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": 1625853054770.909, "dur": 3.726, + "args": { + "External id": 3725787,"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": 1625853054789.929, "dur": 1.748, + "args": { + "External id": 3725788,"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": 1625853054802.994, "dur": 1.004, + "args": { + "External id": 3725789,"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": 1625853054815.095, "dur": 1.243, + "args": { + "External id": 3725790,"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": 1625853054826.517, "dur": 2.620, + "args": { + "External id": 3725791,"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": 1625853054839.958, "dur": 0.807, + "args": { + "External id": 3725792,"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": 1625853054851.269, "dur": 1.329, + "args": { + "External id": 3725793,"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": 1625853054861.572, "dur": 1.118, + "args": { + "External id": 3725794,"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": 1625853054952.420, "dur": 2225.897, + "args": { + "External id": 3725795,"Record function id": 0, "Ev Idx": 5602 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_backward (model.layers.0)", "pid": 1336756, "tid": 1381189, + "ts": 1625853054971.373, "dur": 491.147, + "args": { + "External id": 3725796,"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": 1625853055021.452, "dur": 331.239, + "args": { + "External id": 3725797,"Record function id": 0, "Ev Idx": 5604 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1381189, + "ts": 1625853055118.372, "dur": 5.053, + "args": { + "External id": 3725798,"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": 1625853055127.124, "dur": 1.079, + "args": { + "External id": 3725799,"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": 1625853055129.977, "dur": 2.856, + "args": { + "External id": 3725800,"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": 1625853055135.098, "dur": 1.003, + "args": { + "External id": 3725801,"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": 1625853055138.238, "dur": 1.141, + "args": { + "External id": 3725802,"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": 1625853055140.906, "dur": 1.464, + "args": { + "External id": 3725803,"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": 1625853055143.834, "dur": 1.088, + "args": { + "External id": 3725804,"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": 1625853055147.280, "dur": 1.266, + "args": { + "External id": 3725805,"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": 1625853055150.331, "dur": 0.868, + "args": { + "External id": 3725806,"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": 1625853055152.797, "dur": 1.392, + "args": { + "External id": 3725807,"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": 1625853055172.772, "dur": 150.700, + "args": { + "External id": 3725808,"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": 1625853055190.811, "dur": 128.396, + "args": { + "External id": 3725809,"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": 1625853055206.000, "dur": 14.809, + "args": { + "External id": 3725810,"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": 1625853055224.172, "dur": 65.342, + "args": { + "External id": 3725811,"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": 1625853055227.035, "dur": 62.124, + "args": { + "External id": 3725812,"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": 1625853055230.897, "dur": 6.102, + "args": { + "External id": 3725813,"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": 1625853055239.259, "dur": 49.303, + "args": { + "External id": 3725814,"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": 1625853055469.853, "dur": 1685.131, + "args": { + "External id": 3725815,"Sequence number": 37295074, "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": 1625853055469.853, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1381189, + "ts": 1625853055576.690, "dur": 117.570, + "args": { + "External id": 3725816,"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": 1625853055742.507, "dur": 42.583, + "args": { + "External id": 3725817,"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": 1625853055802.270, "dur": 54.759, + "args": { + "External id": 3725818,"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": 1625853055869.613, "dur": 34.300, + "args": { + "External id": 3725819,"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": 1625853055911.421, "dur": 46.503, + "args": { + "External id": 3725820,"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": 1625853055965.276, "dur": 67.809, + "args": { + "External id": 3725821,"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": 1625853056045.819, "dur": 46.321, + "args": { + "External id": 3725822,"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": 1625853056116.474, "dur": 24.821, + "args": { + "External id": 3725823,"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": 1625853056160.108, "dur": 30.898, + "args": { + "External id": 3725824,"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": 1625853056234.868, "dur": 22.143, + "args": { + "External id": 3725825,"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": 1625853056270.678, "dur": 15.955, + "args": { + "External id": 3725826,"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": 1625853056295.792, "dur": 30.751, + "args": { + "External id": 3725827,"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": 1625853056329.470, "dur": 33.322, + "args": { + "External id": 3725828,"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": 1625853056393.899, "dur": 167.818, + "args": { + "External id": 3725829,"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": 1625853056470.999, "dur": 6.892, + "args": { + "External id": 3725830,"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": 1625853056479.820, "dur": 2.052, + "args": { + "External id": 3725831,"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": 1625853056595.838, "dur": 25.682, + "args": { + "External id": 3725832,"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": 1625853056632.375, "dur": 15.217, + "args": { + "External id": 3725833,"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": 1625853056655.374, "dur": 51.317, + "args": { + "External id": 3725834,"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": 1625853056716.494, "dur": 38.894, + "args": { + "External id": 3725835,"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": 1625853056764.595, "dur": 22.463, + "args": { + "External id": 3725836,"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": 1625853056793.613, "dur": 29.725, + "args": { + "External id": 3725837,"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": 1625853056829.786, "dur": 22.844, + "args": { + "External id": 3725838,"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": 1625853056862.035, "dur": 31.072, + "args": { + "External id": 3725839,"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": 1625853056910.781, "dur": 25.504, + "args": { + "External id": 3725840,"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": 1625853056952.858, "dur": 25.455, + "args": { + "External id": 3725841,"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": 1625853057043.487, "dur": 21.115, + "args": { + "External id": 3725842,"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": 1625853057081.380, "dur": 15.831, + "args": { + "External id": 3725843,"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": 1625853057109.335, "dur": 16.616, + "args": { + "External id": 3725844,"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": 1625853057200.975, "dur": 15.399, + "args": { + "External id": 3725845,"Record function id": 0, "Ev Idx": 5652 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625853057204.225, "dur": 11.252, + "args": { + "External id": 3725846,"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": 1625853057208.762, "dur": 5.793, + "args": { + "External id": 3725847,"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": 1625853057210.592, "dur": 3.837, + "args": { + "External id": 3725848,"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": 1625853057220.058, "dur": 5.173, + "args": { + "External id": 3725849,"Record function id": 0, "Ev Idx": 5656 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625853057221.717, "dur": 3.117, + "args": { + "External id": 3725850,"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": 1625853057222.578, "dur": 1.588, + "args": { + "External id": 3725851,"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": 1625853057223.212, "dur": 0.854, + "args": { + "External id": 3725852,"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": 1625853057228.332, "dur": 4.377, + "args": { + "External id": 3725853,"Record function id": 0, "Ev Idx": 5660 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625853057229.755, "dur": 2.540, + "args": { + "External id": 3725854,"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": 1625853057230.362, "dur": 1.516, + "args": { + "External id": 3725855,"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": 1625853057230.924, "dur": 0.883, + "args": { + "External id": 3725856,"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": 1625853057235.845, "dur": 4.633, + "args": { + "External id": 3725857,"Record function id": 0, "Ev Idx": 5664 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625853057237.446, "dur": 2.646, + "args": { + "External id": 3725858,"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": 1625853057238.115, "dur": 1.575, + "args": { + "External id": 3725859,"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": 1625853057238.717, "dur": 0.909, + "args": { + "External id": 3725860,"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": 1625853057243.483, "dur": 4.098, + "args": { + "External id": 3725861,"Record function id": 0, "Ev Idx": 5668 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625853057244.982, "dur": 2.194, + "args": { + "External id": 3725862,"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": 1625853057245.680, "dur": 1.039, + "args": { + "External id": 3725863,"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": 1625853057245.929, "dur": 0.723, + "args": { + "External id": 3725864,"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": 1625853057250.776, "dur": 4.789, + "args": { + "External id": 3725865,"Record function id": 0, "Ev Idx": 5672 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625853057252.544, "dur": 2.596, + "args": { + "External id": 3725866,"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": 1625853057253.223, "dur": 1.455, + "args": { + "External id": 3725867,"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": 1625853057253.672, "dur": 0.883, + "args": { + "External id": 3725868,"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": 1625853057258.824, "dur": 6.663, + "args": { + "External id": 3725869,"Record function id": 0, "Ev Idx": 5676 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625853057260.328, "dur": 4.747, + "args": { + "External id": 3725870,"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": 1625853057261.281, "dur": 3.333, + "args": { + "External id": 3725871,"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": 1625853057261.711, "dur": 2.826, + "args": { + "External id": 3725872,"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": 1625853057268.643, "dur": 5.166, + "args": { + "External id": 3725873,"Record function id": 0, "Ev Idx": 5680 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625853057270.489, "dur": 2.917, + "args": { + "External id": 3725874,"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": 1625853057271.238, "dur": 1.500, + "args": { + "External id": 3725875,"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": 1625853057271.916, "dur": 0.729, + "args": { + "External id": 3725876,"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": 1625853057279.955, "dur": 4.628, + "args": { + "External id": 3725877,"Record function id": 0, "Ev Idx": 5684 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625853057281.319, "dur": 2.860, + "args": { + "External id": 3725878,"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": 1625853057281.928, "dur": 1.821, + "args": { + "External id": 3725879,"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": 1625853057282.616, "dur": 1.024, + "args": { + "External id": 3725880,"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": 1625853057288.328, "dur": 35332.245, + "args": { + "External id": 3725881,"Record function id": 0, "Sequence number": 37295073, "Fwd thread id": 1, "Ev Idx": 5688 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "RegisterPostBackwardFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1625853057290.057, "dur": 35321.762, + "args": { + "External id": 3725882,"Sequence number": 37295073, "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": 1625853057290.057, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate (model.layers.0)", "pid": 1336756, "tid": 1381189, + "ts": 1625853057318.106, "dur": 42.392, + "args": { + "External id": 3725883,"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": 1625853057368.481, "dur": 95.234, + "args": { + "External id": 3725884,"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": 1625853057472.769, "dur": 35131.297, + "args": { + "External id": 3725885,"Record function id": 0, "Ev Idx": 5692 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1625853057566.066, "dur": 6.300, + "args": { + "External id": 3725886,"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": 1625853057581.866, "dur": 8.635, + "args": { + "External id": 3725887,"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": 1625853057604.802, "dur": 34217.651, + "args": { + "External id": 3725888,"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": 1625853057618.954, "dur": 34194.712, + "args": { + "External id": 3725889,"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": 1625853057670.840, "dur": 33.186, + "args": { + "External id": 3725890,"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": 1625853057711.082, "dur": 34061.995, + "args": { + "External id": 3725891,"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": 1625853057713.774, "dur": 34058.621, + "args": { + "External id": 3725892,"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": 1625853057719.134, "dur": 5.898, + "args": { + "External id": 3725893,"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": 1625853057726.630, "dur": 34042.429, + "args": { + "External id": 3725894,"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": 1625853091907.670, "dur": 9.226, + "args": { + "External id": 3725895,"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": 1625853091910.213, "dur": 6.312, + "args": { + "External id": 3725896,"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": 1625853091945.921, "dur": 372.321, + "args": { + "External id": 3725897,"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": 1625853091973.818, "dur": 340.041, + "args": { + "External id": 3725898,"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": 1625853092009.963, "dur": 298.782, + "args": { + "External id": 3725899,"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": 1625853092339.385, "dur": 2.161, + "args": { + "External id": 3725900,"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": 1625853092400.154, "dur": 6.481, + "args": { + "External id": 3725901,"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": 1625853092451.320, "dur": 1.546, + "args": { + "External id": 3725902,"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": 1625853092468.315, "dur": 3.346, + "args": { + "External id": 3725903,"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": 1625853092483.263, "dur": 0.761, + "args": { + "External id": 3725904,"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": 1625853092496.357, "dur": 0.716, + "args": { + "External id": 3725905,"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": 1625853092506.409, "dur": 1.079, + "args": { + "External id": 3725906,"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": 1625853092518.582, "dur": 2.948, + "args": { + "External id": 3725907,"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": 1625853092533.335, "dur": 1.210, + "args": { + "External id": 3725908,"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": 1625853092545.285, "dur": 0.843, + "args": { + "External id": 3725909,"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": 1625853092634.358, "dur": 299.303, + "args": { + "External id": 3725910,"Record function id": 0, "Sequence number": 37295072, "Fwd thread id": 1, "Ev Idx": 5717 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunctionBackward", "pid": 1336756, "tid": 1381189, + "ts": 1625853092637.235, "dur": 287.895, + "args": { + "External id": 3725911,"Sequence number": 37295072, "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": 1625853092637.235, + "cat": "fwdbwd", "name": "fwdbwd", "bp": "e" + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_embedding_dense_backward_0", "pid": 1336756, "tid": 1381189, + "ts": 1625853092778.102, "dur": 49.257, + "args": { + "External id": 3725912,"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": 1625853092843.534, "dur": 28.949, + "args": { + "External id": 3725913,"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": 1625853092889.045, "dur": 21.536, + "args": { + "External id": 3725914,"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": 1625853092944.802, "dur": 16.320, + "args": { + "External id": 3725915,"Record function id": 0, "Ev Idx": 5722 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "torch::autograd::AccumulateGrad", "pid": 1336756, "tid": 1381189, + "ts": 1625853092948.860, "dur": 11.341, + "args": { + "External id": 3725916,"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": 1625853092953.428, "dur": 5.940, + "args": { + "External id": 3725917,"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": 1625853092955.215, "dur": 4.061, + "args": { + "External id": 3725918,"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": 1625853093017.695, "dur": 8858.047, + "args": { + "External id": 3725919,"Record function id": 0, "Ev Idx": 5726 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_accumulate", "pid": 1336756, "tid": 1381189, + "ts": 1625853093041.080, "dur": 42.863, + "args": { + "External id": 3725920,"Record function id": 0, "Ev Idx": 5727 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reshard", "pid": 1336756, "tid": 1381189, + "ts": 1625853093090.511, "dur": 309.749, + "args": { + "External id": 3725921,"Record function id": 0, "Ev Idx": 5728 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_backward_reduce", "pid": 1336756, "tid": 1381189, + "ts": 1625853093406.800, "dur": 8178.164, + "args": { + "External id": 3725922,"Record function id": 0, "Ev Idx": 5729 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1381189, + "ts": 1625853093530.592, "dur": 7.362, + "args": { + "External id": 3725923,"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": 1625853093548.551, "dur": 4.993, + "args": { + "External id": 3725924,"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": 1625853093576.072, "dur": 6754.931, + "args": { + "External id": 3725925,"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": 1625853093595.321, "dur": 6722.168, + "args": { + "External id": 3725926,"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": 1625853093952.916, "dur": 19.801, + "args": { + "External id": 3725927,"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": 1625853094109.339, "dur": 6158.789, + "args": { + "External id": 3725928,"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": 1625853094112.488, "dur": 6154.647, + "args": { + "External id": 3725929,"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": 1625853094118.369, "dur": 15.568, + "args": { + "External id": 3725930,"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": 1625853094136.336, "dur": 6125.244, + "args": { + "External id": 3725931,"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": 1625853100466.082, "dur": 11.398, + "args": { + "External id": 3725932,"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": 1625853100469.544, "dur": 7.526, + "args": { + "External id": 3725933,"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": 1625853100508.726, "dur": 390.027, + "args": { + "External id": 3725934,"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": 1625853100535.186, "dur": 358.676, + "args": { + "External id": 3725935,"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": 1625853100551.678, "dur": 336.111, + "args": { + "External id": 3725936,"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": 1625853100917.324, "dur": 2.328, + "args": { + "External id": 3725937,"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": 1625853100975.303, "dur": 39.077, + "args": { + "External id": 3725938,"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": 1625853101061.180, "dur": 2.072, + "args": { + "External id": 3725939,"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": 1625853101078.505, "dur": 1.166, + "args": { + "External id": 3725940,"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": 1625853101091.881, "dur": 3.012, + "args": { + "External id": 3725941,"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": 1625853101106.527, "dur": 1.595, + "args": { + "External id": 3725942,"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": 1625853101118.560, "dur": 1.486, + "args": { + "External id": 3725943,"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": 1625853101133.331, "dur": 2.108, + "args": { + "External id": 3725944,"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": 1625853101146.491, "dur": 3.022, + "args": { + "External id": 3725945,"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": 1625853101161.206, "dur": 2.206, + "args": { + "External id": 3725946,"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": 1625853101173.569, "dur": 1.540, + "args": { + "External id": 3725947,"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": 1625853101185.420, "dur": 1.404, + "args": { + "External id": 3725948,"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": 1625853101196.609, "dur": 2.815, + "args": { + "External id": 3725949,"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": 1625853101210.310, "dur": 1.399, + "args": { + "External id": 3725950,"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": 1625853101221.849, "dur": 1.174, + "args": { + "External id": 3725951,"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": 1625853101233.449, "dur": 1.148, + "args": { + "External id": 3725952,"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": 1625853101244.075, "dur": 3.062, + "args": { + "External id": 3725953,"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": 1625853101257.208, "dur": 1.267, + "args": { + "External id": 3725954,"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": 1625853101268.375, "dur": 1.604, + "args": { + "External id": 3725955,"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": 1625853101279.706, "dur": 1.647, + "args": { + "External id": 3725956,"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": 1625853101290.468, "dur": 3.483, + "args": { + "External id": 3725957,"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": 1625853101304.632, "dur": 1.511, + "args": { + "External id": 3725958,"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": 1625853101315.459, "dur": 1.528, + "args": { + "External id": 3725959,"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": 1625853101327.001, "dur": 1.648, + "args": { + "External id": 3725960,"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": 1625853101339.480, "dur": 3.305, + "args": { + "External id": 3725961,"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": 1625853101353.135, "dur": 1.060, + "args": { + "External id": 3725962,"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": 1625853101364.892, "dur": 1.237, + "args": { + "External id": 3725963,"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": 1625853101377.108, "dur": 1.039, + "args": { + "External id": 3725964,"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": 1625853101388.354, "dur": 3.209, + "args": { + "External id": 3725965,"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": 1625853101401.074, "dur": 1.639, + "args": { + "External id": 3725966,"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": 1625853101414.058, "dur": 1.388, + "args": { + "External id": 3725967,"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": 1625853101425.874, "dur": 1.745, + "args": { + "External id": 3725968,"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": 1625853101437.335, "dur": 3.163, + "args": { + "External id": 3725969,"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": 1625853101451.384, "dur": 1.592, + "args": { + "External id": 3725970,"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": 1625853101463.052, "dur": 0.972, + "args": { + "External id": 3725971,"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": 1625853101474.531, "dur": 1.214, + "args": { + "External id": 3725972,"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": 1625853101485.947, "dur": 2.992, + "args": { + "External id": 3725973,"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": 1625853101499.358, "dur": 1.372, + "args": { + "External id": 3725974,"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": 1625853101510.501, "dur": 1.443, + "args": { + "External id": 3725975,"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": 1625853101521.923, "dur": 1.371, + "args": { + "External id": 3725976,"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#155135", "pid": 1336756, "tid": 1336756, + "ts": 1625851009931.035, "dur": 2110179.904, + "args": { + "External id": 3715073,"Record function id": 0, "Ev Idx": 5784 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "Optimizer.zero_grad#AdamW.zero_grad", "pid": 1336756, "tid": 1336756, + "ts": 1625851009964.905, "dur": 789.446, + "args": { + "External id": 3715074,"Record function id": 0, "Ev Idx": 5785 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "enumerate(DataLoader)#_StatefulMultiProcessingDataLoaderIter.__next__", "pid": 1336756, "tid": 1336756, + "ts": 1625851010798.165, "dur": 81.114, + "args": { + "External id": 3715075,"Record function id": 0, "Ev Idx": 5786 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1336756, + "ts": 1625851011769.601, "dur": 18.268, + "args": { + "External id": 3715076,"Sequence number": 37295072, "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": 1625851011781.245, "dur": 2.428, + "args": { + "External id": 3715077,"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": 1625851011789.608, "dur": 3.814, + "args": { + "External id": 3715078,"Sequence number": 37295072, "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": 1625851011791.573, "dur": 0.831, + "args": { + "External id": 3715079,"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": 1625851011819.389, "dur": 627.454, + "args": { + "External id": 3715080,"Sequence number": 37295072, "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": 1625851011826.993, "dur": 619.265, + "args": { + "External id": 3715081,"Sequence number": 37295072, "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": 1625851011835.639, "dur": 10.166, + "args": { + "External id": 3715082,"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": 1625851011848.295, "dur": 596.236, + "args": { + "External id": 3715083,"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": 1625851011858.200, "dur": 0.363, + "args": { + "External id": 3715084,"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": 1625851011861.550, "dur": 8.915, + "args": { + "External id": 3715085,"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": 1625851011866.159, "dur": 4.158, + "args": { + "External id": 3715086,"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": 1625851011869.390, "dur": 0.573, + "args": { + "External id": 3715087,"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": 1625851011872.788, "dur": 316.196, + "args": { + "External id": 3715088,"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": 1625851011875.268, "dur": 313.127, + "args": { + "External id": 3715089,"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": 1625851011877.706, "dur": 12.246, + "args": { + "External id": 3715090,"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": 1625851011884.657, "dur": 4.842, + "args": { + "External id": 3715091,"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": 1625851011890.855, "dur": 295.991, + "args": { + "External id": 3715092,"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": 1625851012194.409, "dur": 247.627, + "args": { + "External id": 3715093,"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": 1625851012462.513, "dur": 816.394, + "args": { + "External id": 3715094,"Sequence number": 37295072, "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": 1625851012464.234, "dur": 813.810, + "args": { + "External id": 3715095,"Sequence number": 37295072, "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": 1625851012469.927, "dur": 9.417, + "args": { + "External id": 3715096,"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": 1625851012480.527, "dur": 792.406, + "args": { + "External id": 3715097,"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": 1625851013313.234, "dur": 59.118, + "args": { + "External id": 3715098,"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": 1625851013320.418, "dur": 6.163, + "args": { + "External id": 3715099,"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": 1625851013329.781, "dur": 42.182, + "args": { + "External id": 3715100,"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": 1625851013337.034, "dur": 6.982, + "args": { + "External id": 3715101,"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": 1625851013384.181, "dur": 69.284, + "args": { + "External id": 3715102,"Sequence number": 37295072, "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": 1625851013389.797, "dur": 8.959, + "args": { + "External id": 3715103,"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": 1625851013396.376, "dur": 2.010, + "args": { + "External id": 3715104,"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": 1625851013399.707, "dur": 3.678, + "args": { + "External id": 3715105,"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": 1625851013406.580, "dur": 3.502, + "args": { + "External id": 3715106,"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": 1625851013412.599, "dur": 6.457, + "args": { + "External id": 3715107,"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": 1625851013418.403, "dur": 0.473, + "args": { + "External id": 3715108,"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": 1625851013419.892, "dur": 1.973, + "args": { + "External id": 3715109,"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": 1625851013421.029, "dur": 0.753, + "args": { + "External id": 3715110,"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": 1625851013423.853, "dur": 3.460, + "args": { + "External id": 3715111,"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": 1625851013425.151, "dur": 2.063, + "args": { + "External id": 3715112,"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": 1625851013426.241, "dur": 0.656, + "args": { + "External id": 3715113,"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": 1625851013428.305, "dur": 24.449, + "args": { + "External id": 3715114,"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": 1625851013463.659, "dur": 28.453, + "args": { + "External id": 3715115,"Sequence number": 37295072, "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": 1625851013465.291, "dur": 26.646, + "args": { + "External id": 3715116,"Sequence number": 37295072, "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": 1625851013470.047, "dur": 3.343, + "args": { + "External id": 3715117,"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": 1625851013473.967, "dur": 17.543, + "args": { + "External id": 3715118,"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": 1625851013601.588, "dur": 165.649, + "args": { + "External id": 3715119,"Record function id": 0, "Ev Idx": 5830 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::inputs_to_device", "pid": 1336756, "tid": 1336756, + "ts": 1625851013698.766, "dur": 57.852, + "args": { + "External id": 3715120,"Record function id": 0, "Ev Idx": 5831 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 1336756, "tid": 1336756, + "ts": 1625851013774.015, "dur": 44.041, + "args": { + "External id": 3715121,"Record function id": 0, "Ev Idx": 5832 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward", "pid": 1336756, "tid": 1336756, + "ts": 1625851013828.645, "dur": 10761.496, + "args": { + "External id": 3715122,"Record function id": 0, "Ev Idx": 5833 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather", "pid": 1336756, "tid": 1336756, + "ts": 1625851013837.429, "dur": 1313.129, + "args": { + "External id": 3715123,"Record function id": 0, "Ev Idx": 5834 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1625851013951.034, "dur": 7.584, + "args": { + "External id": 3715124,"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": 1625851013979.626, "dur": 156.493, + "args": { + "External id": 3715125,"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": 1625851014020.115, "dur": 1.622, + "args": { + "External id": 3715126,"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": 1625851014026.238, "dur": 2.657, + "args": { + "External id": 3715127,"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": 1625851014029.775, "dur": 0.382, + "args": { + "External id": 3715128,"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": 1625851014030.857, "dur": 1.831, + "args": { + "External id": 3715129,"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": 1625851014037.868, "dur": 0.315, + "args": { + "External id": 3715130,"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": 1625851014038.868, "dur": 0.328, + "args": { + "External id": 3715131,"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": 1625851014042.169, "dur": 0.394, + "args": { + "External id": 3715132,"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": 1625851014044.964, "dur": 0.359, + "args": { + "External id": 3715133,"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": 1625851014045.832, "dur": 0.269, + "args": { + "External id": 3715134,"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": 1625851014048.471, "dur": 1.892, + "args": { + "External id": 3715135,"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": 1625851014050.891, "dur": 0.489, + "args": { + "External id": 3715136,"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": 1625851014051.888, "dur": 1.430, + "args": { + "External id": 3715137,"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": 1625851014057.308, "dur": 0.252, + "args": { + "External id": 3715138,"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": 1625851014058.305, "dur": 0.182, + "args": { + "External id": 3715139,"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": 1625851014061.525, "dur": 0.390, + "args": { + "External id": 3715140,"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": 1625851014064.613, "dur": 0.303, + "args": { + "External id": 3715141,"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": 1625851014065.532, "dur": 0.381, + "args": { + "External id": 3715142,"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": 1625851014068.147, "dur": 1.895, + "args": { + "External id": 3715143,"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": 1625851014070.556, "dur": 0.176, + "args": { + "External id": 3715144,"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": 1625851014071.483, "dur": 1.468, + "args": { + "External id": 3715145,"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": 1625851014077.327, "dur": 0.254, + "args": { + "External id": 3715146,"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": 1625851014078.195, "dur": 0.266, + "args": { + "External id": 3715147,"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": 1625851014080.484, "dur": 0.409, + "args": { + "External id": 3715148,"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": 1625851014083.136, "dur": 0.264, + "args": { + "External id": 3715149,"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": 1625851014083.879, "dur": 0.400, + "args": { + "External id": 3715150,"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": 1625851014086.287, "dur": 2.427, + "args": { + "External id": 3715151,"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": 1625851014089.334, "dur": 0.313, + "args": { + "External id": 3715152,"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": 1625851014090.116, "dur": 1.497, + "args": { + "External id": 3715153,"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": 1625851014096.087, "dur": 0.260, + "args": { + "External id": 3715154,"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": 1625851014096.984, "dur": 0.397, + "args": { + "External id": 3715155,"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": 1625851014100.218, "dur": 0.265, + "args": { + "External id": 3715156,"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": 1625851014102.624, "dur": 0.237, + "args": { + "External id": 3715157,"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": 1625851014103.521, "dur": 0.277, + "args": { + "External id": 3715158,"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": 1625851014106.313, "dur": 2.228, + "args": { + "External id": 3715159,"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": 1625851014108.996, "dur": 0.362, + "args": { + "External id": 3715160,"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": 1625851014109.818, "dur": 1.583, + "args": { + "External id": 3715161,"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": 1625851014116.436, "dur": 0.298, + "args": { + "External id": 3715162,"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": 1625851014117.347, "dur": 0.373, + "args": { + "External id": 3715163,"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": 1625851014119.957, "dur": 0.290, + "args": { + "External id": 3715164,"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": 1625851014159.637, "dur": 80.700, + "args": { + "External id": 3715165,"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": 1625851014311.101, "dur": 250.883, + "args": { + "External id": 3715166,"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": 1625851014327.920, "dur": 6.322, + "args": { + "External id": 3715167,"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": 1625851014342.865, "dur": 12.440, + "args": { + "External id": 3715168,"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": 1625851014347.261, "dur": 7.623, + "args": { + "External id": 3715169,"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": 1625851014352.007, "dur": 0.546, + "args": { + "External id": 3715170,"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": 1625851014363.055, "dur": 106.750, + "args": { + "External id": 3715171,"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": 1625851014364.945, "dur": 0.548, + "args": { + "External id": 3715172,"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": 1625851014368.325, "dur": 0.418, + "args": { + "External id": 3715173,"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": 1625851014369.572, "dur": 1.658, + "args": { + "External id": 3715174,"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": 1625851014371.793, "dur": 0.592, + "args": { + "External id": 3715175,"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": 1625851014375.192, "dur": 0.366, + "args": { + "External id": 3715176,"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": 1625851014376.272, "dur": 0.190, + "args": { + "External id": 3715177,"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": 1625851014377.561, "dur": 0.294, + "args": { + "External id": 3715178,"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": 1625851014380.312, "dur": 0.167, + "args": { + "External id": 3715179,"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": 1625851014381.194, "dur": 0.686, + "args": { + "External id": 3715180,"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": 1625851014384.166, "dur": 0.382, + "args": { + "External id": 3715181,"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": 1625851014386.871, "dur": 1.400, + "args": { + "External id": 3715182,"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": 1625851014388.816, "dur": 0.440, + "args": { + "External id": 3715183,"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": 1625851014391.451, "dur": 0.495, + "args": { + "External id": 3715184,"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": 1625851014393.843, "dur": 0.293, + "args": { + "External id": 3715185,"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": 1625851014394.943, "dur": 0.249, + "args": { + "External id": 3715186,"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": 1625851014398.080, "dur": 1.634, + "args": { + "External id": 3715187,"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": 1625851014400.534, "dur": 0.448, + "args": { + "External id": 3715188,"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": 1625851014402.789, "dur": 0.529, + "args": { + "External id": 3715189,"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": 1625851014405.789, "dur": 1.853, + "args": { + "External id": 3715190,"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": 1625851014408.142, "dur": 0.507, + "args": { + "External id": 3715191,"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": 1625851014411.213, "dur": 0.434, + "args": { + "External id": 3715192,"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": 1625851014414.034, "dur": 0.143, + "args": { + "External id": 3715193,"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": 1625851014414.834, "dur": 0.384, + "args": { + "External id": 3715194,"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": 1625851014417.512, "dur": 2.030, + "args": { + "External id": 3715195,"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": 1625851014420.611, "dur": 0.126, + "args": { + "External id": 3715196,"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": 1625851014423.060, "dur": 0.398, + "args": { + "External id": 3715197,"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": 1625851014425.872, "dur": 1.369, + "args": { + "External id": 3715198,"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": 1625851014427.831, "dur": 0.287, + "args": { + "External id": 3715199,"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": 1625851014431.036, "dur": 0.405, + "args": { + "External id": 3715200,"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": 1625851014433.801, "dur": 0.277, + "args": { + "External id": 3715201,"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": 1625851014434.923, "dur": 0.382, + "args": { + "External id": 3715202,"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": 1625851014437.808, "dur": 1.936, + "args": { + "External id": 3715203,"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": 1625851014440.514, "dur": 0.391, + "args": { + "External id": 3715204,"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": 1625851014443.220, "dur": 0.298, + "args": { + "External id": 3715205,"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": 1625851014446.091, "dur": 1.185, + "args": { + "External id": 3715206,"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": 1625851014447.942, "dur": 0.276, + "args": { + "External id": 3715207,"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": 1625851014450.775, "dur": 0.490, + "args": { + "External id": 3715208,"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": 1625851014453.676, "dur": 0.157, + "args": { + "External id": 3715209,"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": 1625851014454.540, "dur": 0.225, + "args": { + "External id": 3715210,"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": 1625851014489.908, "dur": 56.227, + "args": { + "External id": 3715211,"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": 1625851014620.356, "dur": 414.895, + "args": { + "External id": 3715212,"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": 1625851014659.874, "dur": 369.110, + "args": { + "External id": 3715213,"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": 1625851014670.582, "dur": 350.996, + "args": { + "External id": 3715214,"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": 1625851015061.111, "dur": 2.773, + "args": { + "External id": 3715215,"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": 1625851015167.052, "dur": 9222.858, + "args": { + "External id": 3715216,"Record function id": 0, "Ev Idx": 5927 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1625851015387.044, "dur": 6.499, + "args": { + "External id": 3715217,"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": 1625851015397.456, "dur": 1.154, + "args": { + "External id": 3715218,"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": 1625851015400.289, "dur": 1.150, + "args": { + "External id": 3715219,"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": 1625851015404.580, "dur": 2.570, + "args": { + "External id": 3715220,"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": 1625851015408.388, "dur": 0.882, + "args": { + "External id": 3715221,"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": 1625851015410.614, "dur": 1.040, + "args": { + "External id": 3715222,"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": 1625851015412.958, "dur": 1.220, + "args": { + "External id": 3715223,"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": 1625851015419.267, "dur": 1.992, + "args": { + "External id": 3715224,"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": 1625851015422.644, "dur": 1.009, + "args": { + "External id": 3715225,"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": 1625851015424.996, "dur": 0.851, + "args": { + "External id": 3715226,"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": 1625851015427.264, "dur": 0.854, + "args": { + "External id": 3715227,"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": 1625851015431.256, "dur": 1.856, + "args": { + "External id": 3715228,"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": 1625851015434.427, "dur": 0.585, + "args": { + "External id": 3715229,"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": 1625851015436.493, "dur": 0.980, + "args": { + "External id": 3715230,"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": 1625851015438.896, "dur": 0.767, + "args": { + "External id": 3715231,"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": 1625851015444.580, "dur": 1.665, + "args": { + "External id": 3715232,"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": 1625851015447.484, "dur": 0.817, + "args": { + "External id": 3715233,"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": 1625851015449.572, "dur": 0.804, + "args": { + "External id": 3715234,"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": 1625851015451.616, "dur": 0.787, + "args": { + "External id": 3715235,"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": 1625851015455.440, "dur": 1.671, + "args": { + "External id": 3715236,"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": 1625851015458.367, "dur": 0.540, + "args": { + "External id": 3715237,"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": 1625851015460.205, "dur": 0.678, + "args": { + "External id": 3715238,"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": 1625851015462.114, "dur": 0.659, + "args": { + "External id": 3715239,"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": 1625851015467.526, "dur": 1.649, + "args": { + "External id": 3715240,"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": 1625851015470.699, "dur": 0.833, + "args": { + "External id": 3715241,"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": 1625851015472.897, "dur": 0.781, + "args": { + "External id": 3715242,"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": 1625851015475.213, "dur": 0.879, + "args": { + "External id": 3715243,"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": 1625851015478.593, "dur": 1.708, + "args": { + "External id": 3715244,"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": 1625851015481.562, "dur": 0.757, + "args": { + "External id": 3715245,"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": 1625851015484.233, "dur": 0.661, + "args": { + "External id": 3715246,"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": 1625851015486.308, "dur": 0.627, + "args": { + "External id": 3715247,"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": 1625851015491.430, "dur": 1.461, + "args": { + "External id": 3715248,"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": 1625851015494.534, "dur": 0.608, + "args": { + "External id": 3715249,"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": 1625851015496.579, "dur": 0.608, + "args": { + "External id": 3715250,"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": 1625851015498.734, "dur": 0.733, + "args": { + "External id": 3715251,"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": 1625851015502.311, "dur": 1.393, + "args": { + "External id": 3715252,"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": 1625851015504.833, "dur": 0.858, + "args": { + "External id": 3715253,"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": 1625851015522.073, "dur": 0.806, + "args": { + "External id": 3715254,"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": 1625851015524.273, "dur": 0.429, + "args": { + "External id": 3715255,"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": 1625851015528.826, "dur": 1.610, + "args": { + "External id": 3715256,"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": 1625851015556.589, "dur": 8780.294, + "args": { + "External id": 3715257,"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": 1625851015580.505, "dur": 8747.635, + "args": { + "External id": 3715258,"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": 1625851015600.454, "dur": 5.700, + "args": { + "External id": 3715259,"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": 1625851015612.101, "dur": 8675.642, + "args": { + "External id": 3715260,"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": 1625851015614.827, "dur": 8672.283, + "args": { + "External id": 3715261,"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": 1625851015621.294, "dur": 5.184, + "args": { + "External id": 3715262,"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": 1625851015628.285, "dur": 8655.352, + "args": { + "External id": 3715263,"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": 1625851024668.495, "dur": 50.002, + "args": { + "External id": 3715264,"Record function id": 0, "Ev Idx": 5975 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 0/0", "pid": 1336756, "tid": 1336756, + "ts": 1625851024720.706, "dur": 212.910, + "args": { + "External id": 3715265,"Record function id": 0, "Ev Idx": 5976 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 1336756, "tid": 1336756, + "ts": 1625851024761.304, "dur": 163.227, + "args": { + "External id": 3715266,"Sequence number": 37295072, "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": 1625851024761.304, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "triton_poi_fused_embedding_0", "pid": 1336756, "tid": 1336756, + "ts": 1625851024834.094, "dur": 52.245, + "args": { + "External id": 3715267,"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": 1625851025032.181, "dur": 57.085, + "args": { + "External id": 3715268,"Record function id": 0, "Ev Idx": 5979 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.0)", "pid": 1336756, "tid": 1336756, + "ts": 1625851025100.161, "dur": 7310.162, + "args": { + "External id": 3715269,"Record function id": 0, "Ev Idx": 5980 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.0)", "pid": 1336756, "tid": 1336756, + "ts": 1625851025108.058, "dur": 779.871, + "args": { + "External id": 3715270,"Record function id": 0, "Ev Idx": 5981 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1625851025185.054, "dur": 12.162, + "args": { + "External id": 3715271,"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": 1625851025211.524, "dur": 39.694, + "args": { + "External id": 3715272,"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": 1625851025220.227, "dur": 2.505, + "args": { + "External id": 3715273,"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": 1625851025224.334, "dur": 0.480, + "args": { + "External id": 3715274,"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": 1625851025227.307, "dur": 2.283, + "args": { + "External id": 3715275,"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": 1625851025230.476, "dur": 0.405, + "args": { + "External id": 3715276,"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": 1625851025231.594, "dur": 0.147, + "args": { + "External id": 3715277,"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": 1625851025236.041, "dur": 0.153, + "args": { + "External id": 3715278,"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": 1625851025236.971, "dur": 0.323, + "args": { + "External id": 3715279,"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": 1625851025238.184, "dur": 1.848, + "args": { + "External id": 3715280,"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": 1625851025244.450, "dur": 0.185, + "args": { + "External id": 3715281,"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": 1625851025261.539, "dur": 37.336, + "args": { + "External id": 3715282,"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": 1625851025330.083, "dur": 103.722, + "args": { + "External id": 3715283,"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": 1625851025342.433, "dur": 4.352, + "args": { + "External id": 3715284,"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": 1625851025351.513, "dur": 9.052, + "args": { + "External id": 3715285,"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": 1625851025355.773, "dur": 4.400, + "args": { + "External id": 3715286,"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": 1625851025358.634, "dur": 0.460, + "args": { + "External id": 3715287,"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": 1625851025367.068, "dur": 28.478, + "args": { + "External id": 3715288,"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": 1625851025370.152, "dur": 0.385, + "args": { + "External id": 3715289,"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": 1625851025371.665, "dur": 0.423, + "args": { + "External id": 3715290,"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": 1625851025374.583, "dur": 0.520, + "args": { + "External id": 3715291,"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": 1625851025377.772, "dur": 0.681, + "args": { + "External id": 3715292,"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": 1625851025379.121, "dur": 2.744, + "args": { + "External id": 3715293,"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": 1625851025382.783, "dur": 0.294, + "args": { + "External id": 3715294,"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": 1625851025385.461, "dur": 0.444, + "args": { + "External id": 3715295,"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": 1625851025388.545, "dur": 0.189, + "args": { + "External id": 3715296,"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": 1625851025390.973, "dur": 0.402, + "args": { + "External id": 3715297,"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": 1625851025404.839, "dur": 21.245, + "args": { + "External id": 3715298,"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": 1625851025482.831, "dur": 315.612, + "args": { + "External id": 3715299,"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": 1625851025508.223, "dur": 284.996, + "args": { + "External id": 3715300,"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": 1625851025518.407, "dur": 269.205, + "args": { + "External id": 3715301,"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": 1625851025820.428, "dur": 2.302, + "args": { + "External id": 3715302,"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": 1625851025909.079, "dur": 6290.541, + "args": { + "External id": 3715303,"Record function id": 0, "Ev Idx": 6014 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1625851026068.712, "dur": 6.725, + "args": { + "External id": 3715304,"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": 1625851026079.448, "dur": 1.221, + "args": { + "External id": 3715305,"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": 1625851026082.280, "dur": 1.089, + "args": { + "External id": 3715306,"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": 1625851026085.238, "dur": 2.354, + "args": { + "External id": 3715307,"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": 1625851026089.121, "dur": 1.071, + "args": { + "External id": 3715308,"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": 1625851026091.425, "dur": 1.043, + "args": { + "External id": 3715309,"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": 1625851026096.464, "dur": 0.762, + "args": { + "External id": 3715310,"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": 1625851026098.513, "dur": 1.931, + "args": { + "External id": 3715311,"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": 1625851026101.911, "dur": 0.951, + "args": { + "External id": 3715312,"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": 1625851026104.097, "dur": 0.691, + "args": { + "External id": 3715313,"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": 1625851026125.907, "dur": 6035.578, + "args": { + "External id": 3715314,"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": 1625851026143.203, "dur": 6011.289, + "args": { + "External id": 3715315,"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": 1625851026170.105, "dur": 12.394, + "args": { + "External id": 3715316,"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": 1625851026186.603, "dur": 5934.750, + "args": { + "External id": 3715317,"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": 1625851026189.091, "dur": 5931.703, + "args": { + "External id": 3715318,"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": 1625851026194.275, "dur": 5.803, + "args": { + "External id": 3715319,"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": 1625851026201.865, "dur": 5916.149, + "args": { + "External id": 3715320,"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": 1625851032356.241, "dur": 30.364, + "args": { + "External id": 3715321,"Sequence number": 37295073, "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": 1625851032356.241, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 1336756, "tid": 1336756, + "ts": 1625851032372.756, "dur": 9.396, + "args": { + "External id": 3715322,"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": 1625851032377.952, "dur": 4.007, + "args": { + "External id": 3715323,"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": 1625851032448.634, "dur": 94.211, + "args": { + "External id": 3715324,"Record function id": 0, "Ev Idx": 6035 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 1336756, "tid": 1336756, + "ts": 1625851032544.400, "dur": 1674.350, + "args": { + "External id": 3715325,"Record function id": 0, "Ev Idx": 6036 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 1336756, "tid": 1336756, + "ts": 1625851032586.098, "dur": 1605.851, + "args": { + "External id": 3715326,"Sequence number": 37295074, "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": 1625851032586.098, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 1336756, "tid": 1336756, + "ts": 1625851032650.181, "dur": 79.389, + "args": { + "External id": 3715327,"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": 1625851032745.413, "dur": 107.451, + "args": { + "External id": 3715328,"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": 1625851032865.325, "dur": 38.221, + "args": { + "External id": 3715329,"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": 1625851032911.769, "dur": 30.691, + "args": { + "External id": 3715330,"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": 1625851032970.435, "dur": 94.900, + "args": { + "External id": 3715331,"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": 1625851033085.963, "dur": 17.246, + "args": { + "External id": 3715332,"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": 1625851033122.677, "dur": 134.288, + "args": { + "External id": 3715333,"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": 1625851033178.343, "dur": 11.299, + "args": { + "External id": 3715334,"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": 1625851033183.267, "dur": 5.700, + "args": { + "External id": 3715335,"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": 1625851033194.423, "dur": 3.846, + "args": { + "External id": 3715336,"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": 1625851033199.377, "dur": 0.984, + "args": { + "External id": 3715337,"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": 1625851033202.464, "dur": 2.897, + "args": { + "External id": 3715338,"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": 1625851033267.742, "dur": 165.475, + "args": { + "External id": 3715339,"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": 1625851033559.221, "dur": 66.641, + "args": { + "External id": 3715340,"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": 1625851033641.338, "dur": 136.450, + "args": { + "External id": 3715341,"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": 1625851033794.453, "dur": 41.745, + "args": { + "External id": 3715342,"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": 1625851033871.254, "dur": 33.740, + "args": { + "External id": 3715343,"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": 1625851033912.778, "dur": 38.524, + "args": { + "External id": 3715344,"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": 1625851034026.660, "dur": 27.479, + "args": { + "External id": 3715345,"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": 1625851034325.674, "dur": 115.159, + "args": { + "External id": 3715346,"Record function id": 0, "Ev Idx": 6057 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 1336756, "tid": 1336756, + "ts": 1625851034541.868, "dur": 52.194, + "args": { + "External id": 3715347,"Record function id": 0, "Ev Idx": 6058 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.1)", "pid": 1336756, "tid": 1336756, + "ts": 1625851034603.401, "dur": 17055.365, + "args": { + "External id": 3715348,"Record function id": 0, "Ev Idx": 6059 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.1)", "pid": 1336756, "tid": 1336756, + "ts": 1625851034616.892, "dur": 1151.474, + "args": { + "External id": 3715349,"Record function id": 0, "Ev Idx": 6060 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1625851034742.153, "dur": 11.984, + "args": { + "External id": 3715350,"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": 1625851034775.102, "dur": 54.422, + "args": { + "External id": 3715351,"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": 1625851034780.948, "dur": 4.662, + "args": { + "External id": 3715352,"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": 1625851034787.401, "dur": 0.749, + "args": { + "External id": 3715353,"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": 1625851034792.290, "dur": 0.627, + "args": { + "External id": 3715354,"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": 1625851034797.202, "dur": 0.428, + "args": { + "External id": 3715355,"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": 1625851034798.365, "dur": 3.049, + "args": { + "External id": 3715356,"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": 1625851034804.972, "dur": 0.638, + "args": { + "External id": 3715357,"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": 1625851034809.643, "dur": 0.523, + "args": { + "External id": 3715358,"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": 1625851034813.358, "dur": 0.568, + "args": { + "External id": 3715359,"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": 1625851034814.855, "dur": 3.616, + "args": { + "External id": 3715360,"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": 1625851034842.290, "dur": 48.648, + "args": { + "External id": 3715361,"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": 1625851034934.862, "dur": 186.605, + "args": { + "External id": 3715362,"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": 1625851034947.049, "dur": 4.333, + "args": { + "External id": 3715363,"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": 1625851034957.641, "dur": 10.141, + "args": { + "External id": 3715364,"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": 1625851034962.686, "dur": 4.675, + "args": { + "External id": 3715365,"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": 1625851034965.575, "dur": 0.563, + "args": { + "External id": 3715366,"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": 1625851034974.230, "dur": 89.409, + "args": { + "External id": 3715367,"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": 1625851034979.380, "dur": 0.583, + "args": { + "External id": 3715368,"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": 1625851035025.057, "dur": 3.554, + "args": { + "External id": 3715369,"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": 1625851035030.251, "dur": 3.047, + "args": { + "External id": 3715370,"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": 1625851035037.055, "dur": 0.650, + "args": { + "External id": 3715371,"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": 1625851035038.611, "dur": 0.520, + "args": { + "External id": 3715372,"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": 1625851035045.380, "dur": 0.533, + "args": { + "External id": 3715373,"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": 1625851035047.096, "dur": 0.473, + "args": { + "External id": 3715374,"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": 1625851035048.906, "dur": 0.562, + "args": { + "External id": 3715375,"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": 1625851035055.613, "dur": 0.562, + "args": { + "External id": 3715376,"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": 1625851035078.958, "dur": 30.945, + "args": { + "External id": 3715377,"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": 1625851035183.274, "dur": 443.040, + "args": { + "External id": 3715378,"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": 1625851035225.277, "dur": 395.710, + "args": { + "External id": 3715379,"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": 1625851035235.816, "dur": 378.873, + "args": { + "External id": 3715380,"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": 1625851035655.665, "dur": 2.617, + "args": { + "External id": 3715381,"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": 1625851035793.050, "dur": 15651.706, + "args": { + "External id": 3715382,"Record function id": 0, "Ev Idx": 6093 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1625851035903.308, "dur": 6.385, + "args": { + "External id": 3715383,"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": 1625851035913.585, "dur": 1.131, + "args": { + "External id": 3715384,"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": 1625851035916.425, "dur": 1.542, + "args": { + "External id": 3715385,"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": 1625851035919.732, "dur": 1.241, + "args": { + "External id": 3715386,"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": 1625851035922.829, "dur": 1.271, + "args": { + "External id": 3715387,"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": 1625851035928.627, "dur": 1.245, + "args": { + "External id": 3715388,"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": 1625851035931.470, "dur": 1.219, + "args": { + "External id": 3715389,"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": 1625851035934.525, "dur": 6.390, + "args": { + "External id": 3715390,"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": 1625851035942.646, "dur": 0.981, + "args": { + "External id": 3715391,"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": 1625851035947.740, "dur": 1.005, + "args": { + "External id": 3715392,"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": 1625851035970.519, "dur": 15435.269, + "args": { + "External id": 3715393,"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": 1625851036041.885, "dur": 15357.564, + "args": { + "External id": 3715394,"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": 1625851036084.028, "dur": 14.869, + "args": { + "External id": 3715395,"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": 1625851036104.634, "dur": 15261.421, + "args": { + "External id": 3715396,"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": 1625851036107.779, "dur": 15257.798, + "args": { + "External id": 3715397,"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": 1625851036114.557, "dur": 5.982, + "args": { + "External id": 3715398,"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": 1625851036122.922, "dur": 15239.876, + "args": { + "External id": 3715399,"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": 1625851051599.251, "dur": 31.730, + "args": { + "External id": 3715400,"Sequence number": 37295075, "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": 1625851051599.251, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 1336756, "tid": 1336756, + "ts": 1625851051619.661, "dur": 7.063, + "args": { + "External id": 3715401,"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": 1625851051622.648, "dur": 3.847, + "args": { + "External id": 3715402,"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": 1625851051734.223, "dur": 173.914, + "args": { + "External id": 3715403,"Record function id": 0, "Ev Idx": 6114 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 1336756, "tid": 1336756, + "ts": 1625851051910.271, "dur": 1244.507, + "args": { + "External id": 3715404,"Record function id": 0, "Ev Idx": 6115 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 1336756, "tid": 1336756, + "ts": 1625851051967.706, "dur": 1171.275, + "args": { + "External id": 3715405,"Sequence number": 37295076, "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": 1625851051967.706, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 1336756, "tid": 1336756, + "ts": 1625851052097.377, "dur": 49.567, + "args": { + "External id": 3715406,"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": 1625851052163.097, "dur": 109.543, + "args": { + "External id": 3715407,"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": 1625851052281.097, "dur": 40.382, + "args": { + "External id": 3715408,"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": 1625851052327.644, "dur": 30.444, + "args": { + "External id": 3715409,"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": 1625851052394.225, "dur": 29.325, + "args": { + "External id": 3715410,"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": 1625851052440.225, "dur": 20.492, + "args": { + "External id": 3715411,"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": 1625851052479.564, "dur": 155.933, + "args": { + "External id": 3715412,"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": 1625851052544.003, "dur": 16.558, + "args": { + "External id": 3715413,"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": 1625851052552.237, "dur": 7.387, + "args": { + "External id": 3715414,"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": 1625851052563.197, "dur": 5.493, + "args": { + "External id": 3715415,"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": 1625851052569.891, "dur": 3.673, + "args": { + "External id": 3715416,"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": 1625851052575.994, "dur": 3.562, + "args": { + "External id": 3715417,"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": 1625851052646.638, "dur": 67.356, + "args": { + "External id": 3715418,"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": 1625851052750.116, "dur": 32.049, + "args": { + "External id": 3715419,"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": 1625851052792.891, "dur": 45.291, + "args": { + "External id": 3715420,"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": 1625851052844.233, "dur": 34.682, + "args": { + "External id": 3715421,"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": 1625851052906.178, "dur": 26.835, + "args": { + "External id": 3715422,"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": 1625851052938.753, "dur": 32.635, + "args": { + "External id": 3715423,"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": 1625851053032.349, "dur": 27.311, + "args": { + "External id": 3715424,"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": 1625851053227.221, "dur": 80.675, + "args": { + "External id": 3715425,"Record function id": 0, "Ev Idx": 6136 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 1336756, "tid": 1336756, + "ts": 1625851053389.763, "dur": 49.106, + "args": { + "External id": 3715426,"Record function id": 0, "Ev Idx": 6137 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.2)", "pid": 1336756, "tid": 1336756, + "ts": 1625851053447.792, "dur": 18028.399, + "args": { + "External id": 3715427,"Record function id": 0, "Ev Idx": 6138 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.2)", "pid": 1336756, "tid": 1336756, + "ts": 1625851053459.476, "dur": 950.353, + "args": { + "External id": 3715428,"Record function id": 0, "Ev Idx": 6139 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1625851053539.937, "dur": 8.110, + "args": { + "External id": 3715429,"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": 1625851053561.170, "dur": 47.182, + "args": { + "External id": 3715430,"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": 1625851053566.151, "dur": 2.126, + "args": { + "External id": 3715431,"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": 1625851053575.744, "dur": 0.907, + "args": { + "External id": 3715432,"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": 1625851053577.695, "dur": 0.549, + "args": { + "External id": 3715433,"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": 1625851053579.513, "dur": 0.588, + "args": { + "External id": 3715434,"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": 1625851053586.515, "dur": 0.509, + "args": { + "External id": 3715435,"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": 1625851053587.914, "dur": 0.617, + "args": { + "External id": 3715436,"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": 1625851053591.478, "dur": 5.313, + "args": { + "External id": 3715437,"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": 1625851053597.964, "dur": 0.484, + "args": { + "External id": 3715438,"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": 1625851053599.183, "dur": 0.558, + "args": { + "External id": 3715439,"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": 1625851053621.687, "dur": 41.541, + "args": { + "External id": 3715440,"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": 1625851053717.980, "dur": 133.346, + "args": { + "External id": 3715441,"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": 1625851053732.502, "dur": 5.134, + "args": { + "External id": 3715442,"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": 1625851053742.843, "dur": 10.773, + "args": { + "External id": 3715443,"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": 1625851053747.254, "dur": 5.951, + "args": { + "External id": 3715444,"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": 1625851053750.781, "dur": 0.800, + "args": { + "External id": 3715445,"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": 1625851053763.602, "dur": 40.256, + "args": { + "External id": 3715446,"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": 1625851053765.387, "dur": 3.218, + "args": { + "External id": 3715447,"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": 1625851053769.652, "dur": 0.523, + "args": { + "External id": 3715448,"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": 1625851053774.295, "dur": 0.371, + "args": { + "External id": 3715449,"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": 1625851053778.192, "dur": 2.457, + "args": { + "External id": 3715450,"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": 1625851053784.315, "dur": 0.306, + "args": { + "External id": 3715451,"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": 1625851053785.476, "dur": 0.311, + "args": { + "External id": 3715452,"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": 1625851053789.307, "dur": 0.347, + "args": { + "External id": 3715453,"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": 1625851053794.007, "dur": 0.341, + "args": { + "External id": 3715454,"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": 1625851053795.151, "dur": 2.514, + "args": { + "External id": 3715455,"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": 1625851053815.629, "dur": 27.418, + "args": { + "External id": 3715456,"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": 1625851053907.713, "dur": 403.987, + "args": { + "External id": 3715457,"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": 1625851053943.753, "dur": 362.598, + "args": { + "External id": 3715458,"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": 1625851053959.383, "dur": 341.321, + "args": { + "External id": 3715459,"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": 1625851054340.450, "dur": 2.433, + "args": { + "External id": 3715460,"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": 1625851054429.139, "dur": 16852.690, + "args": { + "External id": 3715461,"Record function id": 0, "Ev Idx": 6172 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1625851054526.150, "dur": 6.110, + "args": { + "External id": 3715462,"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": 1625851054535.464, "dur": 1.293, + "args": { + "External id": 3715463,"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": 1625851054538.682, "dur": 3.542, + "args": { + "External id": 3715464,"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": 1625851054543.816, "dur": 1.003, + "args": { + "External id": 3715465,"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": 1625851054546.126, "dur": 0.875, + "args": { + "External id": 3715466,"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": 1625851054548.217, "dur": 1.031, + "args": { + "External id": 3715467,"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": 1625851054554.046, "dur": 1.020, + "args": { + "External id": 3715468,"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": 1625851054556.530, "dur": 3.411, + "args": { + "External id": 3715469,"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": 1625851054561.544, "dur": 0.922, + "args": { + "External id": 3715470,"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": 1625851054564.068, "dur": 0.907, + "args": { + "External id": 3715471,"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": 1625851054587.056, "dur": 16656.637, + "args": { + "External id": 3715472,"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": 1625851054602.190, "dur": 16634.953, + "args": { + "External id": 3715473,"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": 1625851054626.041, "dur": 14.735, + "args": { + "External id": 3715474,"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": 1625851054644.355, "dur": 16557.351, + "args": { + "External id": 3715475,"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": 1625851054646.998, "dur": 16553.981, + "args": { + "External id": 3715476,"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": 1625851054656.084, "dur": 4.507, + "args": { + "External id": 3715477,"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": 1625851054662.493, "dur": 16535.110, + "args": { + "External id": 3715478,"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": 1625851071423.687, "dur": 28.974, + "args": { + "External id": 3715479,"Sequence number": 37295077, "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": 1625851071423.687, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 1336756, "tid": 1336756, + "ts": 1625851071440.754, "dur": 7.448, + "args": { + "External id": 3715480,"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": 1625851071444.056, "dur": 3.957, + "args": { + "External id": 3715481,"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": 1625851071520.861, "dur": 96.771, + "args": { + "External id": 3715482,"Record function id": 0, "Ev Idx": 6193 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 1336756, "tid": 1336756, + "ts": 1625851071619.200, "dur": 1193.574, + "args": { + "External id": 3715483,"Record function id": 0, "Ev Idx": 6194 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 1336756, "tid": 1336756, + "ts": 1625851071666.547, "dur": 1133.296, + "args": { + "External id": 3715484,"Sequence number": 37295078, "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": 1625851071666.547, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 1336756, "tid": 1336756, + "ts": 1625851071765.344, "dur": 45.791, + "args": { + "External id": 3715485,"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": 1625851071825.749, "dur": 102.693, + "args": { + "External id": 3715486,"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": 1625851071938.241, "dur": 39.417, + "args": { + "External id": 3715487,"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": 1625851072053.550, "dur": 37.689, + "args": { + "External id": 3715488,"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": 1625851072119.968, "dur": 28.306, + "args": { + "External id": 3715489,"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": 1625851072167.607, "dur": 15.609, + "args": { + "External id": 3715490,"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": 1625851072203.849, "dur": 139.362, + "args": { + "External id": 3715491,"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": 1625851072255.993, "dur": 13.112, + "args": { + "External id": 3715492,"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": 1625851072263.160, "dur": 5.172, + "args": { + "External id": 3715493,"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": 1625851072271.688, "dur": 8.155, + "args": { + "External id": 3715494,"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": 1625851072281.176, "dur": 1.258, + "args": { + "External id": 3715495,"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": 1625851072284.800, "dur": 5.491, + "args": { + "External id": 3715496,"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": 1625851072353.755, "dur": 44.505, + "args": { + "External id": 3715497,"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": 1625851072431.002, "dur": 28.868, + "args": { + "External id": 3715498,"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": 1625851072469.971, "dur": 40.026, + "args": { + "External id": 3715499,"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": 1625851072517.870, "dur": 34.452, + "args": { + "External id": 3715500,"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": 1625851072574.148, "dur": 26.081, + "args": { + "External id": 3715501,"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": 1625851072606.168, "dur": 33.688, + "args": { + "External id": 3715502,"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": 1625851072665.198, "dur": 45.245, + "args": { + "External id": 3715503,"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": 1625851072877.747, "dur": 75.984, + "args": { + "External id": 3715504,"Record function id": 0, "Ev Idx": 6215 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 1336756, "tid": 1336756, + "ts": 1625851073080.537, "dur": 50.994, + "args": { + "External id": 3715505,"Record function id": 0, "Ev Idx": 6216 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.3)", "pid": 1336756, "tid": 1336756, + "ts": 1625851073141.779, "dur": 18130.214, + "args": { + "External id": 3715506,"Record function id": 0, "Ev Idx": 6217 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.3)", "pid": 1336756, "tid": 1336756, + "ts": 1625851073153.016, "dur": 981.281, + "args": { + "External id": 3715507,"Record function id": 0, "Ev Idx": 6218 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1625851073234.251, "dur": 8.977, + "args": { + "External id": 3715508,"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": 1625851073255.973, "dur": 48.660, + "args": { + "External id": 3715509,"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": 1625851073261.150, "dur": 2.490, + "args": { + "External id": 3715510,"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": 1625851073271.469, "dur": 0.563, + "args": { + "External id": 3715511,"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": 1625851073273.141, "dur": 0.530, + "args": { + "External id": 3715512,"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": 1625851073277.234, "dur": 0.519, + "args": { + "External id": 3715513,"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": 1625851073281.541, "dur": 0.400, + "args": { + "External id": 3715514,"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": 1625851073283.018, "dur": 0.616, + "args": { + "External id": 3715515,"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": 1625851073287.452, "dur": 5.921, + "args": { + "External id": 3715516,"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": 1625851073294.319, "dur": 0.554, + "args": { + "External id": 3715517,"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": 1625851073295.789, "dur": 0.591, + "args": { + "External id": 3715518,"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": 1625851073319.382, "dur": 44.856, + "args": { + "External id": 3715519,"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": 1625851073402.496, "dur": 144.771, + "args": { + "External id": 3715520,"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": 1625851073416.077, "dur": 6.174, + "args": { + "External id": 3715521,"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": 1625851073427.592, "dur": 12.448, + "args": { + "External id": 3715522,"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": 1625851073432.305, "dur": 7.328, + "args": { + "External id": 3715523,"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": 1625851073437.642, "dur": 0.777, + "args": { + "External id": 3715524,"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": 1625851073446.485, "dur": 37.557, + "args": { + "External id": 3715525,"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": 1625851073448.457, "dur": 0.682, + "args": { + "External id": 3715526,"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": 1625851073452.859, "dur": 2.913, + "args": { + "External id": 3715527,"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": 1625851073456.674, "dur": 0.594, + "args": { + "External id": 3715528,"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": 1625851073457.909, "dur": 3.075, + "args": { + "External id": 3715529,"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": 1625851073467.137, "dur": 0.223, + "args": { + "External id": 3715530,"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": 1625851073468.062, "dur": 0.346, + "args": { + "External id": 3715531,"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": 1625851073469.238, "dur": 0.374, + "args": { + "External id": 3715532,"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": 1625851073476.155, "dur": 0.237, + "args": { + "External id": 3715533,"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": 1625851073477.433, "dur": 0.311, + "args": { + "External id": 3715534,"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": 1625851073510.803, "dur": 28.336, + "args": { + "External id": 3715535,"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": 1625851073599.204, "dur": 427.591, + "args": { + "External id": 3715536,"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": 1625851073633.852, "dur": 345.126, + "args": { + "External id": 3715537,"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": 1625851073647.822, "dur": 325.579, + "args": { + "External id": 3715538,"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": 1625851074056.619, "dur": 3.438, + "args": { + "External id": 3715539,"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": 1625851074155.653, "dur": 16909.354, + "args": { + "External id": 3715540,"Record function id": 0, "Ev Idx": 6251 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1625851074254.941, "dur": 5.962, + "args": { + "External id": 3715541,"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": 1625851074264.543, "dur": 1.586, + "args": { + "External id": 3715542,"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": 1625851074268.632, "dur": 4.011, + "args": { + "External id": 3715543,"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": 1625851074274.597, "dur": 1.215, + "args": { + "External id": 3715544,"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": 1625851074277.263, "dur": 1.175, + "args": { + "External id": 3715545,"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": 1625851074280.074, "dur": 1.028, + "args": { + "External id": 3715546,"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": 1625851074284.960, "dur": 1.045, + "args": { + "External id": 3715547,"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": 1625851074287.636, "dur": 3.127, + "args": { + "External id": 3715548,"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": 1625851074292.227, "dur": 1.024, + "args": { + "External id": 3715549,"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": 1625851074297.276, "dur": 1.122, + "args": { + "External id": 3715550,"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": 1625851074319.074, "dur": 16707.073, + "args": { + "External id": 3715551,"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": 1625851074335.487, "dur": 16683.054, + "args": { + "External id": 3715552,"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": 1625851074356.579, "dur": 14.967, + "args": { + "External id": 3715553,"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": 1625851074374.792, "dur": 16585.724, + "args": { + "External id": 3715554,"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": 1625851074377.581, "dur": 16582.387, + "args": { + "External id": 3715555,"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": 1625851074386.484, "dur": 6.927, + "args": { + "External id": 3715556,"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": 1625851074395.149, "dur": 16561.816, + "args": { + "External id": 3715557,"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": 1625851091205.613, "dur": 42.429, + "args": { + "External id": 3715558,"Sequence number": 37295079, "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": 1625851091205.613, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 1336756, "tid": 1336756, + "ts": 1625851091223.726, "dur": 19.695, + "args": { + "External id": 3715559,"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": 1625851091238.776, "dur": 4.408, + "args": { + "External id": 3715560,"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": 1625851091312.650, "dur": 82.731, + "args": { + "External id": 3715561,"Record function id": 0, "Ev Idx": 6272 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 1336756, "tid": 1336756, + "ts": 1625851091399.136, "dur": 1107.842, + "args": { + "External id": 3715562,"Record function id": 0, "Ev Idx": 6273 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 1336756, "tid": 1336756, + "ts": 1625851091439.666, "dur": 1054.776, + "args": { + "External id": 3715563,"Sequence number": 37295080, "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": 1625851091439.666, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 1336756, "tid": 1336756, + "ts": 1625851091506.325, "dur": 41.508, + "args": { + "External id": 3715564,"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": 1625851091559.417, "dur": 102.473, + "args": { + "External id": 3715565,"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": 1625851091696.155, "dur": 42.465, + "args": { + "External id": 3715566,"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": 1625851091746.281, "dur": 31.075, + "args": { + "External id": 3715567,"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": 1625851091805.623, "dur": 26.314, + "args": { + "External id": 3715568,"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": 1625851091849.673, "dur": 15.890, + "args": { + "External id": 3715569,"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": 1625851091887.837, "dur": 179.273, + "args": { + "External id": 3715570,"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": 1625851091940.877, "dur": 10.600, + "args": { + "External id": 3715571,"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": 1625851091945.654, "dur": 5.041, + "args": { + "External id": 3715572,"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": 1625851091953.969, "dur": 5.348, + "args": { + "External id": 3715573,"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": 1625851091960.586, "dur": 1.282, + "args": { + "External id": 3715574,"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": 1625851091967.337, "dur": 7.377, + "args": { + "External id": 3715575,"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": 1625851092080.162, "dur": 51.314, + "args": { + "External id": 3715576,"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": 1625851092168.610, "dur": 32.912, + "args": { + "External id": 3715577,"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": 1625851092211.430, "dur": 41.943, + "args": { + "External id": 3715578,"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": 1625851092261.692, "dur": 33.873, + "args": { + "External id": 3715579,"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": 1625851092315.961, "dur": 30.382, + "args": { + "External id": 3715580,"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": 1625851092351.743, "dur": 33.390, + "args": { + "External id": 3715581,"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": 1625851092405.750, "dur": 20.601, + "args": { + "External id": 3715582,"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": 1625851092570.356, "dur": 70.964, + "args": { + "External id": 3715583,"Record function id": 0, "Ev Idx": 6294 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 1336756, "tid": 1336756, + "ts": 1625851092734.426, "dur": 47.392, + "args": { + "External id": 3715584,"Record function id": 0, "Ev Idx": 6295 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.4)", "pid": 1336756, "tid": 1336756, + "ts": 1625851092818.367, "dur": 18128.051, + "args": { + "External id": 3715585,"Record function id": 0, "Ev Idx": 6296 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.4)", "pid": 1336756, "tid": 1336756, + "ts": 1625851092833.984, "dur": 942.167, + "args": { + "External id": 3715586,"Record function id": 0, "Ev Idx": 6297 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1625851092915.728, "dur": 9.338, + "args": { + "External id": 3715587,"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": 1625851092938.279, "dur": 81.329, + "args": { + "External id": 3715588,"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": 1625851092945.482, "dur": 2.080, + "args": { + "External id": 3715589,"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": 1625851092951.191, "dur": 0.527, + "args": { + "External id": 3715590,"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": 1625851092952.297, "dur": 0.721, + "args": { + "External id": 3715591,"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": 1625851092956.242, "dur": 2.614, + "args": { + "External id": 3715592,"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": 1625851092959.504, "dur": 0.376, + "args": { + "External id": 3715593,"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": 1625851092963.097, "dur": 0.313, + "args": { + "External id": 3715594,"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": 1625851092967.056, "dur": 3.073, + "args": { + "External id": 3715595,"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": 1625851092970.589, "dur": 0.340, + "args": { + "External id": 3715596,"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": 1625851092974.246, "dur": 0.375, + "args": { + "External id": 3715597,"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": 1625851093033.494, "dur": 48.591, + "args": { + "External id": 3715598,"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": 1625851093116.694, "dur": 125.836, + "args": { + "External id": 3715599,"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": 1625851093131.349, "dur": 4.441, + "args": { + "External id": 3715600,"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": 1625851093140.809, "dur": 12.208, + "args": { + "External id": 3715601,"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": 1625851093144.715, "dur": 7.867, + "args": { + "External id": 3715602,"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": 1625851093150.125, "dur": 1.202, + "args": { + "External id": 3715603,"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": 1625851093160.062, "dur": 35.260, + "args": { + "External id": 3715604,"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": 1625851093161.266, "dur": 0.554, + "args": { + "External id": 3715605,"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": 1625851093165.207, "dur": 0.473, + "args": { + "External id": 3715606,"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": 1625851093166.265, "dur": 0.375, + "args": { + "External id": 3715607,"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": 1625851093172.729, "dur": 2.784, + "args": { + "External id": 3715608,"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": 1625851093176.215, "dur": 0.332, + "args": { + "External id": 3715609,"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": 1625851093176.981, "dur": 2.875, + "args": { + "External id": 3715610,"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": 1625851093183.480, "dur": 0.369, + "args": { + "External id": 3715611,"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": 1625851093184.343, "dur": 0.317, + "args": { + "External id": 3715612,"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": 1625851093188.225, "dur": 0.409, + "args": { + "External id": 3715613,"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": 1625851093208.809, "dur": 24.434, + "args": { + "External id": 3715614,"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": 1625851093296.778, "dur": 354.767, + "args": { + "External id": 3715615,"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": 1625851093332.738, "dur": 313.888, + "args": { + "External id": 3715616,"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": 1625851093344.224, "dur": 295.031, + "args": { + "External id": 3715617,"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": 1625851093702.646, "dur": 3.602, + "args": { + "External id": 3715618,"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": 1625851093797.145, "dur": 16961.025, + "args": { + "External id": 3715619,"Record function id": 0, "Ev Idx": 6330 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1625851093894.744, "dur": 6.196, + "args": { + "External id": 3715620,"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": 1625851093904.371, "dur": 1.264, + "args": { + "External id": 3715621,"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": 1625851093907.238, "dur": 4.391, + "args": { + "External id": 3715622,"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": 1625851093913.242, "dur": 1.147, + "args": { + "External id": 3715623,"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": 1625851093916.023, "dur": 1.322, + "args": { + "External id": 3715624,"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": 1625851093918.406, "dur": 1.118, + "args": { + "External id": 3715625,"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": 1625851093924.128, "dur": 1.580, + "args": { + "External id": 3715626,"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": 1625851093929.745, "dur": 3.694, + "args": { + "External id": 3715627,"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": 1625851093934.833, "dur": 0.834, + "args": { + "External id": 3715628,"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": 1625851093936.976, "dur": 0.800, + "args": { + "External id": 3715629,"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": 1625851093956.948, "dur": 16762.915, + "args": { + "External id": 3715630,"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": 1625851093975.020, "dur": 16737.645, + "args": { + "External id": 3715631,"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": 1625851094052.088, "dur": 14.464, + "args": { + "External id": 3715632,"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": 1625851094069.844, "dur": 16596.924, + "args": { + "External id": 3715633,"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": 1625851094072.345, "dur": 16593.952, + "args": { + "External id": 3715634,"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": 1625851094078.782, "dur": 7.654, + "args": { + "External id": 3715635,"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": 1625851094088.045, "dur": 16575.249, + "args": { + "External id": 3715636,"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": 1625851110893.065, "dur": 30.723, + "args": { + "External id": 3715637,"Sequence number": 37295081, "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": 1625851110893.065, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 1336756, "tid": 1336756, + "ts": 1625851110908.575, "dur": 10.726, + "args": { + "External id": 3715638,"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": 1625851110914.938, "dur": 4.120, + "args": { + "External id": 3715639,"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": 1625851111014.127, "dur": 82.501, + "args": { + "External id": 3715640,"Record function id": 0, "Ev Idx": 6351 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 1336756, "tid": 1336756, + "ts": 1625851111098.352, "dur": 1135.269, + "args": { + "External id": 3715641,"Record function id": 0, "Ev Idx": 6352 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 1336756, "tid": 1336756, + "ts": 1625851111141.337, "dur": 1079.786, + "args": { + "External id": 3715642,"Sequence number": 37295082, "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": 1625851111141.337, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 1336756, "tid": 1336756, + "ts": 1625851111208.840, "dur": 43.741, + "args": { + "External id": 3715643,"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": 1625851111264.885, "dur": 103.741, + "args": { + "External id": 3715644,"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": 1625851111379.284, "dur": 39.337, + "args": { + "External id": 3715645,"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": 1625851111428.026, "dur": 31.204, + "args": { + "External id": 3715646,"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": 1625851111488.137, "dur": 30.479, + "args": { + "External id": 3715647,"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": 1625851111541.728, "dur": 15.994, + "args": { + "External id": 3715648,"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": 1625851111577.023, "dur": 154.616, + "args": { + "External id": 3715649,"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": 1625851111626.372, "dur": 10.510, + "args": { + "External id": 3715650,"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": 1625851111631.049, "dur": 5.047, + "args": { + "External id": 3715651,"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": 1625851111639.270, "dur": 5.606, + "args": { + "External id": 3715652,"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": 1625851111648.572, "dur": 0.852, + "args": { + "External id": 3715653,"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": 1625851111651.568, "dur": 7.376, + "args": { + "External id": 3715654,"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": 1625851111744.430, "dur": 54.358, + "args": { + "External id": 3715655,"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": 1625851111832.775, "dur": 29.912, + "args": { + "External id": 3715656,"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": 1625851111872.605, "dur": 41.293, + "args": { + "External id": 3715657,"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": 1625851111924.259, "dur": 34.671, + "args": { + "External id": 3715658,"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": 1625851111979.418, "dur": 66.470, + "args": { + "External id": 3715659,"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": 1625851112053.553, "dur": 39.290, + "args": { + "External id": 3715660,"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": 1625851112117.133, "dur": 22.302, + "args": { + "External id": 3715661,"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": 1625851112298.103, "dur": 75.724, + "args": { + "External id": 3715662,"Record function id": 0, "Ev Idx": 6373 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 1336756, "tid": 1336756, + "ts": 1625851112447.346, "dur": 47.044, + "args": { + "External id": 3715663,"Record function id": 0, "Ev Idx": 6374 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.5)", "pid": 1336756, "tid": 1336756, + "ts": 1625851112504.220, "dur": 18005.205, + "args": { + "External id": 3715664,"Record function id": 0, "Ev Idx": 6375 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.5)", "pid": 1336756, "tid": 1336756, + "ts": 1625851112516.434, "dur": 922.945, + "args": { + "External id": 3715665,"Record function id": 0, "Ev Idx": 6376 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1625851112596.298, "dur": 7.738, + "args": { + "External id": 3715666,"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": 1625851112616.583, "dur": 47.923, + "args": { + "External id": 3715667,"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": 1625851112623.789, "dur": 2.308, + "args": { + "External id": 3715668,"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": 1625851112631.041, "dur": 0.380, + "args": { + "External id": 3715669,"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": 1625851112634.913, "dur": 0.378, + "args": { + "External id": 3715670,"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": 1625851112636.467, "dur": 0.479, + "args": { + "External id": 3715671,"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": 1625851112640.607, "dur": 0.439, + "args": { + "External id": 3715672,"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": 1625851112644.940, "dur": 0.551, + "args": { + "External id": 3715673,"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": 1625851112646.532, "dur": 4.868, + "args": { + "External id": 3715674,"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": 1625851112651.891, "dur": 0.261, + "args": { + "External id": 3715675,"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": 1625851112655.171, "dur": 0.354, + "args": { + "External id": 3715676,"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": 1625851112692.638, "dur": 42.739, + "args": { + "External id": 3715677,"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": 1625851112768.620, "dur": 130.361, + "args": { + "External id": 3715678,"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": 1625851112785.229, "dur": 4.684, + "args": { + "External id": 3715679,"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": 1625851112795.279, "dur": 9.993, + "args": { + "External id": 3715680,"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": 1625851112799.693, "dur": 5.158, + "args": { + "External id": 3715681,"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": 1625851112802.932, "dur": 0.458, + "args": { + "External id": 3715682,"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": 1625851112811.792, "dur": 41.871, + "args": { + "External id": 3715683,"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": 1625851112815.771, "dur": 3.029, + "args": { + "External id": 3715684,"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": 1625851112819.505, "dur": 0.354, + "args": { + "External id": 3715685,"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": 1625851112820.994, "dur": 0.578, + "args": { + "External id": 3715686,"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": 1625851112827.931, "dur": 2.770, + "args": { + "External id": 3715687,"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": 1625851112831.604, "dur": 0.477, + "args": { + "External id": 3715688,"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": 1625851112832.551, "dur": 0.993, + "args": { + "External id": 3715689,"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": 1625851112839.019, "dur": 0.346, + "args": { + "External id": 3715690,"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": 1625851112839.832, "dur": 0.506, + "args": { + "External id": 3715691,"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": 1625851112843.747, "dur": 2.774, + "args": { + "External id": 3715692,"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": 1625851112867.192, "dur": 24.213, + "args": { + "External id": 3715693,"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": 1625851112951.359, "dur": 395.349, + "args": { + "External id": 3715694,"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": 1625851113022.757, "dur": 318.079, + "args": { + "External id": 3715695,"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": 1625851113036.489, "dur": 298.869, + "args": { + "External id": 3715696,"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": 1625851113370.347, "dur": 2.440, + "args": { + "External id": 3715697,"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": 1625851113458.634, "dur": 16852.772, + "args": { + "External id": 3715698,"Record function id": 0, "Ev Idx": 6409 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1625851113556.328, "dur": 6.115, + "args": { + "External id": 3715699,"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": 1625851113565.714, "dur": 1.300, + "args": { + "External id": 3715700,"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": 1625851113568.710, "dur": 3.977, + "args": { + "External id": 3715701,"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": 1625851113574.277, "dur": 1.024, + "args": { + "External id": 3715702,"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": 1625851113576.738, "dur": 0.847, + "args": { + "External id": 3715703,"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": 1625851113581.275, "dur": 1.064, + "args": { + "External id": 3715704,"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": 1625851113585.694, "dur": 1.380, + "args": { + "External id": 3715705,"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": 1625851113588.376, "dur": 3.863, + "args": { + "External id": 3715706,"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": 1625851113593.423, "dur": 0.980, + "args": { + "External id": 3715707,"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": 1625851113597.980, "dur": 1.246, + "args": { + "External id": 3715708,"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": 1625851113617.526, "dur": 16653.382, + "args": { + "External id": 3715709,"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": 1625851113638.560, "dur": 16625.641, + "args": { + "External id": 3715710,"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": 1625851113658.967, "dur": 15.502, + "args": { + "External id": 3715711,"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": 1625851113696.255, "dur": 16531.012, + "args": { + "External id": 3715712,"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": 1625851113698.647, "dur": 16528.070, + "args": { + "External id": 3715713,"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": 1625851113705.416, "dur": 6.462, + "args": { + "External id": 3715714,"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": 1625851113713.623, "dur": 16509.761, + "args": { + "External id": 3715715,"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": 1625851130448.136, "dur": 36.706, + "args": { + "External id": 3715716,"Sequence number": 37295083, "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": 1625851130448.136, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 1336756, "tid": 1336756, + "ts": 1625851130472.496, "dur": 7.948, + "args": { + "External id": 3715717,"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": 1625851130476.324, "dur": 3.906, + "args": { + "External id": 3715718,"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": 1625851130549.898, "dur": 80.246, + "args": { + "External id": 3715719,"Record function id": 0, "Ev Idx": 6430 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 1336756, "tid": 1336756, + "ts": 1625851130631.615, "dur": 1130.987, + "args": { + "External id": 3715720,"Record function id": 0, "Ev Idx": 6431 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 1336756, "tid": 1336756, + "ts": 1625851130670.381, "dur": 1078.735, + "args": { + "External id": 3715721,"Sequence number": 37295084, "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": 1625851130670.381, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 1336756, "tid": 1336756, + "ts": 1625851130757.012, "dur": 43.979, + "args": { + "External id": 3715722,"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": 1625851130814.578, "dur": 104.935, + "args": { + "External id": 3715723,"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": 1625851130929.448, "dur": 38.312, + "args": { + "External id": 3715724,"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": 1625851130979.292, "dur": 70.139, + "args": { + "External id": 3715725,"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": 1625851131080.732, "dur": 29.271, + "args": { + "External id": 3715726,"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": 1625851131132.486, "dur": 18.187, + "args": { + "External id": 3715727,"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": 1625851131171.840, "dur": 142.191, + "args": { + "External id": 3715728,"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": 1625851131223.672, "dur": 13.765, + "args": { + "External id": 3715729,"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": 1625851131228.766, "dur": 7.758, + "args": { + "External id": 3715730,"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": 1625851131240.361, "dur": 6.832, + "args": { + "External id": 3715731,"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": 1625851131248.708, "dur": 1.063, + "args": { + "External id": 3715732,"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": 1625851131257.138, "dur": 4.962, + "args": { + "External id": 3715733,"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": 1625851131324.081, "dur": 45.927, + "args": { + "External id": 3715734,"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": 1625851131404.688, "dur": 31.020, + "args": { + "External id": 3715735,"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": 1625851131445.988, "dur": 40.718, + "args": { + "External id": 3715736,"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": 1625851131495.473, "dur": 34.813, + "args": { + "External id": 3715737,"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": 1625851131553.042, "dur": 28.965, + "args": { + "External id": 3715738,"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": 1625851131587.819, "dur": 33.747, + "args": { + "External id": 3715739,"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": 1625851131644.803, "dur": 17.774, + "args": { + "External id": 3715740,"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": 1625851131825.058, "dur": 75.098, + "args": { + "External id": 3715741,"Record function id": 0, "Ev Idx": 6452 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 1336756, "tid": 1336756, + "ts": 1625851131970.712, "dur": 83.436, + "args": { + "External id": 3715742,"Record function id": 0, "Ev Idx": 6453 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.6)", "pid": 1336756, "tid": 1336756, + "ts": 1625851132064.524, "dur": 18062.643, + "args": { + "External id": 3715743,"Record function id": 0, "Ev Idx": 6454 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.6)", "pid": 1336756, "tid": 1336756, + "ts": 1625851132074.398, "dur": 951.569, + "args": { + "External id": 3715744,"Record function id": 0, "Ev Idx": 6455 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1625851132153.604, "dur": 8.293, + "args": { + "External id": 3715745,"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": 1625851132175.171, "dur": 45.649, + "args": { + "External id": 3715746,"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": 1625851132180.673, "dur": 2.276, + "args": { + "External id": 3715747,"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": 1625851132188.130, "dur": 0.486, + "args": { + "External id": 3715748,"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": 1625851132190.890, "dur": 0.641, + "args": { + "External id": 3715749,"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": 1625851132193.439, "dur": 0.649, + "args": { + "External id": 3715750,"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": 1625851132198.459, "dur": 0.378, + "args": { + "External id": 3715751,"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": 1625851132200.331, "dur": 0.475, + "args": { + "External id": 3715752,"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": 1625851132202.729, "dur": 4.594, + "args": { + "External id": 3715753,"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": 1625851132208.974, "dur": 0.429, + "args": { + "External id": 3715754,"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": 1625851132211.449, "dur": 0.498, + "args": { + "External id": 3715755,"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": 1625851132233.067, "dur": 43.306, + "args": { + "External id": 3715756,"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": 1625851132310.198, "dur": 120.580, + "args": { + "External id": 3715757,"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": 1625851132323.304, "dur": 3.695, + "args": { + "External id": 3715758,"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": 1625851132332.022, "dur": 10.366, + "args": { + "External id": 3715759,"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": 1625851132336.267, "dur": 5.718, + "args": { + "External id": 3715760,"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": 1625851132339.983, "dur": 0.656, + "args": { + "External id": 3715761,"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": 1625851132349.622, "dur": 39.652, + "args": { + "External id": 3715762,"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": 1625851132351.962, "dur": 2.836, + "args": { + "External id": 3715763,"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": 1625851132356.579, "dur": 0.609, + "args": { + "External id": 3715764,"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": 1625851132359.332, "dur": 0.607, + "args": { + "External id": 3715765,"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": 1625851132364.571, "dur": 2.671, + "args": { + "External id": 3715766,"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": 1625851132369.230, "dur": 0.547, + "args": { + "External id": 3715767,"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": 1625851132371.079, "dur": 0.456, + "args": { + "External id": 3715768,"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": 1625851132375.554, "dur": 0.454, + "args": { + "External id": 3715769,"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": 1625851132377.592, "dur": 0.640, + "args": { + "External id": 3715770,"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": 1625851132379.963, "dur": 2.696, + "args": { + "External id": 3715771,"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": 1625851132400.298, "dur": 21.894, + "args": { + "External id": 3715772,"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": 1625851132484.606, "dur": 401.124, + "args": { + "External id": 3715773,"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": 1625851132518.917, "dur": 360.798, + "args": { + "External id": 3715774,"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": 1625851132529.964, "dur": 343.825, + "args": { + "External id": 3715775,"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": 1625851132916.213, "dur": 2.321, + "args": { + "External id": 3715776,"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": 1625851133049.244, "dur": 16855.105, + "args": { + "External id": 3715777,"Record function id": 0, "Ev Idx": 6488 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1625851133158.185, "dur": 6.656, + "args": { + "External id": 3715778,"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": 1625851133169.438, "dur": 1.160, + "args": { + "External id": 3715779,"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": 1625851133172.540, "dur": 3.741, + "args": { + "External id": 3715780,"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": 1625851133178.385, "dur": 1.140, + "args": { + "External id": 3715781,"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": 1625851133181.365, "dur": 1.016, + "args": { + "External id": 3715782,"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": 1625851133183.834, "dur": 0.864, + "args": { + "External id": 3715783,"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": 1625851133188.760, "dur": 1.185, + "args": { + "External id": 3715784,"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": 1625851133191.563, "dur": 4.369, + "args": { + "External id": 3715785,"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": 1625851133197.810, "dur": 0.782, + "args": { + "External id": 3715786,"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": 1625851133200.365, "dur": 1.414, + "args": { + "External id": 3715787,"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": 1625851133222.892, "dur": 16635.675, + "args": { + "External id": 3715788,"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": 1625851133239.455, "dur": 16612.714, + "args": { + "External id": 3715789,"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": 1625851133264.207, "dur": 14.620, + "args": { + "External id": 3715790,"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": 1625851133281.921, "dur": 16536.545, + "args": { + "External id": 3715791,"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": 1625851133284.164, "dur": 16533.808, + "args": { + "External id": 3715792,"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": 1625851133291.541, "dur": 4.895, + "args": { + "External id": 3715793,"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": 1625851133298.135, "dur": 16517.201, + "args": { + "External id": 3715794,"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": 1625851150074.589, "dur": 28.033, + "args": { + "External id": 3715795,"Sequence number": 37295085, "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": 1625851150074.589, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 1336756, "tid": 1336756, + "ts": 1625851150090.304, "dur": 7.548, + "args": { + "External id": 3715796,"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": 1625851150093.478, "dur": 4.037, + "args": { + "External id": 3715797,"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": 1625851150167.891, "dur": 79.832, + "args": { + "External id": 3715798,"Record function id": 0, "Ev Idx": 6509 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 1336756, "tid": 1336756, + "ts": 1625851150249.470, "dur": 1112.158, + "args": { + "External id": 3715799,"Record function id": 0, "Ev Idx": 6510 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 1336756, "tid": 1336756, + "ts": 1625851150289.449, "dur": 1059.000, + "args": { + "External id": 3715800,"Sequence number": 37295086, "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": 1625851150289.449, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 1336756, "tid": 1336756, + "ts": 1625851150354.450, "dur": 43.660, + "args": { + "External id": 3715801,"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": 1625851150410.103, "dur": 102.731, + "args": { + "External id": 3715802,"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": 1625851150522.672, "dur": 39.141, + "args": { + "External id": 3715803,"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": 1625851150573.567, "dur": 30.675, + "args": { + "External id": 3715804,"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": 1625851150628.840, "dur": 26.927, + "args": { + "External id": 3715805,"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": 1625851150674.778, "dur": 34.526, + "args": { + "External id": 3715806,"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": 1625851150731.258, "dur": 136.545, + "args": { + "External id": 3715807,"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": 1625851150782.549, "dur": 11.450, + "args": { + "External id": 3715808,"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": 1625851150787.091, "dur": 6.119, + "args": { + "External id": 3715809,"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": 1625851150796.925, "dur": 8.456, + "args": { + "External id": 3715810,"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": 1625851150806.965, "dur": 1.452, + "args": { + "External id": 3715811,"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": 1625851150810.719, "dur": 5.418, + "args": { + "External id": 3715812,"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": 1625851150879.167, "dur": 49.340, + "args": { + "External id": 3715813,"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": 1625851150962.837, "dur": 68.343, + "args": { + "External id": 3715814,"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": 1625851151045.253, "dur": 45.566, + "args": { + "External id": 3715815,"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": 1625851151100.093, "dur": 35.006, + "args": { + "External id": 3715816,"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": 1625851151162.314, "dur": 29.012, + "args": { + "External id": 3715817,"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": 1625851151196.881, "dur": 34.875, + "args": { + "External id": 3715818,"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": 1625851151253.018, "dur": 21.926, + "args": { + "External id": 3715819,"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": 1625851151424.846, "dur": 75.881, + "args": { + "External id": 3715820,"Record function id": 0, "Ev Idx": 6531 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 1336756, "tid": 1336756, + "ts": 1625851151575.046, "dur": 48.229, + "args": { + "External id": 3715821,"Record function id": 0, "Ev Idx": 6532 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.7)", "pid": 1336756, "tid": 1336756, + "ts": 1625851151632.480, "dur": 18158.486, + "args": { + "External id": 3715822,"Record function id": 0, "Ev Idx": 6533 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.7)", "pid": 1336756, "tid": 1336756, + "ts": 1625851151640.354, "dur": 908.007, + "args": { + "External id": 3715823,"Record function id": 0, "Ev Idx": 6534 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1625851151742.211, "dur": 8.782, + "args": { + "External id": 3715824,"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": 1625851151765.076, "dur": 43.985, + "args": { + "External id": 3715825,"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": 1625851151770.675, "dur": 2.354, + "args": { + "External id": 3715826,"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": 1625851151778.639, "dur": 0.492, + "args": { + "External id": 3715827,"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": 1625851151780.485, "dur": 0.445, + "args": { + "External id": 3715828,"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": 1625851151782.585, "dur": 0.593, + "args": { + "External id": 3715829,"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": 1625851151787.138, "dur": 0.593, + "args": { + "External id": 3715830,"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": 1625851151789.753, "dur": 0.445, + "args": { + "External id": 3715831,"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": 1625851151791.668, "dur": 4.950, + "args": { + "External id": 3715832,"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": 1625851151798.229, "dur": 0.232, + "args": { + "External id": 3715833,"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": 1625851151799.637, "dur": 0.347, + "args": { + "External id": 3715834,"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": 1625851151823.023, "dur": 41.228, + "args": { + "External id": 3715835,"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": 1625851151898.859, "dur": 167.678, + "args": { + "External id": 3715836,"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": 1625851151911.595, "dur": 3.734, + "args": { + "External id": 3715837,"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": 1625851151920.282, "dur": 10.470, + "args": { + "External id": 3715838,"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": 1625851151924.686, "dur": 5.661, + "args": { + "External id": 3715839,"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": 1625851151928.730, "dur": 0.444, + "args": { + "External id": 3715840,"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": 1625851151937.285, "dur": 40.821, + "args": { + "External id": 3715841,"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": 1625851151939.817, "dur": 3.537, + "args": { + "External id": 3715842,"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": 1625851151945.605, "dur": 0.558, + "args": { + "External id": 3715843,"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": 1625851151948.037, "dur": 0.370, + "args": { + "External id": 3715844,"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": 1625851151953.154, "dur": 3.272, + "args": { + "External id": 3715845,"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": 1625851151958.050, "dur": 0.327, + "args": { + "External id": 3715846,"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": 1625851151960.185, "dur": 0.322, + "args": { + "External id": 3715847,"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": 1625851151964.494, "dur": 0.345, + "args": { + "External id": 3715848,"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": 1625851151966.141, "dur": 0.494, + "args": { + "External id": 3715849,"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": 1625851151968.409, "dur": 2.600, + "args": { + "External id": 3715850,"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": 1625851152029.805, "dur": 27.241, + "args": { + "External id": 3715851,"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": 1625851152121.284, "dur": 340.507, + "args": { + "External id": 3715852,"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": 1625851152156.861, "dur": 300.210, + "args": { + "External id": 3715853,"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": 1625851152168.255, "dur": 283.887, + "args": { + "External id": 3715854,"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": 1625851152484.349, "dur": 1.928, + "args": { + "External id": 3715855,"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": 1625851152566.460, "dur": 17021.557, + "args": { + "External id": 3715856,"Record function id": 0, "Ev Idx": 6567 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1625851152661.551, "dur": 5.634, + "args": { + "External id": 3715857,"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": 1625851152671.324, "dur": 1.258, + "args": { + "External id": 3715858,"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": 1625851152674.600, "dur": 21.978, + "args": { + "External id": 3715859,"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": 1625851152708.041, "dur": 1.295, + "args": { + "External id": 3715860,"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": 1625851152711.147, "dur": 1.311, + "args": { + "External id": 3715861,"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": 1625851152713.876, "dur": 0.936, + "args": { + "External id": 3715862,"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": 1625851152718.696, "dur": 0.825, + "args": { + "External id": 3715863,"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": 1625851152721.248, "dur": 3.548, + "args": { + "External id": 3715864,"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": 1625851152726.413, "dur": 1.081, + "args": { + "External id": 3715865,"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": 1625851152728.984, "dur": 1.178, + "args": { + "External id": 3715866,"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": 1625851152753.471, "dur": 16789.313, + "args": { + "External id": 3715867,"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": 1625851152769.194, "dur": 16767.122, + "args": { + "External id": 3715868,"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": 1625851152790.227, "dur": 13.576, + "args": { + "External id": 3715869,"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": 1625851152806.609, "dur": 16697.185, + "args": { + "External id": 3715870,"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": 1625851152809.331, "dur": 16693.951, + "args": { + "External id": 3715871,"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": 1625851152815.524, "dur": 5.715, + "args": { + "External id": 3715872,"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": 1625851152823.079, "dur": 16677.269, + "args": { + "External id": 3715873,"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": 1625851169737.024, "dur": 29.899, + "args": { + "External id": 3715874,"Sequence number": 37295087, "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": 1625851169737.024, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 1336756, "tid": 1336756, + "ts": 1625851169755.004, "dur": 7.599, + "args": { + "External id": 3715875,"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": 1625851169758.310, "dur": 3.971, + "args": { + "External id": 3715876,"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": 1625851169829.366, "dur": 77.022, + "args": { + "External id": 3715877,"Record function id": 0, "Ev Idx": 6588 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 1336756, "tid": 1336756, + "ts": 1625851169908.351, "dur": 1131.752, + "args": { + "External id": 3715878,"Record function id": 0, "Ev Idx": 6589 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 1336756, "tid": 1336756, + "ts": 1625851169953.087, "dur": 1073.048, + "args": { + "External id": 3715879,"Sequence number": 37295088, "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": 1625851169953.087, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 1336756, "tid": 1336756, + "ts": 1625851170052.331, "dur": 44.616, + "args": { + "External id": 3715880,"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": 1625851170110.252, "dur": 104.685, + "args": { + "External id": 3715881,"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": 1625851170226.155, "dur": 37.767, + "args": { + "External id": 3715882,"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": 1625851170275.118, "dur": 31.119, + "args": { + "External id": 3715883,"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": 1625851170331.928, "dur": 26.644, + "args": { + "External id": 3715884,"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": 1625851170376.855, "dur": 17.164, + "args": { + "External id": 3715885,"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": 1625851170414.300, "dur": 133.908, + "args": { + "External id": 3715886,"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": 1625851170464.168, "dur": 11.091, + "args": { + "External id": 3715887,"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": 1625851170469.130, "dur": 5.189, + "args": { + "External id": 3715888,"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": 1625851170477.909, "dur": 8.446, + "args": { + "External id": 3715889,"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": 1625851170487.710, "dur": 0.993, + "args": { + "External id": 3715890,"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": 1625851170491.242, "dur": 4.691, + "args": { + "External id": 3715891,"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": 1625851170558.501, "dur": 43.641, + "args": { + "External id": 3715892,"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": 1625851170635.437, "dur": 28.021, + "args": { + "External id": 3715893,"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": 1625851170673.188, "dur": 62.260, + "args": { + "External id": 3715894,"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": 1625851170746.418, "dur": 35.652, + "args": { + "External id": 3715895,"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": 1625851170814.196, "dur": 31.170, + "args": { + "External id": 3715896,"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": 1625851170853.562, "dur": 34.574, + "args": { + "External id": 3715897,"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": 1625851170905.963, "dur": 18.125, + "args": { + "External id": 3715898,"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": 1625851171104.626, "dur": 76.931, + "args": { + "External id": 3715899,"Record function id": 0, "Ev Idx": 6610 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 1336756, "tid": 1336756, + "ts": 1625851171254.422, "dur": 48.475, + "args": { + "External id": 3715900,"Record function id": 0, "Ev Idx": 6611 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.8)", "pid": 1336756, "tid": 1336756, + "ts": 1625851171311.989, "dur": 18098.016, + "args": { + "External id": 3715901,"Record function id": 0, "Ev Idx": 6612 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.8)", "pid": 1336756, "tid": 1336756, + "ts": 1625851171320.995, "dur": 932.740, + "args": { + "External id": 3715902,"Record function id": 0, "Ev Idx": 6613 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1625851171401.716, "dur": 8.205, + "args": { + "External id": 3715903,"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": 1625851171423.478, "dur": 44.922, + "args": { + "External id": 3715904,"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": 1625851171428.863, "dur": 2.177, + "args": { + "External id": 3715905,"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": 1625851171435.866, "dur": 0.471, + "args": { + "External id": 3715906,"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": 1625851171438.399, "dur": 0.586, + "args": { + "External id": 3715907,"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": 1625851171440.608, "dur": 0.550, + "args": { + "External id": 3715908,"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": 1625851171445.064, "dur": 0.428, + "args": { + "External id": 3715909,"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": 1625851171446.852, "dur": 0.561, + "args": { + "External id": 3715910,"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": 1625851171448.672, "dur": 4.817, + "args": { + "External id": 3715911,"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": 1625851171455.445, "dur": 0.587, + "args": { + "External id": 3715912,"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": 1625851171457.601, "dur": 0.513, + "args": { + "External id": 3715913,"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": 1625851171482.079, "dur": 40.719, + "args": { + "External id": 3715914,"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": 1625851171555.170, "dur": 137.769, + "args": { + "External id": 3715915,"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": 1625851171568.980, "dur": 3.953, + "args": { + "External id": 3715916,"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": 1625851171578.217, "dur": 10.167, + "args": { + "External id": 3715917,"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": 1625851171582.461, "dur": 5.514, + "args": { + "External id": 3715918,"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": 1625851171586.176, "dur": 0.549, + "args": { + "External id": 3715919,"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": 1625851171595.099, "dur": 39.534, + "args": { + "External id": 3715920,"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": 1625851171597.817, "dur": 3.574, + "args": { + "External id": 3715921,"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": 1625851171602.851, "dur": 0.517, + "args": { + "External id": 3715922,"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": 1625851171605.642, "dur": 0.746, + "args": { + "External id": 3715923,"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": 1625851171610.207, "dur": 2.436, + "args": { + "External id": 3715924,"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": 1625851171614.178, "dur": 0.342, + "args": { + "External id": 3715925,"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": 1625851171616.613, "dur": 0.689, + "args": { + "External id": 3715926,"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": 1625851171621.231, "dur": 0.449, + "args": { + "External id": 3715927,"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": 1625851171622.993, "dur": 0.383, + "args": { + "External id": 3715928,"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": 1625851171624.955, "dur": 2.333, + "args": { + "External id": 3715929,"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": 1625851171645.328, "dur": 23.009, + "args": { + "External id": 3715930,"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": 1625851171750.102, "dur": 400.720, + "args": { + "External id": 3715931,"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": 1625851171784.229, "dur": 361.016, + "args": { + "External id": 3715932,"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": 1625851171796.075, "dur": 343.594, + "args": { + "External id": 3715933,"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": 1625851172178.902, "dur": 2.323, + "args": { + "External id": 3715934,"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": 1625851172272.791, "dur": 16952.898, + "args": { + "External id": 3715935,"Record function id": 0, "Ev Idx": 6646 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1625851172372.560, "dur": 6.143, + "args": { + "External id": 3715936,"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": 1625851172383.352, "dur": 1.010, + "args": { + "External id": 3715937,"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": 1625851172386.236, "dur": 3.471, + "args": { + "External id": 3715938,"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": 1625851172391.777, "dur": 1.091, + "args": { + "External id": 3715939,"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": 1625851172394.647, "dur": 0.861, + "args": { + "External id": 3715940,"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": 1625851172397.097, "dur": 1.236, + "args": { + "External id": 3715941,"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": 1625851172402.448, "dur": 1.419, + "args": { + "External id": 3715942,"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": 1625851172405.528, "dur": 3.573, + "args": { + "External id": 3715943,"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": 1625851172410.767, "dur": 0.943, + "args": { + "External id": 3715944,"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": 1625851172413.154, "dur": 1.096, + "args": { + "External id": 3715945,"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": 1625851172434.652, "dur": 16745.727, + "args": { + "External id": 3715946,"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": 1625851172450.587, "dur": 16723.019, + "args": { + "External id": 3715947,"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": 1625851172473.515, "dur": 13.906, + "args": { + "External id": 3715948,"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": 1625851172490.210, "dur": 16651.116, + "args": { + "External id": 3715949,"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": 1625851172492.692, "dur": 16648.032, + "args": { + "External id": 3715950,"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": 1625851172499.809, "dur": 4.778, + "args": { + "External id": 3715951,"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": 1625851172506.168, "dur": 16631.420, + "args": { + "External id": 3715952,"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": 1625851189360.414, "dur": 26.737, + "args": { + "External id": 3715953,"Sequence number": 37295089, "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": 1625851189360.414, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 1336756, "tid": 1336756, + "ts": 1625851189375.636, "dur": 7.079, + "args": { + "External id": 3715954,"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": 1625851189378.776, "dur": 3.672, + "args": { + "External id": 3715955,"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": 1625851189450.804, "dur": 77.869, + "args": { + "External id": 3715956,"Record function id": 0, "Ev Idx": 6667 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 1336756, "tid": 1336756, + "ts": 1625851189530.752, "dur": 1086.615, + "args": { + "External id": 3715957,"Record function id": 0, "Ev Idx": 6668 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 1336756, "tid": 1336756, + "ts": 1625851189571.150, "dur": 1034.382, + "args": { + "External id": 3715958,"Sequence number": 37295090, "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": 1625851189571.150, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 1336756, "tid": 1336756, + "ts": 1625851189644.921, "dur": 57.037, + "args": { + "External id": 3715959,"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": 1625851189722.109, "dur": 103.157, + "args": { + "External id": 3715960,"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": 1625851189836.064, "dur": 39.195, + "args": { + "External id": 3715961,"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": 1625851189881.532, "dur": 30.905, + "args": { + "External id": 3715962,"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": 1625851189942.867, "dur": 28.214, + "args": { + "External id": 3715963,"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": 1625851190021.129, "dur": 23.185, + "args": { + "External id": 3715964,"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": 1625851190063.422, "dur": 137.145, + "args": { + "External id": 3715965,"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": 1625851190114.413, "dur": 11.525, + "args": { + "External id": 3715966,"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": 1625851190119.017, "dur": 6.086, + "args": { + "External id": 3715967,"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": 1625851190129.142, "dur": 6.193, + "args": { + "External id": 3715968,"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": 1625851190137.100, "dur": 3.690, + "args": { + "External id": 3715969,"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": 1625851190143.146, "dur": 7.343, + "args": { + "External id": 3715970,"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": 1625851190211.322, "dur": 49.932, + "args": { + "External id": 3715971,"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": 1625851190291.143, "dur": 28.250, + "args": { + "External id": 3715972,"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": 1625851190328.010, "dur": 40.233, + "args": { + "External id": 3715973,"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": 1625851190376.331, "dur": 34.897, + "args": { + "External id": 3715974,"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": 1625851190436.573, "dur": 27.602, + "args": { + "External id": 3715975,"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": 1625851190470.015, "dur": 33.883, + "args": { + "External id": 3715976,"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": 1625851190520.914, "dur": 20.992, + "args": { + "External id": 3715977,"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": 1625851190696.168, "dur": 81.315, + "args": { + "External id": 3715978,"Record function id": 0, "Ev Idx": 6689 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 1336756, "tid": 1336756, + "ts": 1625851190851.435, "dur": 46.816, + "args": { + "External id": 3715979,"Record function id": 0, "Ev Idx": 6690 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.9)", "pid": 1336756, "tid": 1336756, + "ts": 1625851190907.573, "dur": 17998.714, + "args": { + "External id": 3715980,"Record function id": 0, "Ev Idx": 6691 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.9)", "pid": 1336756, "tid": 1336756, + "ts": 1625851190917.022, "dur": 920.613, + "args": { + "External id": 3715981,"Record function id": 0, "Ev Idx": 6692 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1625851191036.663, "dur": 9.114, + "args": { + "External id": 3715982,"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": 1625851191059.572, "dur": 40.401, + "args": { + "External id": 3715983,"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": 1625851191065.063, "dur": 2.435, + "args": { + "External id": 3715984,"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": 1625851191072.348, "dur": 0.340, + "args": { + "External id": 3715985,"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": 1625851191073.675, "dur": 0.667, + "args": { + "External id": 3715986,"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": 1625851191075.377, "dur": 0.537, + "args": { + "External id": 3715987,"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": 1625851191079.234, "dur": 0.585, + "args": { + "External id": 3715988,"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": 1625851191080.807, "dur": 0.513, + "args": { + "External id": 3715989,"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": 1625851191082.381, "dur": 4.919, + "args": { + "External id": 3715990,"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": 1625851191088.521, "dur": 0.428, + "args": { + "External id": 3715991,"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": 1625851191090.200, "dur": 0.460, + "args": { + "External id": 3715992,"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": 1625851191112.321, "dur": 41.727, + "args": { + "External id": 3715993,"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": 1625851191186.567, "dur": 127.680, + "args": { + "External id": 3715994,"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": 1625851191200.783, "dur": 3.946, + "args": { + "External id": 3715995,"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": 1625851191209.965, "dur": 9.902, + "args": { + "External id": 3715996,"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": 1625851191214.208, "dur": 5.245, + "args": { + "External id": 3715997,"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": 1625851191217.501, "dur": 0.713, + "args": { + "External id": 3715998,"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": 1625851191226.754, "dur": 36.282, + "args": { + "External id": 3715999,"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": 1625851191228.399, "dur": 2.898, + "args": { + "External id": 3716000,"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": 1625851191232.527, "dur": 0.312, + "args": { + "External id": 3716001,"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": 1625851191233.873, "dur": 0.465, + "args": { + "External id": 3716002,"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": 1625851191238.540, "dur": 3.007, + "args": { + "External id": 3716003,"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": 1625851191246.310, "dur": 0.637, + "args": { + "External id": 3716004,"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": 1625851191248.081, "dur": 0.335, + "args": { + "External id": 3716005,"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": 1625851191251.471, "dur": 0.372, + "args": { + "External id": 3716006,"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": 1625851191252.793, "dur": 0.293, + "args": { + "External id": 3716007,"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": 1625851191254.019, "dur": 3.220, + "args": { + "External id": 3716008,"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": 1625851191283.507, "dur": 22.472, + "args": { + "External id": 3716009,"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": 1625851191370.274, "dur": 370.973, + "args": { + "External id": 3716010,"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": 1625851191402.719, "dur": 333.292, + "args": { + "External id": 3716011,"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": 1625851191415.580, "dur": 314.882, + "args": { + "External id": 3716012,"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": 1625851191767.113, "dur": 2.791, + "args": { + "External id": 3716013,"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": 1625851191857.462, "dur": 16854.530, + "args": { + "External id": 3716014,"Record function id": 0, "Ev Idx": 6725 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1625851191957.842, "dur": 6.105, + "args": { + "External id": 3716015,"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": 1625851191967.938, "dur": 1.160, + "args": { + "External id": 3716016,"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": 1625851191970.936, "dur": 3.782, + "args": { + "External id": 3716017,"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": 1625851191976.743, "dur": 1.145, + "args": { + "External id": 3716018,"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": 1625851191979.278, "dur": 1.344, + "args": { + "External id": 3716019,"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": 1625851192018.650, "dur": 1.863, + "args": { + "External id": 3716020,"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": 1625851192025.323, "dur": 0.926, + "args": { + "External id": 3716021,"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": 1625851192027.740, "dur": 3.166, + "args": { + "External id": 3716022,"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": 1625851192032.353, "dur": 0.937, + "args": { + "External id": 3716023,"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": 1625851192034.691, "dur": 0.922, + "args": { + "External id": 3716024,"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": 1625851192057.220, "dur": 16597.291, + "args": { + "External id": 3716025,"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": 1625851192072.902, "dur": 16574.953, + "args": { + "External id": 3716026,"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": 1625851192094.086, "dur": 14.601, + "args": { + "External id": 3716027,"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": 1625851192111.699, "dur": 16503.314, + "args": { + "External id": 3716028,"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": 1625851192114.235, "dur": 16500.290, + "args": { + "External id": 3716029,"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": 1625851192120.115, "dur": 7.362, + "args": { + "External id": 3716030,"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": 1625851192129.458, "dur": 16482.112, + "args": { + "External id": 3716031,"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": 1625851208854.651, "dur": 27.820, + "args": { + "External id": 3716032,"Sequence number": 37295091, "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": 1625851208854.651, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 1336756, "tid": 1336756, + "ts": 1625851208870.326, "dur": 7.721, + "args": { + "External id": 3716033,"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": 1625851208873.603, "dur": 4.176, + "args": { + "External id": 3716034,"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": 1625851208947.591, "dur": 103.481, + "args": { + "External id": 3716035,"Record function id": 0, "Ev Idx": 6746 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 1336756, "tid": 1336756, + "ts": 1625851209054.099, "dur": 1089.711, + "args": { + "External id": 3716036,"Record function id": 0, "Ev Idx": 6747 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 1336756, "tid": 1336756, + "ts": 1625851209095.937, "dur": 1034.920, + "args": { + "External id": 3716037,"Sequence number": 37295092, "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": 1625851209095.937, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 1336756, "tid": 1336756, + "ts": 1625851209165.140, "dur": 42.212, + "args": { + "External id": 3716038,"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": 1625851209220.083, "dur": 101.353, + "args": { + "External id": 3716039,"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": 1625851209332.097, "dur": 39.185, + "args": { + "External id": 3716040,"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": 1625851209379.637, "dur": 30.896, + "args": { + "External id": 3716041,"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": 1625851209438.698, "dur": 26.085, + "args": { + "External id": 3716042,"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": 1625851209482.805, "dur": 16.969, + "args": { + "External id": 3716043,"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": 1625851209519.231, "dur": 131.571, + "args": { + "External id": 3716044,"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": 1625851209570.520, "dur": 10.360, + "args": { + "External id": 3716045,"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": 1625851209575.020, "dur": 5.085, + "args": { + "External id": 3716046,"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": 1625851209583.513, "dur": 6.350, + "args": { + "External id": 3716047,"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": 1625851209591.125, "dur": 1.059, + "args": { + "External id": 3716048,"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": 1625851209594.371, "dur": 7.205, + "args": { + "External id": 3716049,"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": 1625851209661.641, "dur": 63.136, + "args": { + "External id": 3716050,"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": 1625851209757.865, "dur": 31.123, + "args": { + "External id": 3716051,"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": 1625851209801.226, "dur": 43.519, + "args": { + "External id": 3716052,"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": 1625851209853.221, "dur": 34.381, + "args": { + "External id": 3716053,"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": 1625851209910.430, "dur": 30.436, + "args": { + "External id": 3716054,"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": 1625851209947.033, "dur": 33.689, + "args": { + "External id": 3716055,"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": 1625851210037.155, "dur": 21.451, + "args": { + "External id": 3716056,"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": 1625851210205.866, "dur": 74.388, + "args": { + "External id": 3716057,"Record function id": 0, "Ev Idx": 6768 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 1336756, "tid": 1336756, + "ts": 1625851210351.278, "dur": 44.622, + "args": { + "External id": 3716058,"Record function id": 0, "Ev Idx": 6769 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.10)", "pid": 1336756, "tid": 1336756, + "ts": 1625851210405.035, "dur": 18438.706, + "args": { + "External id": 3716059,"Record function id": 0, "Ev Idx": 6770 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.10)", "pid": 1336756, "tid": 1336756, + "ts": 1625851210413.436, "dur": 898.139, + "args": { + "External id": 3716060,"Record function id": 0, "Ev Idx": 6771 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1625851210491.381, "dur": 7.353, + "args": { + "External id": 3716061,"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": 1625851210511.676, "dur": 37.722, + "args": { + "External id": 3716062,"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": 1625851210519.637, "dur": 2.155, + "args": { + "External id": 3716063,"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": 1625851210525.860, "dur": 0.475, + "args": { + "External id": 3716064,"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": 1625851210527.269, "dur": 0.384, + "args": { + "External id": 3716065,"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": 1625851210528.658, "dur": 3.065, + "args": { + "External id": 3716066,"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": 1625851210532.296, "dur": 0.572, + "args": { + "External id": 3716067,"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": 1625851210533.498, "dur": 0.576, + "args": { + "External id": 3716068,"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": 1625851210536.730, "dur": 2.466, + "args": { + "External id": 3716069,"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": 1625851210539.916, "dur": 0.355, + "args": { + "External id": 3716070,"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": 1625851210540.884, "dur": 0.521, + "args": { + "External id": 3716071,"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": 1625851210560.578, "dur": 37.583, + "args": { + "External id": 3716072,"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": 1625851210628.332, "dur": 141.191, + "args": { + "External id": 3716073,"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": 1625851210641.022, "dur": 3.397, + "args": { + "External id": 3716074,"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": 1625851210649.693, "dur": 12.525, + "args": { + "External id": 3716075,"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": 1625851210653.888, "dur": 7.865, + "args": { + "External id": 3716076,"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": 1625851210657.406, "dur": 3.116, + "args": { + "External id": 3716077,"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": 1625851210669.250, "dur": 52.900, + "args": { + "External id": 3716078,"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": 1625851210671.218, "dur": 0.451, + "args": { + "External id": 3716079,"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": 1625851210673.023, "dur": 0.696, + "args": { + "External id": 3716080,"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": 1625851210675.367, "dur": 17.744, + "args": { + "External id": 3716081,"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": 1625851210698.062, "dur": 2.676, + "args": { + "External id": 3716082,"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": 1625851210702.342, "dur": 0.488, + "args": { + "External id": 3716083,"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": 1625851210704.561, "dur": 2.768, + "args": { + "External id": 3716084,"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": 1625851210709.127, "dur": 0.340, + "args": { + "External id": 3716085,"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": 1625851210711.008, "dur": 0.552, + "args": { + "External id": 3716086,"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": 1625851210715.805, "dur": 0.269, + "args": { + "External id": 3716087,"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": 1625851210735.792, "dur": 25.060, + "args": { + "External id": 3716088,"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": 1625851210824.496, "dur": 390.682, + "args": { + "External id": 3716089,"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": 1625851210857.813, "dur": 351.891, + "args": { + "External id": 3716090,"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": 1625851210870.187, "dur": 334.154, + "args": { + "External id": 3716091,"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": 1625851211242.362, "dur": 2.503, + "args": { + "External id": 3716092,"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": 1625851211330.141, "dur": 17309.273, + "args": { + "External id": 3716093,"Record function id": 0, "Ev Idx": 6804 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1625851211424.959, "dur": 6.188, + "args": { + "External id": 3716094,"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": 1625851211434.492, "dur": 1.358, + "args": { + "External id": 3716095,"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": 1625851211437.543, "dur": 3.911, + "args": { + "External id": 3716096,"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": 1625851211470.669, "dur": 0.920, + "args": { + "External id": 3716097,"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": 1625851211473.145, "dur": 0.804, + "args": { + "External id": 3716098,"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": 1625851211475.199, "dur": 0.762, + "args": { + "External id": 3716099,"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": 1625851211479.759, "dur": 0.789, + "args": { + "External id": 3716100,"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": 1625851211481.806, "dur": 3.730, + "args": { + "External id": 3716101,"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": 1625851211487.069, "dur": 0.771, + "args": { + "External id": 3716102,"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": 1625851211489.077, "dur": 0.740, + "args": { + "External id": 3716103,"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": 1625851211511.403, "dur": 17078.790, + "args": { + "External id": 3716104,"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": 1625851211526.630, "dur": 17056.981, + "args": { + "External id": 3716105,"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": 1625851211539.060, "dur": 14.118, + "args": { + "External id": 3716106,"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": 1625851211555.793, "dur": 16991.277, + "args": { + "External id": 3716107,"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": 1625851211557.851, "dur": 16988.631, + "args": { + "External id": 3716108,"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": 1625851211563.835, "dur": 6.954, + "args": { + "External id": 3716109,"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": 1625851211572.405, "dur": 16971.059, + "args": { + "External id": 3716110,"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": 1625851228789.509, "dur": 29.134, + "args": { + "External id": 3716111,"Sequence number": 37295093, "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": 1625851228789.509, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 1336756, "tid": 1336756, + "ts": 1625851228805.704, "dur": 8.115, + "args": { + "External id": 3716112,"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": 1625851228809.377, "dur": 4.076, + "args": { + "External id": 3716113,"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": 1625851228883.683, "dur": 75.942, + "args": { + "External id": 3716114,"Record function id": 0, "Ev Idx": 6825 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 1336756, "tid": 1336756, + "ts": 1625851228961.696, "dur": 1120.123, + "args": { + "External id": 3716115,"Record function id": 0, "Ev Idx": 6826 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 1336756, "tid": 1336756, + "ts": 1625851229030.414, "dur": 1037.693, + "args": { + "External id": 3716116,"Sequence number": 37295094, "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": 1625851229030.414, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 1336756, "tid": 1336756, + "ts": 1625851229098.131, "dur": 42.537, + "args": { + "External id": 3716117,"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": 1625851229154.256, "dur": 102.180, + "args": { + "External id": 3716118,"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": 1625851229267.620, "dur": 37.921, + "args": { + "External id": 3716119,"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": 1625851229314.283, "dur": 32.398, + "args": { + "External id": 3716120,"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": 1625851229373.915, "dur": 26.194, + "args": { + "External id": 3716121,"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": 1625851229421.040, "dur": 17.232, + "args": { + "External id": 3716122,"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": 1625851229458.508, "dur": 135.186, + "args": { + "External id": 3716123,"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": 1625851229510.589, "dur": 10.731, + "args": { + "External id": 3716124,"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": 1625851229515.661, "dur": 4.725, + "args": { + "External id": 3716125,"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": 1625851229524.126, "dur": 7.196, + "args": { + "External id": 3716126,"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": 1625851229532.844, "dur": 0.942, + "args": { + "External id": 3716127,"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": 1625851229536.336, "dur": 6.620, + "args": { + "External id": 3716128,"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": 1625851229604.574, "dur": 44.661, + "args": { + "External id": 3716129,"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": 1625851229698.068, "dur": 32.994, + "args": { + "External id": 3716130,"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": 1625851229744.510, "dur": 44.717, + "args": { + "External id": 3716131,"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": 1625851229797.927, "dur": 34.577, + "args": { + "External id": 3716132,"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": 1625851229857.094, "dur": 28.981, + "args": { + "External id": 3716133,"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": 1625851229892.976, "dur": 33.930, + "args": { + "External id": 3716134,"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": 1625851229947.662, "dur": 19.197, + "args": { + "External id": 3716135,"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": 1625851230145.491, "dur": 74.728, + "args": { + "External id": 3716136,"Record function id": 0, "Ev Idx": 6847 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 1336756, "tid": 1336756, + "ts": 1625851230292.908, "dur": 45.189, + "args": { + "External id": 3716137,"Record function id": 0, "Ev Idx": 6848 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.11)", "pid": 1336756, "tid": 1336756, + "ts": 1625851230347.199, "dur": 18237.592, + "args": { + "External id": 3716138,"Record function id": 0, "Ev Idx": 6849 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.11)", "pid": 1336756, "tid": 1336756, + "ts": 1625851230354.499, "dur": 975.066, + "args": { + "External id": 3716139,"Record function id": 0, "Ev Idx": 6850 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1625851230434.204, "dur": 7.816, + "args": { + "External id": 3716140,"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": 1625851230454.662, "dur": 45.590, + "args": { + "External id": 3716141,"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": 1625851230460.563, "dur": 2.337, + "args": { + "External id": 3716142,"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": 1625851230468.398, "dur": 0.695, + "args": { + "External id": 3716143,"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": 1625851230470.642, "dur": 0.775, + "args": { + "External id": 3716144,"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": 1625851230472.746, "dur": 0.410, + "args": { + "External id": 3716145,"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": 1625851230477.223, "dur": 0.596, + "args": { + "External id": 3716146,"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": 1625851230479.276, "dur": 0.381, + "args": { + "External id": 3716147,"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": 1625851230481.226, "dur": 4.960, + "args": { + "External id": 3716148,"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": 1625851230487.477, "dur": 0.565, + "args": { + "External id": 3716149,"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": 1625851230490.449, "dur": 0.696, + "args": { + "External id": 3716150,"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": 1625851230515.522, "dur": 43.128, + "args": { + "External id": 3716151,"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": 1625851230589.914, "dur": 143.591, + "args": { + "External id": 3716152,"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": 1625851230602.724, "dur": 5.626, + "args": { + "External id": 3716153,"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": 1625851230613.775, "dur": 9.988, + "args": { + "External id": 3716154,"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": 1625851230617.881, "dur": 5.462, + "args": { + "External id": 3716155,"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": 1625851230621.632, "dur": 0.485, + "args": { + "External id": 3716156,"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": 1625851230630.663, "dur": 34.664, + "args": { + "External id": 3716157,"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": 1625851230633.138, "dur": 0.787, + "args": { + "External id": 3716158,"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": 1625851230635.694, "dur": 2.684, + "args": { + "External id": 3716159,"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": 1625851230640.251, "dur": 0.670, + "args": { + "External id": 3716160,"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": 1625851230642.562, "dur": 2.858, + "args": { + "External id": 3716161,"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": 1625851230649.028, "dur": 0.443, + "args": { + "External id": 3716162,"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": 1625851230650.858, "dur": 0.341, + "args": { + "External id": 3716163,"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": 1625851230652.488, "dur": 0.493, + "args": { + "External id": 3716164,"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": 1625851230656.584, "dur": 0.569, + "args": { + "External id": 3716165,"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": 1625851230658.663, "dur": 0.537, + "args": { + "External id": 3716166,"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": 1625851230695.621, "dur": 28.239, + "args": { + "External id": 3716167,"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": 1625851230788.293, "dur": 437.706, + "args": { + "External id": 3716168,"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": 1625851230819.621, "dur": 401.112, + "args": { + "External id": 3716169,"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": 1625851230831.428, "dur": 383.025, + "args": { + "External id": 3716170,"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": 1625851231254.927, "dur": 2.629, + "args": { + "External id": 3716171,"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": 1625851231349.299, "dur": 17040.073, + "args": { + "External id": 3716172,"Record function id": 0, "Ev Idx": 6883 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1625851231449.125, "dur": 6.575, + "args": { + "External id": 3716173,"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": 1625851231458.821, "dur": 1.320, + "args": { + "External id": 3716174,"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": 1625851231462.176, "dur": 3.460, + "args": { + "External id": 3716175,"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": 1625851231467.522, "dur": 1.411, + "args": { + "External id": 3716176,"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": 1625851231470.136, "dur": 1.091, + "args": { + "External id": 3716177,"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": 1625851231472.352, "dur": 1.016, + "args": { + "External id": 3716178,"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": 1625851231477.791, "dur": 1.071, + "args": { + "External id": 3716179,"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": 1625851231480.675, "dur": 3.207, + "args": { + "External id": 3716180,"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": 1625851231485.794, "dur": 0.988, + "args": { + "External id": 3716181,"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": 1625851231488.362, "dur": 1.122, + "args": { + "External id": 3716182,"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": 1625851231509.895, "dur": 16841.926, + "args": { + "External id": 3716183,"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": 1625851231526.360, "dur": 16819.182, + "args": { + "External id": 3716184,"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": 1625851231546.497, "dur": 13.387, + "args": { + "External id": 3716185,"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": 1625851231562.990, "dur": 16749.683, + "args": { + "External id": 3716186,"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": 1625851231565.281, "dur": 16746.828, + "args": { + "External id": 3716187,"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": 1625851231571.320, "dur": 7.332, + "args": { + "External id": 3716188,"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": 1625851231580.283, "dur": 16728.921, + "args": { + "External id": 3716189,"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": 1625851248523.694, "dur": 37.793, + "args": { + "External id": 3716190,"Sequence number": 37295095, "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": 1625851248523.694, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 1336756, "tid": 1336756, + "ts": 1625851248549.574, "dur": 7.636, + "args": { + "External id": 3716191,"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": 1625851248552.751, "dur": 4.258, + "args": { + "External id": 3716192,"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": 1625851248622.570, "dur": 87.917, + "args": { + "External id": 3716193,"Record function id": 0, "Ev Idx": 6904 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 1336756, "tid": 1336756, + "ts": 1625851248713.802, "dur": 1090.396, + "args": { + "External id": 3716194,"Record function id": 0, "Ev Idx": 6905 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 1336756, "tid": 1336756, + "ts": 1625851248755.864, "dur": 1035.665, + "args": { + "External id": 3716195,"Sequence number": 37295096, "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": 1625851248755.864, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 1336756, "tid": 1336756, + "ts": 1625851248822.464, "dur": 42.538, + "args": { + "External id": 3716196,"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": 1625851248877.594, "dur": 136.137, + "args": { + "External id": 3716197,"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": 1625851249028.947, "dur": 45.040, + "args": { + "External id": 3716198,"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": 1625851249082.661, "dur": 32.031, + "args": { + "External id": 3716199,"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": 1625851249144.075, "dur": 27.891, + "args": { + "External id": 3716200,"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": 1625851249190.692, "dur": 17.942, + "args": { + "External id": 3716201,"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": 1625851249228.486, "dur": 134.184, + "args": { + "External id": 3716202,"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": 1625851249278.060, "dur": 10.889, + "args": { + "External id": 3716203,"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": 1625851249282.970, "dur": 5.065, + "args": { + "External id": 3716204,"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": 1625851249291.624, "dur": 6.896, + "args": { + "External id": 3716205,"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": 1625851249300.110, "dur": 1.111, + "args": { + "External id": 3716206,"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": 1625851249303.624, "dur": 7.754, + "args": { + "External id": 3716207,"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": 1625851249374.019, "dur": 43.186, + "args": { + "External id": 3716208,"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": 1625851249446.738, "dur": 30.241, + "args": { + "External id": 3716209,"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": 1625851249486.850, "dur": 40.632, + "args": { + "External id": 3716210,"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": 1625851249537.923, "dur": 34.899, + "args": { + "External id": 3716211,"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": 1625851249594.158, "dur": 29.758, + "args": { + "External id": 3716212,"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": 1625851249629.023, "dur": 34.066, + "args": { + "External id": 3716213,"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": 1625851249700.651, "dur": 20.681, + "args": { + "External id": 3716214,"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": 1625851249867.365, "dur": 78.983, + "args": { + "External id": 3716215,"Record function id": 0, "Ev Idx": 6926 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 1336756, "tid": 1336756, + "ts": 1625851250058.821, "dur": 49.018, + "args": { + "External id": 3716216,"Record function id": 0, "Ev Idx": 6927 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.12)", "pid": 1336756, "tid": 1336756, + "ts": 1625851250117.317, "dur": 18181.076, + "args": { + "External id": 3716217,"Record function id": 0, "Ev Idx": 6928 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.12)", "pid": 1336756, "tid": 1336756, + "ts": 1625851250126.499, "dur": 904.340, + "args": { + "External id": 3716218,"Record function id": 0, "Ev Idx": 6929 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1625851250206.814, "dur": 8.491, + "args": { + "External id": 3716219,"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": 1625851250228.693, "dur": 48.320, + "args": { + "External id": 3716220,"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": 1625851250234.170, "dur": 2.594, + "args": { + "External id": 3716221,"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": 1625851250241.782, "dur": 0.433, + "args": { + "External id": 3716222,"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": 1625851250243.917, "dur": 0.616, + "args": { + "External id": 3716223,"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": 1625851250246.207, "dur": 1.177, + "args": { + "External id": 3716224,"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": 1625851250250.991, "dur": 0.825, + "args": { + "External id": 3716225,"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": 1625851250254.276, "dur": 0.972, + "args": { + "External id": 3716226,"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": 1625851250257.084, "dur": 4.775, + "args": { + "External id": 3716227,"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": 1625851250265.729, "dur": 0.408, + "args": { + "External id": 3716228,"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": 1625851250268.152, "dur": 0.341, + "args": { + "External id": 3716229,"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": 1625851250289.367, "dur": 42.033, + "args": { + "External id": 3716230,"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": 1625851250362.600, "dur": 121.983, + "args": { + "External id": 3716231,"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": 1625851250375.738, "dur": 3.599, + "args": { + "External id": 3716232,"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": 1625851250384.751, "dur": 12.459, + "args": { + "External id": 3716233,"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": 1625851250389.163, "dur": 7.602, + "args": { + "External id": 3716234,"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": 1625851250393.009, "dur": 2.493, + "args": { + "External id": 3716235,"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": 1625851250405.186, "dur": 33.626, + "args": { + "External id": 3716236,"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": 1625851250407.641, "dur": 0.811, + "args": { + "External id": 3716237,"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": 1625851250410.194, "dur": 0.661, + "args": { + "External id": 3716238,"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": 1625851250412.372, "dur": 0.838, + "args": { + "External id": 3716239,"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": 1625851250416.628, "dur": 2.299, + "args": { + "External id": 3716240,"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": 1625851250420.172, "dur": 0.287, + "args": { + "External id": 3716241,"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": 1625851250421.980, "dur": 2.555, + "args": { + "External id": 3716242,"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": 1625851250426.132, "dur": 0.438, + "args": { + "External id": 3716243,"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": 1625851250428.336, "dur": 0.387, + "args": { + "External id": 3716244,"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": 1625851250432.303, "dur": 0.305, + "args": { + "External id": 3716245,"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": 1625851250451.453, "dur": 25.039, + "args": { + "External id": 3716246,"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": 1625851250534.883, "dur": 364.025, + "args": { + "External id": 3716247,"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": 1625851250565.978, "dur": 327.868, + "args": { + "External id": 3716248,"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": 1625851250577.322, "dur": 307.483, + "args": { + "External id": 3716249,"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": 1625851250925.804, "dur": 2.347, + "args": { + "External id": 3716250,"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": 1625851251054.242, "dur": 17050.265, + "args": { + "External id": 3716251,"Record function id": 0, "Ev Idx": 6962 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1625851251161.029, "dur": 6.510, + "args": { + "External id": 3716252,"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": 1625851251171.157, "dur": 1.175, + "args": { + "External id": 3716253,"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": 1625851251174.137, "dur": 3.399, + "args": { + "External id": 3716254,"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": 1625851251179.126, "dur": 1.420, + "args": { + "External id": 3716255,"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": 1625851251182.169, "dur": 1.029, + "args": { + "External id": 3716256,"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": 1625851251184.454, "dur": 1.369, + "args": { + "External id": 3716257,"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": 1625851251189.623, "dur": 1.354, + "args": { + "External id": 3716258,"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": 1625851251192.667, "dur": 3.123, + "args": { + "External id": 3716259,"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": 1625851251197.563, "dur": 0.663, + "args": { + "External id": 3716260,"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": 1625851251199.728, "dur": 1.117, + "args": { + "External id": 3716261,"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": 1625851251221.861, "dur": 16845.039, + "args": { + "External id": 3716262,"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": 1625851251237.880, "dur": 16822.683, + "args": { + "External id": 3716263,"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": 1625851251261.374, "dur": 13.632, + "args": { + "External id": 3716264,"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": 1625851251277.991, "dur": 16748.788, + "args": { + "External id": 3716265,"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": 1625851251280.262, "dur": 16746.038, + "args": { + "External id": 3716266,"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": 1625851251286.568, "dur": 6.513, + "args": { + "External id": 3716267,"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": 1625851251294.931, "dur": 16728.543, + "args": { + "External id": 3716268,"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": 1625851268240.095, "dur": 34.974, + "args": { + "External id": 3716269,"Sequence number": 37295097, "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": 1625851268240.095, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 1336756, "tid": 1336756, + "ts": 1625851268263.095, "dur": 7.483, + "args": { + "External id": 3716270,"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": 1625851268266.404, "dur": 3.934, + "args": { + "External id": 3716271,"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": 1625851268337.265, "dur": 75.487, + "args": { + "External id": 3716272,"Record function id": 0, "Ev Idx": 6983 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 1336756, "tid": 1336756, + "ts": 1625851268414.312, "dur": 1084.318, + "args": { + "External id": 3716273,"Record function id": 0, "Ev Idx": 6984 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 1336756, "tid": 1336756, + "ts": 1625851268454.688, "dur": 1031.823, + "args": { + "External id": 3716274,"Sequence number": 37295098, "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": 1625851268454.688, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 1336756, "tid": 1336756, + "ts": 1625851268520.361, "dur": 40.175, + "args": { + "External id": 3716275,"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": 1625851268573.101, "dur": 101.040, + "args": { + "External id": 3716276,"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": 1625851268704.369, "dur": 43.491, + "args": { + "External id": 3716277,"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": 1625851268757.635, "dur": 30.778, + "args": { + "External id": 3716278,"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": 1625851268815.493, "dur": 28.899, + "args": { + "External id": 3716279,"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": 1625851268861.940, "dur": 16.090, + "args": { + "External id": 3716280,"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": 1625851268897.527, "dur": 171.453, + "args": { + "External id": 3716281,"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": 1625851268949.516, "dur": 10.948, + "args": { + "External id": 3716282,"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": 1625851268954.824, "dur": 4.946, + "args": { + "External id": 3716283,"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": 1625851268963.521, "dur": 6.169, + "args": { + "External id": 3716284,"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": 1625851268971.152, "dur": 0.893, + "args": { + "External id": 3716285,"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": 1625851268974.535, "dur": 5.608, + "args": { + "External id": 3716286,"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": 1625851269081.658, "dur": 51.196, + "args": { + "External id": 3716287,"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": 1625851269163.788, "dur": 28.194, + "args": { + "External id": 3716288,"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": 1625851269202.599, "dur": 40.923, + "args": { + "External id": 3716289,"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": 1625851269251.242, "dur": 34.596, + "args": { + "External id": 3716290,"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": 1625851269313.866, "dur": 27.291, + "args": { + "External id": 3716291,"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": 1625851269349.338, "dur": 33.598, + "args": { + "External id": 3716292,"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": 1625851269401.069, "dur": 19.102, + "args": { + "External id": 3716293,"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": 1625851269560.414, "dur": 73.802, + "args": { + "External id": 3716294,"Record function id": 0, "Ev Idx": 7005 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 1336756, "tid": 1336756, + "ts": 1625851269725.932, "dur": 47.755, + "args": { + "External id": 3716295,"Record function id": 0, "Ev Idx": 7006 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.13)", "pid": 1336756, "tid": 1336756, + "ts": 1625851269783.495, "dur": 18309.431, + "args": { + "External id": 3716296,"Record function id": 0, "Ev Idx": 7007 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.13)", "pid": 1336756, "tid": 1336756, + "ts": 1625851269791.631, "dur": 881.805, + "args": { + "External id": 3716297,"Record function id": 0, "Ev Idx": 7008 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1625851269868.018, "dur": 8.533, + "args": { + "External id": 3716298,"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": 1625851269889.928, "dur": 40.580, + "args": { + "External id": 3716299,"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": 1625851269895.342, "dur": 2.311, + "args": { + "External id": 3716300,"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": 1625851269902.956, "dur": 0.400, + "args": { + "External id": 3716301,"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": 1625851269905.101, "dur": 0.643, + "args": { + "External id": 3716302,"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": 1625851269907.368, "dur": 0.359, + "args": { + "External id": 3716303,"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": 1625851269911.509, "dur": 0.404, + "args": { + "External id": 3716304,"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": 1625851269913.544, "dur": 0.372, + "args": { + "External id": 3716305,"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": 1625851269915.335, "dur": 2.961, + "args": { + "External id": 3716306,"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": 1625851269919.783, "dur": 0.360, + "args": { + "External id": 3716307,"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": 1625851269922.064, "dur": 0.355, + "args": { + "External id": 3716308,"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": 1625851269942.681, "dur": 73.414, + "args": { + "External id": 3716309,"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": 1625851270052.905, "dur": 130.599, + "args": { + "External id": 3716310,"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": 1625851270067.501, "dur": 4.816, + "args": { + "External id": 3716311,"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": 1625851270077.165, "dur": 11.173, + "args": { + "External id": 3716312,"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": 1625851270081.314, "dur": 6.612, + "args": { + "External id": 3716313,"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": 1625851270085.636, "dur": 0.651, + "args": { + "External id": 3716314,"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": 1625851270096.102, "dur": 37.596, + "args": { + "External id": 3716315,"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": 1625851270098.973, "dur": 2.617, + "args": { + "External id": 3716316,"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": 1625851270104.009, "dur": 0.476, + "args": { + "External id": 3716317,"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": 1625851270106.819, "dur": 0.501, + "args": { + "External id": 3716318,"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": 1625851270111.016, "dur": 2.343, + "args": { + "External id": 3716319,"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": 1625851270114.976, "dur": 0.296, + "args": { + "External id": 3716320,"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": 1625851270117.173, "dur": 0.377, + "args": { + "External id": 3716321,"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": 1625851270121.203, "dur": 0.444, + "args": { + "External id": 3716322,"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": 1625851270123.460, "dur": 0.248, + "args": { + "External id": 3716323,"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": 1625851270124.973, "dur": 2.213, + "args": { + "External id": 3716324,"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": 1625851270148.024, "dur": 27.180, + "args": { + "External id": 3716325,"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": 1625851270237.411, "dur": 346.408, + "args": { + "External id": 3716326,"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": 1625851270271.625, "dur": 307.535, + "args": { + "External id": 3716327,"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": 1625851270281.093, "dur": 292.631, + "args": { + "External id": 3716328,"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": 1625851270608.022, "dur": 1.913, + "args": { + "External id": 3716329,"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": 1625851270716.439, "dur": 17156.893, + "args": { + "External id": 3716330,"Record function id": 0, "Ev Idx": 7041 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1625851270820.228, "dur": 5.891, + "args": { + "External id": 3716331,"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": 1625851270829.302, "dur": 1.017, + "args": { + "External id": 3716332,"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": 1625851270831.969, "dur": 3.127, + "args": { + "External id": 3716333,"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": 1625851270836.550, "dur": 1.379, + "args": { + "External id": 3716334,"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": 1625851270839.031, "dur": 1.141, + "args": { + "External id": 3716335,"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": 1625851270841.382, "dur": 1.259, + "args": { + "External id": 3716336,"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": 1625851270845.740, "dur": 1.068, + "args": { + "External id": 3716337,"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": 1625851270848.792, "dur": 2.958, + "args": { + "External id": 3716338,"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": 1625851270853.110, "dur": 1.043, + "args": { + "External id": 3716339,"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": 1625851270855.513, "dur": 1.063, + "args": { + "External id": 3716340,"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": 1625851270877.447, "dur": 16957.621, + "args": { + "External id": 3716341,"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": 1625851270893.306, "dur": 16934.836, + "args": { + "External id": 3716342,"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": 1625851270918.465, "dur": 14.190, + "args": { + "External id": 3716343,"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": 1625851270935.466, "dur": 16859.852, + "args": { + "External id": 3716344,"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": 1625851270938.228, "dur": 16856.548, + "args": { + "External id": 3716345,"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": 1625851270945.092, "dur": 4.958, + "args": { + "External id": 3716346,"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": 1625851270951.759, "dur": 16839.936, + "args": { + "External id": 3716347,"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": 1625851288031.448, "dur": 36.188, + "args": { + "External id": 3716348,"Sequence number": 37295099, "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": 1625851288031.448, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 1336756, "tid": 1336756, + "ts": 1625851288055.142, "dur": 7.858, + "args": { + "External id": 3716349,"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": 1625851288058.194, "dur": 4.456, + "args": { + "External id": 3716350,"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": 1625851288134.043, "dur": 75.438, + "args": { + "External id": 3716351,"Record function id": 0, "Ev Idx": 7062 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 1336756, "tid": 1336756, + "ts": 1625851288210.913, "dur": 1084.844, + "args": { + "External id": 3716352,"Record function id": 0, "Ev Idx": 7063 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 1336756, "tid": 1336756, + "ts": 1625851288251.774, "dur": 1031.124, + "args": { + "External id": 3716353,"Sequence number": 37295100, "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": 1625851288251.774, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 1336756, "tid": 1336756, + "ts": 1625851288319.941, "dur": 42.199, + "args": { + "External id": 3716354,"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": 1625851288374.187, "dur": 100.769, + "args": { + "External id": 3716355,"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": 1625851288486.810, "dur": 37.977, + "args": { + "External id": 3716356,"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": 1625851288533.338, "dur": 32.576, + "args": { + "External id": 3716357,"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": 1625851288590.996, "dur": 26.984, + "args": { + "External id": 3716358,"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": 1625851288636.850, "dur": 17.113, + "args": { + "External id": 3716359,"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": 1625851288671.620, "dur": 148.213, + "args": { + "External id": 3716360,"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": 1625851288738.733, "dur": 11.735, + "args": { + "External id": 3716361,"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": 1625851288743.596, "dur": 5.892, + "args": { + "External id": 3716362,"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": 1625851288753.309, "dur": 6.153, + "args": { + "External id": 3716363,"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": 1625851288760.879, "dur": 0.804, + "args": { + "External id": 3716364,"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": 1625851288764.189, "dur": 4.227, + "args": { + "External id": 3716365,"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": 1625851288831.151, "dur": 46.692, + "args": { + "External id": 3716366,"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": 1625851288908.274, "dur": 28.356, + "args": { + "External id": 3716367,"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": 1625851288945.506, "dur": 78.481, + "args": { + "External id": 3716368,"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": 1625851289035.231, "dur": 38.741, + "args": { + "External id": 3716369,"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": 1625851289099.370, "dur": 29.760, + "args": { + "External id": 3716370,"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": 1625851289135.269, "dur": 36.144, + "args": { + "External id": 3716371,"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": 1625851289191.455, "dur": 19.032, + "args": { + "External id": 3716372,"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": 1625851289357.979, "dur": 76.348, + "args": { + "External id": 3716373,"Record function id": 0, "Ev Idx": 7084 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 1336756, "tid": 1336756, + "ts": 1625851289507.523, "dur": 45.680, + "args": { + "External id": 3716374,"Record function id": 0, "Ev Idx": 7085 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.14)", "pid": 1336756, "tid": 1336756, + "ts": 1625851289563.053, "dur": 18163.741, + "args": { + "External id": 3716375,"Record function id": 0, "Ev Idx": 7086 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.14)", "pid": 1336756, "tid": 1336756, + "ts": 1625851289571.409, "dur": 920.466, + "args": { + "External id": 3716376,"Record function id": 0, "Ev Idx": 7087 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1625851289651.689, "dur": 6.807, + "args": { + "External id": 3716377,"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": 1625851289672.610, "dur": 71.390, + "args": { + "External id": 3716378,"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": 1625851289695.559, "dur": 2.392, + "args": { + "External id": 3716379,"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": 1625851289703.493, "dur": 0.496, + "args": { + "External id": 3716380,"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": 1625851289705.800, "dur": 0.689, + "args": { + "External id": 3716381,"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": 1625851289708.961, "dur": 0.307, + "args": { + "External id": 3716382,"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": 1625851289713.602, "dur": 0.646, + "args": { + "External id": 3716383,"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": 1625851289715.896, "dur": 0.452, + "args": { + "External id": 3716384,"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": 1625851289722.572, "dur": 5.240, + "args": { + "External id": 3716385,"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": 1625851289732.743, "dur": 0.583, + "args": { + "External id": 3716386,"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": 1625851289735.152, "dur": 0.332, + "args": { + "External id": 3716387,"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": 1625851289759.105, "dur": 41.823, + "args": { + "External id": 3716388,"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": 1625851289835.494, "dur": 119.801, + "args": { + "External id": 3716389,"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": 1625851289849.450, "dur": 6.243, + "args": { + "External id": 3716390,"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": 1625851289860.981, "dur": 10.239, + "args": { + "External id": 3716391,"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": 1625851289865.161, "dur": 5.653, + "args": { + "External id": 3716392,"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": 1625851289868.932, "dur": 0.520, + "args": { + "External id": 3716393,"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": 1625851289879.252, "dur": 33.382, + "args": { + "External id": 3716394,"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": 1625851289881.971, "dur": 0.507, + "args": { + "External id": 3716395,"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": 1625851289884.237, "dur": 2.643, + "args": { + "External id": 3716396,"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": 1625851289888.467, "dur": 0.563, + "args": { + "External id": 3716397,"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": 1625851289891.184, "dur": 2.554, + "args": { + "External id": 3716398,"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": 1625851289897.412, "dur": 0.287, + "args": { + "External id": 3716399,"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": 1625851289899.228, "dur": 0.578, + "args": { + "External id": 3716400,"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": 1625851289901.349, "dur": 0.258, + "args": { + "External id": 3716401,"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": 1625851289904.993, "dur": 0.285, + "args": { + "External id": 3716402,"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": 1625851289906.760, "dur": 0.249, + "args": { + "External id": 3716403,"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": 1625851289924.047, "dur": 23.257, + "args": { + "External id": 3716404,"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": 1625851290048.044, "dur": 352.423, + "args": { + "External id": 3716405,"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": 1625851290084.228, "dur": 311.343, + "args": { + "External id": 3716406,"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": 1625851290094.985, "dur": 294.826, + "args": { + "External id": 3716407,"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": 1625851290425.302, "dur": 2.153, + "args": { + "External id": 3716408,"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": 1625851290511.314, "dur": 17006.184, + "args": { + "External id": 3716409,"Record function id": 0, "Ev Idx": 7120 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1625851290605.230, "dur": 6.244, + "args": { + "External id": 3716410,"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": 1625851290614.665, "dur": 1.396, + "args": { + "External id": 3716411,"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": 1625851290617.805, "dur": 2.693, + "args": { + "External id": 3716412,"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": 1625851290622.239, "dur": 1.077, + "args": { + "External id": 3716413,"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": 1625851290624.840, "dur": 0.833, + "args": { + "External id": 3716414,"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": 1625851290627.073, "dur": 1.173, + "args": { + "External id": 3716415,"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": 1625851290632.293, "dur": 1.076, + "args": { + "External id": 3716416,"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": 1625851290634.832, "dur": 2.419, + "args": { + "External id": 3716417,"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": 1625851290638.724, "dur": 1.171, + "args": { + "External id": 3716418,"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": 1625851290641.476, "dur": 0.856, + "args": { + "External id": 3716419,"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": 1625851290662.716, "dur": 16816.749, + "args": { + "External id": 3716420,"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": 1625851290695.867, "dur": 16776.922, + "args": { + "External id": 3716421,"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": 1625851290719.597, "dur": 14.808, + "args": { + "External id": 3716422,"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": 1625851290737.783, "dur": 16702.648, + "args": { + "External id": 3716423,"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": 1625851290740.131, "dur": 16699.687, + "args": { + "External id": 3716424,"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": 1625851290746.397, "dur": 6.024, + "args": { + "External id": 3716425,"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": 1625851290754.054, "dur": 16682.810, + "args": { + "External id": 3716426,"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": 1625851307652.731, "dur": 48.141, + "args": { + "External id": 3716427,"Sequence number": 37295101, "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": 1625851307652.731, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 1336756, "tid": 1336756, + "ts": 1625851307687.336, "dur": 8.340, + "args": { + "External id": 3716428,"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": 1625851307690.989, "dur": 4.268, + "args": { + "External id": 3716429,"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": 1625851307767.064, "dur": 77.329, + "args": { + "External id": 3716430,"Record function id": 0, "Ev Idx": 7141 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 1336756, "tid": 1336756, + "ts": 1625851307846.061, "dur": 1081.945, + "args": { + "External id": 3716431,"Record function id": 0, "Ev Idx": 7142 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 1336756, "tid": 1336756, + "ts": 1625851307887.255, "dur": 1028.751, + "args": { + "External id": 3716432,"Sequence number": 37295102, "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": 1625851307887.255, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 1336756, "tid": 1336756, + "ts": 1625851307953.889, "dur": 70.035, + "args": { + "External id": 3716433,"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": 1625851308039.603, "dur": 102.763, + "args": { + "External id": 3716434,"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": 1625851308152.833, "dur": 38.139, + "args": { + "External id": 3716435,"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": 1625851308200.057, "dur": 30.338, + "args": { + "External id": 3716436,"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": 1625851308257.884, "dur": 27.989, + "args": { + "External id": 3716437,"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": 1625851308305.079, "dur": 14.267, + "args": { + "External id": 3716438,"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": 1625851308338.576, "dur": 134.040, + "args": { + "External id": 3716439,"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": 1625851308390.168, "dur": 12.224, + "args": { + "External id": 3716440,"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": 1625851308396.011, "dur": 5.696, + "args": { + "External id": 3716441,"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": 1625851308405.336, "dur": 6.971, + "args": { + "External id": 3716442,"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": 1625851308413.664, "dur": 1.649, + "args": { + "External id": 3716443,"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": 1625851308417.968, "dur": 5.203, + "args": { + "External id": 3716444,"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": 1625851308488.700, "dur": 44.596, + "args": { + "External id": 3716445,"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": 1625851308570.344, "dur": 27.118, + "args": { + "External id": 3716446,"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": 1625851308607.222, "dur": 40.585, + "args": { + "External id": 3716447,"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": 1625851308655.974, "dur": 54.005, + "args": { + "External id": 3716448,"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": 1625851308736.030, "dur": 28.859, + "args": { + "External id": 3716449,"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": 1625851308770.610, "dur": 36.827, + "args": { + "External id": 3716450,"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": 1625851308829.738, "dur": 18.319, + "args": { + "External id": 3716451,"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": 1625851309026.866, "dur": 78.521, + "args": { + "External id": 3716452,"Record function id": 0, "Ev Idx": 7163 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 1336756, "tid": 1336756, + "ts": 1625851309180.580, "dur": 47.561, + "args": { + "External id": 3716453,"Record function id": 0, "Ev Idx": 7164 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.15)", "pid": 1336756, "tid": 1336756, + "ts": 1625851309238.025, "dur": 18269.420, + "args": { + "External id": 3716454,"Record function id": 0, "Ev Idx": 7165 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.15)", "pid": 1336756, "tid": 1336756, + "ts": 1625851309246.549, "dur": 916.156, + "args": { + "External id": 3716455,"Record function id": 0, "Ev Idx": 7166 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1625851309329.739, "dur": 8.413, + "args": { + "External id": 3716456,"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": 1625851309351.734, "dur": 42.953, + "args": { + "External id": 3716457,"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": 1625851309357.365, "dur": 2.533, + "args": { + "External id": 3716458,"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": 1625851309364.653, "dur": 0.385, + "args": { + "External id": 3716459,"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": 1625851309366.787, "dur": 0.394, + "args": { + "External id": 3716460,"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": 1625851309368.941, "dur": 0.276, + "args": { + "External id": 3716461,"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": 1625851309372.964, "dur": 0.548, + "args": { + "External id": 3716462,"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": 1625851309375.147, "dur": 0.763, + "args": { + "External id": 3716463,"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": 1625851309377.816, "dur": 4.577, + "args": { + "External id": 3716464,"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": 1625851309384.472, "dur": 0.477, + "args": { + "External id": 3716465,"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": 1625851309386.658, "dur": 0.578, + "args": { + "External id": 3716466,"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": 1625851309407.045, "dur": 39.164, + "args": { + "External id": 3716467,"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": 1625851309477.556, "dur": 123.005, + "args": { + "External id": 3716468,"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": 1625851309488.023, "dur": 3.935, + "args": { + "External id": 3716469,"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": 1625851309496.660, "dur": 10.644, + "args": { + "External id": 3716470,"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": 1625851309501.106, "dur": 5.794, + "args": { + "External id": 3716471,"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": 1625851309504.729, "dur": 0.871, + "args": { + "External id": 3716472,"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": 1625851309514.249, "dur": 34.001, + "args": { + "External id": 3716473,"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": 1625851309516.525, "dur": 2.617, + "args": { + "External id": 3716474,"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": 1625851309520.904, "dur": 0.519, + "args": { + "External id": 3716475,"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": 1625851309523.147, "dur": 0.577, + "args": { + "External id": 3716476,"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": 1625851309527.753, "dur": 3.076, + "args": { + "External id": 3716477,"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": 1625851309532.429, "dur": 0.438, + "args": { + "External id": 3716478,"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": 1625851309534.600, "dur": 0.537, + "args": { + "External id": 3716479,"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": 1625851309537.017, "dur": 0.548, + "args": { + "External id": 3716480,"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": 1625851309539.072, "dur": 0.430, + "args": { + "External id": 3716481,"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": 1625851309540.903, "dur": 2.346, + "args": { + "External id": 3716482,"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": 1625851309570.587, "dur": 22.690, + "args": { + "External id": 3716483,"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": 1625851309651.596, "dur": 409.353, + "args": { + "External id": 3716484,"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": 1625851309701.317, "dur": 353.861, + "args": { + "External id": 3716485,"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": 1625851309714.830, "dur": 334.645, + "args": { + "External id": 3716486,"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": 1625851310089.347, "dur": 2.421, + "args": { + "External id": 3716487,"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": 1625851310184.267, "dur": 17120.757, + "args": { + "External id": 3716488,"Record function id": 0, "Ev Idx": 7199 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1625851310282.496, "dur": 6.439, + "args": { + "External id": 3716489,"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": 1625851310292.220, "dur": 1.351, + "args": { + "External id": 3716490,"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": 1625851310295.593, "dur": 3.067, + "args": { + "External id": 3716491,"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": 1625851310300.334, "dur": 0.888, + "args": { + "External id": 3716492,"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": 1625851310302.749, "dur": 1.274, + "args": { + "External id": 3716493,"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": 1625851310305.410, "dur": 0.848, + "args": { + "External id": 3716494,"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": 1625851310310.297, "dur": 1.039, + "args": { + "External id": 3716495,"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": 1625851310312.855, "dur": 2.205, + "args": { + "External id": 3716496,"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": 1625851310316.613, "dur": 0.890, + "args": { + "External id": 3716497,"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": 1625851310319.240, "dur": 0.938, + "args": { + "External id": 3716498,"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": 1625851310340.725, "dur": 16925.546, + "args": { + "External id": 3716499,"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": 1625851310356.306, "dur": 16902.840, + "args": { + "External id": 3716500,"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": 1625851310377.082, "dur": 14.719, + "args": { + "External id": 3716501,"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": 1625851310394.772, "dur": 16830.459, + "args": { + "External id": 3716502,"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": 1625851310397.368, "dur": 16827.416, + "args": { + "External id": 3716503,"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": 1625851310403.700, "dur": 5.447, + "args": { + "External id": 3716504,"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": 1625851310410.955, "dur": 16810.985, + "args": { + "External id": 3716505,"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": 1625851327442.364, "dur": 40.417, + "args": { + "External id": 3716506,"Sequence number": 37295103, "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": 1625851327442.364, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 1336756, "tid": 1336756, + "ts": 1625851327470.106, "dur": 7.808, + "args": { + "External id": 3716507,"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": 1625851327473.440, "dur": 4.215, + "args": { + "External id": 3716508,"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": 1625851327547.712, "dur": 75.371, + "args": { + "External id": 3716509,"Record function id": 0, "Ev Idx": 7220 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 1336756, "tid": 1336756, + "ts": 1625851327624.927, "dur": 1099.908, + "args": { + "External id": 3716510,"Record function id": 0, "Ev Idx": 7221 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 1336756, "tid": 1336756, + "ts": 1625851327667.655, "dur": 1043.503, + "args": { + "External id": 3716511,"Sequence number": 37295104, "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": 1625851327667.655, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 1336756, "tid": 1336756, + "ts": 1625851327750.437, "dur": 41.050, + "args": { + "External id": 3716512,"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": 1625851327803.464, "dur": 101.945, + "args": { + "External id": 3716513,"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": 1625851327915.611, "dur": 41.310, + "args": { + "External id": 3716514,"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": 1625851327965.975, "dur": 65.788, + "args": { + "External id": 3716515,"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": 1625851328062.441, "dur": 27.166, + "args": { + "External id": 3716516,"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": 1625851328110.144, "dur": 17.242, + "args": { + "External id": 3716517,"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": 1625851328147.637, "dur": 130.166, + "args": { + "External id": 3716518,"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": 1625851328196.291, "dur": 11.832, + "args": { + "External id": 3716519,"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": 1625851328202.110, "dur": 5.245, + "args": { + "External id": 3716520,"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": 1625851328210.900, "dur": 6.598, + "args": { + "External id": 3716521,"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": 1625851328218.886, "dur": 1.503, + "args": { + "External id": 3716522,"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": 1625851328222.854, "dur": 5.724, + "args": { + "External id": 3716523,"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": 1625851328287.969, "dur": 48.649, + "args": { + "External id": 3716524,"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": 1625851328365.682, "dur": 30.485, + "args": { + "External id": 3716525,"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": 1625851328406.113, "dur": 41.131, + "args": { + "External id": 3716526,"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": 1625851328456.276, "dur": 34.846, + "args": { + "External id": 3716527,"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": 1625851328515.348, "dur": 30.453, + "args": { + "External id": 3716528,"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": 1625851328550.855, "dur": 33.747, + "args": { + "External id": 3716529,"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": 1625851328604.623, "dur": 18.070, + "args": { + "External id": 3716530,"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": 1625851328787.000, "dur": 74.001, + "args": { + "External id": 3716531,"Record function id": 0, "Ev Idx": 7242 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 1336756, "tid": 1336756, + "ts": 1625851328931.851, "dur": 46.186, + "args": { + "External id": 3716532,"Record function id": 0, "Ev Idx": 7243 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.16)", "pid": 1336756, "tid": 1336756, + "ts": 1625851329037.465, "dur": 18257.907, + "args": { + "External id": 3716533,"Record function id": 0, "Ev Idx": 7244 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.16)", "pid": 1336756, "tid": 1336756, + "ts": 1625851329047.154, "dur": 881.255, + "args": { + "External id": 3716534,"Record function id": 0, "Ev Idx": 7245 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1625851329129.590, "dur": 9.043, + "args": { + "External id": 3716535,"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": 1625851329153.296, "dur": 42.795, + "args": { + "External id": 3716536,"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": 1625851329158.959, "dur": 2.409, + "args": { + "External id": 3716537,"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": 1625851329166.828, "dur": 0.419, + "args": { + "External id": 3716538,"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": 1625851329168.774, "dur": 0.469, + "args": { + "External id": 3716539,"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": 1625851329170.959, "dur": 0.582, + "args": { + "External id": 3716540,"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": 1625851329175.023, "dur": 0.763, + "args": { + "External id": 3716541,"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": 1625851329177.645, "dur": 0.642, + "args": { + "External id": 3716542,"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": 1625851329179.888, "dur": 4.672, + "args": { + "External id": 3716543,"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": 1625851329186.680, "dur": 0.594, + "args": { + "External id": 3716544,"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": 1625851329188.830, "dur": 0.398, + "args": { + "External id": 3716545,"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": 1625851329209.149, "dur": 41.114, + "args": { + "External id": 3716546,"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": 1625851329282.359, "dur": 120.766, + "args": { + "External id": 3716547,"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": 1625851329293.119, "dur": 4.305, + "args": { + "External id": 3716548,"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": 1625851329302.769, "dur": 13.698, + "args": { + "External id": 3716549,"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": 1625851329310.543, "dur": 5.485, + "args": { + "External id": 3716550,"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": 1625851329314.069, "dur": 0.689, + "args": { + "External id": 3716551,"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": 1625851329324.449, "dur": 35.258, + "args": { + "External id": 3716552,"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": 1625851329326.844, "dur": 2.682, + "args": { + "External id": 3716553,"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": 1625851329331.116, "dur": 0.506, + "args": { + "External id": 3716554,"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": 1625851329333.290, "dur": 0.569, + "args": { + "External id": 3716555,"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": 1625851329338.046, "dur": 2.106, + "args": { + "External id": 3716556,"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": 1625851329341.578, "dur": 0.606, + "args": { + "External id": 3716557,"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": 1625851329344.132, "dur": 0.615, + "args": { + "External id": 3716558,"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": 1625851329348.145, "dur": 0.721, + "args": { + "External id": 3716559,"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": 1625851329350.326, "dur": 0.806, + "args": { + "External id": 3716560,"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": 1625851329352.678, "dur": 2.387, + "args": { + "External id": 3716561,"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": 1625851329372.006, "dur": 23.523, + "args": { + "External id": 3716562,"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": 1625851329454.899, "dur": 374.495, + "args": { + "External id": 3716563,"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": 1625851329489.648, "dur": 334.449, + "args": { + "External id": 3716564,"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": 1625851329499.376, "dur": 319.106, + "args": { + "External id": 3716565,"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": 1625851329857.427, "dur": 2.433, + "args": { + "External id": 3716566,"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": 1625851329949.562, "dur": 17147.271, + "args": { + "External id": 3716567,"Record function id": 0, "Ev Idx": 7278 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1625851330092.351, "dur": 6.426, + "args": { + "External id": 3716568,"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": 1625851330102.651, "dur": 1.355, + "args": { + "External id": 3716569,"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": 1625851330105.704, "dur": 3.324, + "args": { + "External id": 3716570,"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": 1625851330110.763, "dur": 1.184, + "args": { + "External id": 3716571,"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": 1625851330113.117, "dur": 0.895, + "args": { + "External id": 3716572,"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": 1625851330115.153, "dur": 0.945, + "args": { + "External id": 3716573,"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": 1625851330119.686, "dur": 0.927, + "args": { + "External id": 3716574,"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": 1625851330122.300, "dur": 2.097, + "args": { + "External id": 3716575,"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": 1625851330126.355, "dur": 0.789, + "args": { + "External id": 3716576,"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": 1625851330128.459, "dur": 0.711, + "args": { + "External id": 3716577,"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": 1625851330151.804, "dur": 16907.327, + "args": { + "External id": 3716578,"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": 1625851330168.433, "dur": 16884.413, + "args": { + "External id": 3716579,"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": 1625851330191.229, "dur": 13.988, + "args": { + "External id": 3716580,"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": 1625851330208.010, "dur": 16811.751, + "args": { + "External id": 3716581,"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": 1625851330210.714, "dur": 16808.607, + "args": { + "External id": 3716582,"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": 1625851330217.225, "dur": 5.478, + "args": { + "External id": 3716583,"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": 1625851330224.476, "dur": 16791.782, + "args": { + "External id": 3716584,"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": 1625851347233.797, "dur": 35.815, + "args": { + "External id": 3716585,"Sequence number": 37295105, "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": 1625851347233.797, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 1336756, "tid": 1336756, + "ts": 1625851347258.138, "dur": 7.145, + "args": { + "External id": 3716586,"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": 1625851347261.175, "dur": 3.938, + "args": { + "External id": 3716587,"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": 1625851347333.965, "dur": 77.119, + "args": { + "External id": 3716588,"Record function id": 0, "Ev Idx": 7299 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 1336756, "tid": 1336756, + "ts": 1625851347412.813, "dur": 1144.133, + "args": { + "External id": 3716589,"Record function id": 0, "Ev Idx": 7300 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 1336756, "tid": 1336756, + "ts": 1625851347453.705, "dur": 1090.003, + "args": { + "External id": 3716590,"Sequence number": 37295106, "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": 1625851347453.705, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 1336756, "tid": 1336756, + "ts": 1625851347519.504, "dur": 40.854, + "args": { + "External id": 3716591,"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": 1625851347572.627, "dur": 101.529, + "args": { + "External id": 3716592,"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": 1625851347705.837, "dur": 44.877, + "args": { + "External id": 3716593,"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": 1625851347759.711, "dur": 30.782, + "args": { + "External id": 3716594,"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": 1625851347825.556, "dur": 30.995, + "args": { + "External id": 3716595,"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": 1625851347873.634, "dur": 16.304, + "args": { + "External id": 3716596,"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": 1625851347908.252, "dur": 176.751, + "args": { + "External id": 3716597,"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": 1625851347959.482, "dur": 11.234, + "args": { + "External id": 3716598,"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": 1625851347964.697, "dur": 5.289, + "args": { + "External id": 3716599,"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": 1625851347973.677, "dur": 6.842, + "args": { + "External id": 3716600,"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": 1625851348016.678, "dur": 2.402, + "args": { + "External id": 3716601,"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": 1625851348022.320, "dur": 7.608, + "args": { + "External id": 3716602,"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": 1625851348096.189, "dur": 54.234, + "args": { + "External id": 3716603,"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": 1625851348183.652, "dur": 33.034, + "args": { + "External id": 3716604,"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": 1625851348227.302, "dur": 40.501, + "args": { + "External id": 3716605,"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": 1625851348274.466, "dur": 35.009, + "args": { + "External id": 3716606,"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": 1625851348334.618, "dur": 29.674, + "args": { + "External id": 3716607,"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": 1625851348371.798, "dur": 35.731, + "args": { + "External id": 3716608,"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": 1625851348453.938, "dur": 24.228, + "args": { + "External id": 3716609,"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": 1625851348620.776, "dur": 95.555, + "args": { + "External id": 3716610,"Record function id": 0, "Ev Idx": 7321 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 1336756, "tid": 1336756, + "ts": 1625851348791.630, "dur": 46.791, + "args": { + "External id": 3716611,"Record function id": 0, "Ev Idx": 7322 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.17)", "pid": 1336756, "tid": 1336756, + "ts": 1625851348847.609, "dur": 18172.027, + "args": { + "External id": 3716612,"Record function id": 0, "Ev Idx": 7323 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.17)", "pid": 1336756, "tid": 1336756, + "ts": 1625851348856.211, "dur": 948.818, + "args": { + "External id": 3716613,"Record function id": 0, "Ev Idx": 7324 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1625851348938.091, "dur": 9.622, + "args": { + "External id": 3716614,"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": 1625851348961.407, "dur": 75.320, + "args": { + "External id": 3716615,"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": 1625851348966.800, "dur": 2.241, + "args": { + "External id": 3716616,"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": 1625851348973.837, "dur": 0.492, + "args": { + "External id": 3716617,"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": 1625851348975.688, "dur": 0.394, + "args": { + "External id": 3716618,"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": 1625851348977.729, "dur": 0.616, + "args": { + "External id": 3716619,"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": 1625851349017.116, "dur": 0.545, + "args": { + "External id": 3716620,"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": 1625851349019.656, "dur": 0.497, + "args": { + "External id": 3716621,"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": 1625851349021.532, "dur": 4.538, + "args": { + "External id": 3716622,"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": 1625851349027.776, "dur": 0.379, + "args": { + "External id": 3716623,"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": 1625851349029.581, "dur": 0.325, + "args": { + "External id": 3716624,"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": 1625851349051.041, "dur": 40.796, + "args": { + "External id": 3716625,"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": 1625851349125.496, "dur": 121.521, + "args": { + "External id": 3716626,"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": 1625851349137.301, "dur": 5.190, + "args": { + "External id": 3716627,"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": 1625851349147.274, "dur": 10.095, + "args": { + "External id": 3716628,"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": 1625851349151.319, "dur": 5.628, + "args": { + "External id": 3716629,"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": 1625851349155.109, "dur": 0.444, + "args": { + "External id": 3716630,"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": 1625851349165.076, "dur": 34.617, + "args": { + "External id": 3716631,"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": 1625851349167.482, "dur": 2.527, + "args": { + "External id": 3716632,"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": 1625851349171.672, "dur": 0.323, + "args": { + "External id": 3716633,"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": 1625851349173.667, "dur": 0.420, + "args": { + "External id": 3716634,"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": 1625851349178.061, "dur": 2.315, + "args": { + "External id": 3716635,"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": 1625851349182.498, "dur": 0.310, + "args": { + "External id": 3716636,"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": 1625851349184.027, "dur": 0.254, + "args": { + "External id": 3716637,"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": 1625851349188.158, "dur": 0.365, + "args": { + "External id": 3716638,"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": 1625851349190.038, "dur": 0.316, + "args": { + "External id": 3716639,"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": 1625851349192.362, "dur": 2.340, + "args": { + "External id": 3716640,"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": 1625851349214.377, "dur": 24.982, + "args": { + "External id": 3716641,"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": 1625851349301.558, "dur": 403.662, + "args": { + "External id": 3716642,"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": 1625851349334.557, "dur": 364.627, + "args": { + "External id": 3716643,"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": 1625851349344.539, "dur": 330.753, + "args": { + "External id": 3716644,"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": 1625851349732.366, "dur": 3.054, + "args": { + "External id": 3716645,"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": 1625851349824.622, "dur": 16972.881, + "args": { + "External id": 3716646,"Record function id": 0, "Ev Idx": 7357 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1625851349928.130, "dur": 6.065, + "args": { + "External id": 3716647,"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": 1625851349937.569, "dur": 1.579, + "args": { + "External id": 3716648,"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": 1625851349940.996, "dur": 3.400, + "args": { + "External id": 3716649,"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": 1625851349946.033, "dur": 0.816, + "args": { + "External id": 3716650,"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": 1625851349948.234, "dur": 0.959, + "args": { + "External id": 3716651,"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": 1625851349950.453, "dur": 0.906, + "args": { + "External id": 3716652,"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": 1625851349955.105, "dur": 1.051, + "args": { + "External id": 3716653,"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": 1625851349957.619, "dur": 1.651, + "args": { + "External id": 3716654,"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": 1625851349960.912, "dur": 0.928, + "args": { + "External id": 3716655,"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": 1625851349963.303, "dur": 0.857, + "args": { + "External id": 3716656,"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": 1625851350019.639, "dur": 16740.390, + "args": { + "External id": 3716657,"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": 1625851350036.723, "dur": 16716.650, + "args": { + "External id": 3716658,"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": 1625851350064.296, "dur": 15.331, + "args": { + "External id": 3716659,"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": 1625851350082.656, "dur": 16638.127, + "args": { + "External id": 3716660,"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": 1625851350084.836, "dur": 16635.399, + "args": { + "External id": 3716661,"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": 1625851350091.222, "dur": 6.647, + "args": { + "External id": 3716662,"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": 1625851350099.901, "dur": 16617.508, + "args": { + "External id": 3716663,"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": 1625851366932.778, "dur": 35.780, + "args": { + "External id": 3716664,"Sequence number": 37295107, "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": 1625851366932.778, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 1336756, "tid": 1336756, + "ts": 1625851366957.343, "dur": 7.018, + "args": { + "External id": 3716665,"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": 1625851366960.512, "dur": 3.666, + "args": { + "External id": 3716666,"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": 1625851367061.239, "dur": 79.751, + "args": { + "External id": 3716667,"Record function id": 0, "Ev Idx": 7378 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 1336756, "tid": 1336756, + "ts": 1625851367142.776, "dur": 1092.874, + "args": { + "External id": 3716668,"Record function id": 0, "Ev Idx": 7379 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 1336756, "tid": 1336756, + "ts": 1625851367184.289, "dur": 1038.780, + "args": { + "External id": 3716669,"Sequence number": 37295108, "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": 1625851367184.289, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 1336756, "tid": 1336756, + "ts": 1625851367253.201, "dur": 40.149, + "args": { + "External id": 3716670,"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": 1625851367306.040, "dur": 102.918, + "args": { + "External id": 3716671,"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": 1625851367419.991, "dur": 38.750, + "args": { + "External id": 3716672,"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": 1625851367467.674, "dur": 31.408, + "args": { + "External id": 3716673,"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": 1625851367524.823, "dur": 25.922, + "args": { + "External id": 3716674,"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": 1625851367569.063, "dur": 17.371, + "args": { + "External id": 3716675,"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": 1625851367604.425, "dur": 155.248, + "args": { + "External id": 3716676,"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": 1625851367653.206, "dur": 12.739, + "args": { + "External id": 3716677,"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": 1625851367658.735, "dur": 6.432, + "args": { + "External id": 3716678,"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": 1625851367668.725, "dur": 6.635, + "args": { + "External id": 3716679,"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": 1625851367694.420, "dur": 2.454, + "args": { + "External id": 3716680,"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": 1625851367699.804, "dur": 5.564, + "args": { + "External id": 3716681,"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": 1625851367770.673, "dur": 48.326, + "args": { + "External id": 3716682,"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": 1625851367850.939, "dur": 29.664, + "args": { + "External id": 3716683,"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": 1625851367890.269, "dur": 40.790, + "args": { + "External id": 3716684,"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": 1625851367939.618, "dur": 33.835, + "args": { + "External id": 3716685,"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": 1625851368033.800, "dur": 31.158, + "args": { + "External id": 3716686,"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": 1625851368071.500, "dur": 38.436, + "args": { + "External id": 3716687,"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": 1625851368130.819, "dur": 18.088, + "args": { + "External id": 3716688,"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": 1625851368299.529, "dur": 80.636, + "args": { + "External id": 3716689,"Record function id": 0, "Ev Idx": 7400 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 1336756, "tid": 1336756, + "ts": 1625851368452.875, "dur": 46.974, + "args": { + "External id": 3716690,"Record function id": 0, "Ev Idx": 7401 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.18)", "pid": 1336756, "tid": 1336756, + "ts": 1625851368508.924, "dur": 18131.223, + "args": { + "External id": 3716691,"Record function id": 0, "Ev Idx": 7402 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.18)", "pid": 1336756, "tid": 1336756, + "ts": 1625851368516.479, "dur": 905.339, + "args": { + "External id": 3716692,"Record function id": 0, "Ev Idx": 7403 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1625851368597.296, "dur": 7.305, + "args": { + "External id": 3716693,"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": 1625851368617.810, "dur": 40.122, + "args": { + "External id": 3716694,"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": 1625851368622.820, "dur": 2.154, + "args": { + "External id": 3716695,"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": 1625851368630.063, "dur": 0.431, + "args": { + "External id": 3716696,"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": 1625851368632.236, "dur": 0.525, + "args": { + "External id": 3716697,"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": 1625851368634.674, "dur": 0.281, + "args": { + "External id": 3716698,"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": 1625851368638.292, "dur": 0.397, + "args": { + "External id": 3716699,"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": 1625851368640.520, "dur": 0.585, + "args": { + "External id": 3716700,"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": 1625851368642.975, "dur": 4.085, + "args": { + "External id": 3716701,"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": 1625851368648.659, "dur": 0.499, + "args": { + "External id": 3716702,"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": 1625851368651.000, "dur": 0.498, + "args": { + "External id": 3716703,"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": 1625851368669.375, "dur": 55.456, + "args": { + "External id": 3716704,"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": 1625851368760.631, "dur": 123.397, + "args": { + "External id": 3716705,"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": 1625851368772.289, "dur": 5.708, + "args": { + "External id": 3716706,"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": 1625851368783.215, "dur": 11.058, + "args": { + "External id": 3716707,"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": 1625851368787.371, "dur": 6.503, + "args": { + "External id": 3716708,"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": 1625851368791.710, "dur": 0.733, + "args": { + "External id": 3716709,"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": 1625851368801.888, "dur": 39.717, + "args": { + "External id": 3716710,"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": 1625851368804.541, "dur": 2.913, + "args": { + "External id": 3716711,"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": 1625851368809.573, "dur": 0.503, + "args": { + "External id": 3716712,"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": 1625851368812.007, "dur": 0.513, + "args": { + "External id": 3716713,"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": 1625851368820.071, "dur": 2.442, + "args": { + "External id": 3716714,"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": 1625851368824.073, "dur": 0.766, + "args": { + "External id": 3716715,"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": 1625851368826.106, "dur": 0.593, + "args": { + "External id": 3716716,"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": 1625851368830.267, "dur": 0.256, + "args": { + "External id": 3716717,"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": 1625851368831.996, "dur": 0.336, + "args": { + "External id": 3716718,"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": 1625851368833.772, "dur": 2.331, + "args": { + "External id": 3716719,"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": 1625851368852.861, "dur": 23.997, + "args": { + "External id": 3716720,"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": 1625851368936.460, "dur": 387.945, + "args": { + "External id": 3716721,"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": 1625851368971.492, "dur": 347.943, + "args": { + "External id": 3716722,"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": 1625851369016.114, "dur": 297.887, + "args": { + "External id": 3716723,"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": 1625851369352.810, "dur": 2.256, + "args": { + "External id": 3716724,"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": 1625851369442.440, "dur": 17002.317, + "args": { + "External id": 3716725,"Record function id": 0, "Ev Idx": 7436 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1625851369544.265, "dur": 6.187, + "args": { + "External id": 3716726,"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": 1625851369553.528, "dur": 1.748, + "args": { + "External id": 3716727,"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": 1625851369556.902, "dur": 3.419, + "args": { + "External id": 3716728,"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": 1625851369562.037, "dur": 1.187, + "args": { + "External id": 3716729,"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": 1625851369564.466, "dur": 0.917, + "args": { + "External id": 3716730,"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": 1625851369566.675, "dur": 1.165, + "args": { + "External id": 3716731,"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": 1625851369571.455, "dur": 0.828, + "args": { + "External id": 3716732,"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": 1625851369573.799, "dur": 2.001, + "args": { + "External id": 3716733,"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": 1625851369577.459, "dur": 0.801, + "args": { + "External id": 3716734,"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": 1625851369579.764, "dur": 1.345, + "args": { + "External id": 3716735,"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": 1625851369602.447, "dur": 16806.118, + "args": { + "External id": 3716736,"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": 1625851369618.103, "dur": 16783.866, + "args": { + "External id": 3716737,"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": 1625851369641.051, "dur": 13.136, + "args": { + "External id": 3716738,"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": 1625851369657.228, "dur": 16711.514, + "args": { + "External id": 3716739,"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": 1625851369659.642, "dur": 16708.541, + "args": { + "External id": 3716740,"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": 1625851369665.588, "dur": 5.789, + "args": { + "External id": 3716741,"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": 1625851369672.980, "dur": 16692.362, + "args": { + "External id": 3716742,"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": 1625851386579.200, "dur": 36.268, + "args": { + "External id": 3716743,"Sequence number": 37295109, "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": 1625851386579.200, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 1336756, "tid": 1336756, + "ts": 1625851386603.162, "dur": 7.439, + "args": { + "External id": 3716744,"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": 1625851386606.588, "dur": 3.771, + "args": { + "External id": 3716745,"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": 1625851386693.119, "dur": 77.395, + "args": { + "External id": 3716746,"Record function id": 0, "Ev Idx": 7457 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 1336756, "tid": 1336756, + "ts": 1625851386772.719, "dur": 1085.095, + "args": { + "External id": 3716747,"Record function id": 0, "Ev Idx": 7458 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 1336756, "tid": 1336756, + "ts": 1625851386816.249, "dur": 1028.821, + "args": { + "External id": 3716748,"Sequence number": 37295110, "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": 1625851386816.249, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 1336756, "tid": 1336756, + "ts": 1625851386890.016, "dur": 44.057, + "args": { + "External id": 3716749,"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": 1625851386948.695, "dur": 129.166, + "args": { + "External id": 3716750,"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": 1625851387092.137, "dur": 39.650, + "args": { + "External id": 3716751,"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": 1625851387138.300, "dur": 30.678, + "args": { + "External id": 3716752,"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": 1625851387199.360, "dur": 27.766, + "args": { + "External id": 3716753,"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": 1625851387244.098, "dur": 18.530, + "args": { + "External id": 3716754,"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": 1625851387280.291, "dur": 134.936, + "args": { + "External id": 3716755,"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": 1625851387330.486, "dur": 12.017, + "args": { + "External id": 3716756,"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": 1625851387335.977, "dur": 5.824, + "args": { + "External id": 3716757,"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": 1625851387345.539, "dur": 7.576, + "args": { + "External id": 3716758,"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": 1625851387354.771, "dur": 3.690, + "args": { + "External id": 3716759,"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": 1625851387360.914, "dur": 4.528, + "args": { + "External id": 3716760,"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": 1625851387425.942, "dur": 44.685, + "args": { + "External id": 3716761,"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": 1625851387501.263, "dur": 26.979, + "args": { + "External id": 3716762,"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": 1625851387538.303, "dur": 40.708, + "args": { + "External id": 3716763,"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": 1625851387585.255, "dur": 35.111, + "args": { + "External id": 3716764,"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": 1625851387646.132, "dur": 25.178, + "args": { + "External id": 3716765,"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": 1625851387692.611, "dur": 39.593, + "args": { + "External id": 3716766,"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": 1625851387753.620, "dur": 22.775, + "args": { + "External id": 3716767,"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": 1625851387920.835, "dur": 124.591, + "args": { + "External id": 3716768,"Record function id": 0, "Ev Idx": 7479 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 1336756, "tid": 1336756, + "ts": 1625851388123.366, "dur": 47.805, + "args": { + "External id": 3716769,"Record function id": 0, "Ev Idx": 7480 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.19)", "pid": 1336756, "tid": 1336756, + "ts": 1625851388180.743, "dur": 18210.900, + "args": { + "External id": 3716770,"Record function id": 0, "Ev Idx": 7481 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.19)", "pid": 1336756, "tid": 1336756, + "ts": 1625851388189.542, "dur": 908.921, + "args": { + "External id": 3716771,"Record function id": 0, "Ev Idx": 7482 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1625851388269.593, "dur": 9.827, + "args": { + "External id": 3716772,"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": 1625851388292.952, "dur": 42.014, + "args": { + "External id": 3716773,"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": 1625851388298.273, "dur": 2.344, + "args": { + "External id": 3716774,"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": 1625851388305.346, "dur": 0.412, + "args": { + "External id": 3716775,"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": 1625851388308.353, "dur": 0.364, + "args": { + "External id": 3716776,"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": 1625851388310.420, "dur": 0.451, + "args": { + "External id": 3716777,"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": 1625851388314.591, "dur": 0.593, + "args": { + "External id": 3716778,"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": 1625851388317.092, "dur": 0.345, + "args": { + "External id": 3716779,"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": 1625851388319.132, "dur": 4.346, + "args": { + "External id": 3716780,"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": 1625851388325.162, "dur": 0.243, + "args": { + "External id": 3716781,"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": 1625851388327.036, "dur": 0.269, + "args": { + "External id": 3716782,"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": 1625851388347.754, "dur": 41.428, + "args": { + "External id": 3716783,"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": 1625851388421.329, "dur": 121.258, + "args": { + "External id": 3716784,"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": 1625851388431.733, "dur": 4.343, + "args": { + "External id": 3716785,"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": 1625851388440.964, "dur": 10.367, + "args": { + "External id": 3716786,"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": 1625851388445.030, "dur": 5.895, + "args": { + "External id": 3716787,"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": 1625851388449.434, "dur": 0.345, + "args": { + "External id": 3716788,"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": 1625851388459.237, "dur": 36.640, + "args": { + "External id": 3716789,"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": 1625851388461.767, "dur": 2.399, + "args": { + "External id": 3716790,"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": 1625851388465.892, "dur": 0.460, + "args": { + "External id": 3716791,"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": 1625851388467.796, "dur": 0.515, + "args": { + "External id": 3716792,"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": 1625851388472.623, "dur": 2.354, + "args": { + "External id": 3716793,"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": 1625851388476.742, "dur": 0.628, + "args": { + "External id": 3716794,"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": 1625851388479.065, "dur": 0.278, + "args": { + "External id": 3716795,"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": 1625851388482.717, "dur": 0.281, + "args": { + "External id": 3716796,"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": 1625851388484.718, "dur": 0.455, + "args": { + "External id": 3716797,"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": 1625851388486.827, "dur": 2.522, + "args": { + "External id": 3716798,"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": 1625851388509.943, "dur": 25.434, + "args": { + "External id": 3716799,"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": 1625851388592.460, "dur": 371.435, + "args": { + "External id": 3716800,"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": 1625851388626.417, "dur": 332.524, + "args": { + "External id": 3716801,"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": 1625851388636.466, "dur": 316.642, + "args": { + "External id": 3716802,"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": 1625851389023.565, "dur": 3.676, + "args": { + "External id": 3716803,"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": 1625851389120.055, "dur": 17075.267, + "args": { + "External id": 3716804,"Record function id": 0, "Ev Idx": 7515 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1625851389227.465, "dur": 6.057, + "args": { + "External id": 3716805,"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": 1625851389236.689, "dur": 1.404, + "args": { + "External id": 3716806,"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": 1625851389239.737, "dur": 2.672, + "args": { + "External id": 3716807,"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": 1625851389244.004, "dur": 1.061, + "args": { + "External id": 3716808,"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": 1625851389246.302, "dur": 0.932, + "args": { + "External id": 3716809,"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": 1625851389248.312, "dur": 1.207, + "args": { + "External id": 3716810,"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": 1625851389254.082, "dur": 0.858, + "args": { + "External id": 3716811,"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": 1625851389256.582, "dur": 1.797, + "args": { + "External id": 3716812,"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": 1625851389259.915, "dur": 1.043, + "args": { + "External id": 3716813,"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": 1625851389262.504, "dur": 0.831, + "args": { + "External id": 3716814,"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": 1625851389284.782, "dur": 16873.173, + "args": { + "External id": 3716815,"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": 1625851389300.753, "dur": 16850.558, + "args": { + "External id": 3716816,"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": 1625851389329.123, "dur": 14.027, + "args": { + "External id": 3716817,"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": 1625851389346.075, "dur": 16771.394, + "args": { + "External id": 3716818,"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": 1625851389352.802, "dur": 16764.176, + "args": { + "External id": 3716819,"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": 1625851389361.335, "dur": 5.586, + "args": { + "External id": 3716820,"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": 1625851389368.351, "dur": 16745.800, + "args": { + "External id": 3716821,"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": 1625851406331.167, "dur": 36.784, + "args": { + "External id": 3716822,"Sequence number": 37295111, "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": 1625851406331.167, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 1336756, "tid": 1336756, + "ts": 1625851406355.935, "dur": 6.989, + "args": { + "External id": 3716823,"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": 1625851406358.899, "dur": 3.819, + "args": { + "External id": 3716824,"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": 1625851406430.974, "dur": 72.403, + "args": { + "External id": 3716825,"Record function id": 0, "Ev Idx": 7536 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 1336756, "tid": 1336756, + "ts": 1625851406505.263, "dur": 1093.180, + "args": { + "External id": 3716826,"Record function id": 0, "Ev Idx": 7537 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 1336756, "tid": 1336756, + "ts": 1625851406546.416, "dur": 1039.620, + "args": { + "External id": 3716827,"Sequence number": 37295112, "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": 1625851406546.416, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 1336756, "tid": 1336756, + "ts": 1625851406613.802, "dur": 39.495, + "args": { + "External id": 3716828,"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": 1625851406666.267, "dur": 118.476, + "args": { + "External id": 3716829,"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": 1625851406798.266, "dur": 38.562, + "args": { + "External id": 3716830,"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": 1625851406845.737, "dur": 30.782, + "args": { + "External id": 3716831,"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": 1625851406903.394, "dur": 29.184, + "args": { + "External id": 3716832,"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": 1625851406950.714, "dur": 16.398, + "args": { + "External id": 3716833,"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": 1625851407019.325, "dur": 139.561, + "args": { + "External id": 3716834,"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": 1625851407070.346, "dur": 12.702, + "args": { + "External id": 3716835,"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": 1625851407075.582, "dur": 6.475, + "args": { + "External id": 3716836,"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": 1625851407085.937, "dur": 7.254, + "args": { + "External id": 3716837,"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": 1625851407094.660, "dur": 1.604, + "args": { + "External id": 3716838,"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": 1625851407098.683, "dur": 5.137, + "args": { + "External id": 3716839,"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": 1625851407170.063, "dur": 50.227, + "args": { + "External id": 3716840,"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": 1625851407253.037, "dur": 30.274, + "args": { + "External id": 3716841,"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": 1625851407293.214, "dur": 41.762, + "args": { + "External id": 3716842,"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": 1625851407343.684, "dur": 35.354, + "args": { + "External id": 3716843,"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": 1625851407402.906, "dur": 31.895, + "args": { + "External id": 3716844,"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": 1625851407439.989, "dur": 34.110, + "args": { + "External id": 3716845,"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": 1625851407494.113, "dur": 18.477, + "args": { + "External id": 3716846,"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": 1625851407661.768, "dur": 90.629, + "args": { + "External id": 3716847,"Record function id": 0, "Ev Idx": 7558 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 1336756, "tid": 1336756, + "ts": 1625851407827.190, "dur": 47.045, + "args": { + "External id": 3716848,"Record function id": 0, "Ev Idx": 7559 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.20)", "pid": 1336756, "tid": 1336756, + "ts": 1625851407883.734, "dur": 18237.349, + "args": { + "External id": 3716849,"Record function id": 0, "Ev Idx": 7560 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.20)", "pid": 1336756, "tid": 1336756, + "ts": 1625851407892.079, "dur": 912.136, + "args": { + "External id": 3716850,"Record function id": 0, "Ev Idx": 7561 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1625851407970.313, "dur": 8.882, + "args": { + "External id": 3716851,"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": 1625851408029.447, "dur": 40.830, + "args": { + "External id": 3716852,"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": 1625851408034.658, "dur": 2.242, + "args": { + "External id": 3716853,"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": 1625851408042.096, "dur": 0.502, + "args": { + "External id": 3716854,"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": 1625851408044.210, "dur": 0.518, + "args": { + "External id": 3716855,"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": 1625851408046.751, "dur": 0.406, + "args": { + "External id": 3716856,"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": 1625851408051.074, "dur": 0.519, + "args": { + "External id": 3716857,"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": 1625851408053.146, "dur": 0.373, + "args": { + "External id": 3716858,"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": 1625851408055.099, "dur": 4.294, + "args": { + "External id": 3716859,"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": 1625851408061.118, "dur": 0.337, + "args": { + "External id": 3716860,"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": 1625851408063.611, "dur": 0.241, + "args": { + "External id": 3716861,"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": 1625851408082.358, "dur": 41.871, + "args": { + "External id": 3716862,"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": 1625851408157.582, "dur": 122.478, + "args": { + "External id": 3716863,"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": 1625851408168.780, "dur": 5.590, + "args": { + "External id": 3716864,"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": 1625851408179.826, "dur": 10.607, + "args": { + "External id": 3716865,"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": 1625851408184.223, "dur": 5.798, + "args": { + "External id": 3716866,"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": 1625851408188.160, "dur": 0.780, + "args": { + "External id": 3716867,"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": 1625851408197.590, "dur": 33.120, + "args": { + "External id": 3716868,"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": 1625851408200.464, "dur": 2.465, + "args": { + "External id": 3716869,"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": 1625851408204.756, "dur": 0.436, + "args": { + "External id": 3716870,"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": 1625851408206.932, "dur": 0.285, + "args": { + "External id": 3716871,"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": 1625851408210.505, "dur": 2.412, + "args": { + "External id": 3716872,"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": 1625851408214.640, "dur": 0.291, + "args": { + "External id": 3716873,"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": 1625851408216.178, "dur": 0.327, + "args": { + "External id": 3716874,"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": 1625851408219.696, "dur": 0.371, + "args": { + "External id": 3716875,"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": 1625851408221.466, "dur": 0.402, + "args": { + "External id": 3716876,"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": 1625851408223.390, "dur": 2.147, + "args": { + "External id": 3716877,"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": 1625851408246.759, "dur": 25.404, + "args": { + "External id": 3716878,"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": 1625851408333.380, "dur": 371.419, + "args": { + "External id": 3716879,"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": 1625851408368.763, "dur": 330.060, + "args": { + "External id": 3716880,"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": 1625851408380.840, "dur": 291.598, + "args": { + "External id": 3716881,"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": 1625851408731.993, "dur": 3.030, + "args": { + "External id": 3716882,"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": 1625851408825.294, "dur": 17064.330, + "args": { + "External id": 3716883,"Record function id": 0, "Ev Idx": 7594 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1625851408926.351, "dur": 5.924, + "args": { + "External id": 3716884,"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": 1625851408935.441, "dur": 1.251, + "args": { + "External id": 3716885,"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": 1625851408938.427, "dur": 3.338, + "args": { + "External id": 3716886,"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": 1625851408943.572, "dur": 1.137, + "args": { + "External id": 3716887,"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": 1625851408946.085, "dur": 1.080, + "args": { + "External id": 3716888,"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": 1625851408948.721, "dur": 0.821, + "args": { + "External id": 3716889,"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": 1625851408953.247, "dur": 0.776, + "args": { + "External id": 3716890,"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": 1625851408955.477, "dur": 2.165, + "args": { + "External id": 3716891,"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": 1625851408959.040, "dur": 0.994, + "args": { + "External id": 3716892,"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": 1625851408961.659, "dur": 0.717, + "args": { + "External id": 3716893,"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": 1625851409016.355, "dur": 16836.708, + "args": { + "External id": 3716894,"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": 1625851409033.954, "dur": 16812.734, + "args": { + "External id": 3716895,"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": 1625851409055.800, "dur": 14.335, + "args": { + "External id": 3716896,"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": 1625851409073.105, "dur": 16738.888, + "args": { + "External id": 3716897,"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": 1625851409075.327, "dur": 16736.209, + "args": { + "External id": 3716898,"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": 1625851409081.358, "dur": 6.369, + "args": { + "External id": 3716899,"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": 1625851409089.198, "dur": 16719.422, + "args": { + "External id": 3716900,"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": 1625851426050.876, "dur": 43.811, + "args": { + "External id": 3716901,"Sequence number": 37295113, "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": 1625851426050.876, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 1336756, "tid": 1336756, + "ts": 1625851426076.926, "dur": 12.822, + "args": { + "External id": 3716902,"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": 1625851426085.240, "dur": 4.146, + "args": { + "External id": 3716903,"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": 1625851426160.691, "dur": 75.191, + "args": { + "External id": 3716904,"Record function id": 0, "Ev Idx": 7615 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 1336756, "tid": 1336756, + "ts": 1625851426237.756, "dur": 1126.959, + "args": { + "External id": 3716905,"Record function id": 0, "Ev Idx": 7616 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 1336756, "tid": 1336756, + "ts": 1625851426279.842, "dur": 1071.941, + "args": { + "External id": 3716906,"Sequence number": 37295114, "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": 1625851426279.842, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 1336756, "tid": 1336756, + "ts": 1625851426347.692, "dur": 43.925, + "args": { + "External id": 3716907,"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": 1625851426403.419, "dur": 103.958, + "args": { + "External id": 3716908,"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": 1625851426520.973, "dur": 39.283, + "args": { + "External id": 3716909,"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": 1625851426567.434, "dur": 31.629, + "args": { + "External id": 3716910,"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": 1625851426627.340, "dur": 26.761, + "args": { + "External id": 3716911,"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": 1625851426669.877, "dur": 33.162, + "args": { + "External id": 3716912,"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": 1625851426724.543, "dur": 137.646, + "args": { + "External id": 3716913,"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": 1625851426777.287, "dur": 12.044, + "args": { + "External id": 3716914,"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": 1625851426781.979, "dur": 6.652, + "args": { + "External id": 3716915,"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": 1625851426792.005, "dur": 6.551, + "args": { + "External id": 3716916,"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": 1625851426800.059, "dur": 1.235, + "args": { + "External id": 3716917,"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": 1625851426806.192, "dur": 5.062, + "args": { + "External id": 3716918,"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": 1625851426873.266, "dur": 49.320, + "args": { + "External id": 3716919,"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": 1625851426954.442, "dur": 78.574, + "args": { + "External id": 3716920,"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": 1625851427049.880, "dur": 49.321, + "args": { + "External id": 3716921,"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": 1625851427106.516, "dur": 35.727, + "args": { + "External id": 3716922,"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": 1625851427168.422, "dur": 29.570, + "args": { + "External id": 3716923,"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": 1625851427203.890, "dur": 35.515, + "args": { + "External id": 3716924,"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": 1625851427258.533, "dur": 21.406, + "args": { + "External id": 3716925,"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": 1625851427428.783, "dur": 75.299, + "args": { + "External id": 3716926,"Record function id": 0, "Ev Idx": 7637 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 1336756, "tid": 1336756, + "ts": 1625851427577.698, "dur": 49.714, + "args": { + "External id": 3716927,"Record function id": 0, "Ev Idx": 7638 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.21)", "pid": 1336756, "tid": 1336756, + "ts": 1625851427636.603, "dur": 18143.332, + "args": { + "External id": 3716928,"Record function id": 0, "Ev Idx": 7639 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.21)", "pid": 1336756, "tid": 1336756, + "ts": 1625851427646.271, "dur": 919.768, + "args": { + "External id": 3716929,"Record function id": 0, "Ev Idx": 7640 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1625851427747.950, "dur": 8.931, + "args": { + "External id": 3716930,"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": 1625851427770.958, "dur": 40.652, + "args": { + "External id": 3716931,"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": 1625851427776.456, "dur": 2.470, + "args": { + "External id": 3716932,"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": 1625851427783.856, "dur": 0.804, + "args": { + "External id": 3716933,"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": 1625851427786.657, "dur": 0.506, + "args": { + "External id": 3716934,"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": 1625851427788.874, "dur": 0.400, + "args": { + "External id": 3716935,"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": 1625851427792.527, "dur": 0.664, + "args": { + "External id": 3716936,"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": 1625851427794.532, "dur": 0.626, + "args": { + "External id": 3716937,"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": 1625851427796.715, "dur": 4.205, + "args": { + "External id": 3716938,"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": 1625851427802.646, "dur": 0.273, + "args": { + "External id": 3716939,"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": 1625851427804.766, "dur": 0.340, + "args": { + "External id": 3716940,"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": 1625851427825.058, "dur": 40.050, + "args": { + "External id": 3716941,"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": 1625851427898.109, "dur": 159.820, + "args": { + "External id": 3716942,"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": 1625851427909.425, "dur": 4.190, + "args": { + "External id": 3716943,"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": 1625851427918.496, "dur": 10.112, + "args": { + "External id": 3716944,"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": 1625851427923.024, "dur": 5.165, + "args": { + "External id": 3716945,"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": 1625851427926.542, "dur": 0.457, + "args": { + "External id": 3716946,"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": 1625851427936.054, "dur": 36.103, + "args": { + "External id": 3716947,"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": 1625851427938.419, "dur": 2.320, + "args": { + "External id": 3716948,"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": 1625851427942.528, "dur": 0.303, + "args": { + "External id": 3716949,"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": 1625851427944.801, "dur": 0.449, + "args": { + "External id": 3716950,"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": 1625851427949.794, "dur": 2.152, + "args": { + "External id": 3716951,"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": 1625851427953.744, "dur": 0.339, + "args": { + "External id": 3716952,"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": 1625851427955.763, "dur": 0.538, + "args": { + "External id": 3716953,"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": 1625851427960.084, "dur": 0.150, + "args": { + "External id": 3716954,"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": 1625851427962.206, "dur": 0.353, + "args": { + "External id": 3716955,"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": 1625851427964.186, "dur": 2.915, + "args": { + "External id": 3716956,"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": 1625851428021.863, "dur": 26.524, + "args": { + "External id": 3716957,"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": 1625851428115.089, "dur": 362.607, + "args": { + "External id": 3716958,"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": 1625851428150.604, "dur": 322.721, + "args": { + "External id": 3716959,"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": 1625851428169.804, "dur": 297.952, + "args": { + "External id": 3716960,"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": 1625851428500.163, "dur": 2.271, + "args": { + "External id": 3716961,"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": 1625851428586.321, "dur": 16981.724, + "args": { + "External id": 3716962,"Record function id": 0, "Ev Idx": 7673 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1625851428704.360, "dur": 6.338, + "args": { + "External id": 3716963,"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": 1625851428714.168, "dur": 1.573, + "args": { + "External id": 3716964,"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": 1625851428730.704, "dur": 5.875, + "args": { + "External id": 3716965,"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": 1625851428745.025, "dur": 0.898, + "args": { + "External id": 3716966,"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": 1625851428747.270, "dur": 1.335, + "args": { + "External id": 3716967,"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": 1625851428749.816, "dur": 0.965, + "args": { + "External id": 3716968,"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": 1625851428754.569, "dur": 1.149, + "args": { + "External id": 3716969,"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": 1625851428757.338, "dur": 2.621, + "args": { + "External id": 3716970,"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": 1625851428761.524, "dur": 1.247, + "args": { + "External id": 3716971,"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": 1625851428764.457, "dur": 1.191, + "args": { + "External id": 3716972,"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": 1625851428789.452, "dur": 16741.511, + "args": { + "External id": 3716973,"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": 1625851428805.945, "dur": 16719.180, + "args": { + "External id": 3716974,"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": 1625851428829.332, "dur": 16.267, + "args": { + "External id": 3716975,"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": 1625851428848.514, "dur": 16643.085, + "args": { + "External id": 3716976,"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": 1625851428851.031, "dur": 16640.046, + "args": { + "External id": 3716977,"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": 1625851428857.795, "dur": 6.153, + "args": { + "External id": 3716978,"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": 1625851428866.028, "dur": 16622.776, + "args": { + "External id": 3716979,"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": 1625851445718.720, "dur": 35.693, + "args": { + "External id": 3716980,"Sequence number": 37295115, "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": 1625851445718.720, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 1336756, "tid": 1336756, + "ts": 1625851445742.225, "dur": 7.283, + "args": { + "External id": 3716981,"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": 1625851445745.459, "dur": 3.756, + "args": { + "External id": 3716982,"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": 1625851445818.840, "dur": 75.377, + "args": { + "External id": 3716983,"Record function id": 0, "Ev Idx": 7694 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 1336756, "tid": 1336756, + "ts": 1625851445896.208, "dur": 1125.256, + "args": { + "External id": 3716984,"Record function id": 0, "Ev Idx": 7695 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 1336756, "tid": 1336756, + "ts": 1625851445939.334, "dur": 1034.948, + "args": { + "External id": 3716985,"Sequence number": 37295116, "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": 1625851445939.334, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 1336756, "tid": 1336756, + "ts": 1625851446039.390, "dur": 44.130, + "args": { + "External id": 3716986,"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": 1625851446097.842, "dur": 104.975, + "args": { + "External id": 3716987,"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": 1625851446213.448, "dur": 37.389, + "args": { + "External id": 3716988,"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": 1625851446259.060, "dur": 32.030, + "args": { + "External id": 3716989,"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": 1625851446318.115, "dur": 27.025, + "args": { + "External id": 3716990,"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": 1625851446363.734, "dur": 16.682, + "args": { + "External id": 3716991,"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": 1625851446398.923, "dur": 130.609, + "args": { + "External id": 3716992,"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": 1625851446448.454, "dur": 11.276, + "args": { + "External id": 3716993,"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": 1625851446453.448, "dur": 5.348, + "args": { + "External id": 3716994,"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": 1625851446462.603, "dur": 5.788, + "args": { + "External id": 3716995,"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": 1625851446469.934, "dur": 1.604, + "args": { + "External id": 3716996,"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": 1625851446473.921, "dur": 4.732, + "args": { + "External id": 3716997,"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": 1625851446540.424, "dur": 42.631, + "args": { + "External id": 3716998,"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": 1625851446613.783, "dur": 32.091, + "args": { + "External id": 3716999,"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": 1625851446655.491, "dur": 60.487, + "args": { + "External id": 3717000,"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": 1625851446728.459, "dur": 37.556, + "args": { + "External id": 3717001,"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": 1625851446791.809, "dur": 30.007, + "args": { + "External id": 3717002,"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": 1625851446827.279, "dur": 34.955, + "args": { + "External id": 3717003,"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": 1625851446882.528, "dur": 19.264, + "args": { + "External id": 3717004,"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": 1625851447089.369, "dur": 76.758, + "args": { + "External id": 3717005,"Record function id": 0, "Ev Idx": 7716 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 1336756, "tid": 1336756, + "ts": 1625851447240.368, "dur": 48.133, + "args": { + "External id": 3717006,"Record function id": 0, "Ev Idx": 7717 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.22)", "pid": 1336756, "tid": 1336756, + "ts": 1625851447297.857, "dur": 18228.084, + "args": { + "External id": 3717007,"Record function id": 0, "Ev Idx": 7718 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.22)", "pid": 1336756, "tid": 1336756, + "ts": 1625851447306.065, "dur": 970.272, + "args": { + "External id": 3717008,"Record function id": 0, "Ev Idx": 7719 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1625851447388.864, "dur": 8.712, + "args": { + "External id": 3717009,"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": 1625851447411.702, "dur": 42.254, + "args": { + "External id": 3717010,"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": 1625851447417.373, "dur": 2.242, + "args": { + "External id": 3717011,"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": 1625851447425.399, "dur": 0.694, + "args": { + "External id": 3717012,"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": 1625851447428.182, "dur": 0.363, + "args": { + "External id": 3717013,"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": 1625851447430.238, "dur": 0.584, + "args": { + "External id": 3717014,"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": 1625851447434.399, "dur": 0.386, + "args": { + "External id": 3717015,"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": 1625851447436.487, "dur": 0.291, + "args": { + "External id": 3717016,"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": 1625851447438.624, "dur": 4.569, + "args": { + "External id": 3717017,"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": 1625851447445.028, "dur": 0.372, + "args": { + "External id": 3717018,"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": 1625851447447.274, "dur": 0.480, + "args": { + "External id": 3717019,"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": 1625851447466.960, "dur": 40.230, + "args": { + "External id": 3717020,"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": 1625851447539.521, "dur": 116.900, + "args": { + "External id": 3717021,"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": 1625851447550.011, "dur": 3.884, + "args": { + "External id": 3717022,"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": 1625851447558.953, "dur": 10.216, + "args": { + "External id": 3717023,"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": 1625851447563.222, "dur": 5.542, + "args": { + "External id": 3717024,"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": 1625851447566.978, "dur": 0.611, + "args": { + "External id": 3717025,"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": 1625851447577.081, "dur": 34.695, + "args": { + "External id": 3717026,"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": 1625851447579.294, "dur": 3.034, + "args": { + "External id": 3717027,"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": 1625851447584.095, "dur": 0.444, + "args": { + "External id": 3717028,"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": 1625851447586.279, "dur": 0.414, + "args": { + "External id": 3717029,"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": 1625851447590.688, "dur": 2.129, + "args": { + "External id": 3717030,"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": 1625851447594.641, "dur": 0.381, + "args": { + "External id": 3717031,"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": 1625851447596.337, "dur": 0.660, + "args": { + "External id": 3717032,"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": 1625851447600.268, "dur": 0.335, + "args": { + "External id": 3717033,"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": 1625851447602.161, "dur": 0.427, + "args": { + "External id": 3717034,"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": 1625851447603.869, "dur": 2.367, + "args": { + "External id": 3717035,"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": 1625851447623.767, "dur": 24.740, + "args": { + "External id": 3717036,"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": 1625851447729.791, "dur": 444.353, + "args": { + "External id": 3717037,"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": 1625851447772.160, "dur": 395.792, + "args": { + "External id": 3717038,"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": 1625851447782.562, "dur": 379.454, + "args": { + "External id": 3717039,"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": 1625851448201.747, "dur": 2.546, + "args": { + "External id": 3717040,"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": 1625851448296.597, "dur": 17026.856, + "args": { + "External id": 3717041,"Record function id": 0, "Ev Idx": 7752 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1625851448405.854, "dur": 6.324, + "args": { + "External id": 3717042,"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": 1625851448415.367, "dur": 1.438, + "args": { + "External id": 3717043,"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": 1625851448418.445, "dur": 3.236, + "args": { + "External id": 3717044,"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": 1625851448423.268, "dur": 1.039, + "args": { + "External id": 3717045,"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": 1625851448425.601, "dur": 2.358, + "args": { + "External id": 3717046,"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": 1625851448431.366, "dur": 0.932, + "args": { + "External id": 3717047,"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": 1625851448433.911, "dur": 0.939, + "args": { + "External id": 3717048,"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": 1625851448436.495, "dur": 2.632, + "args": { + "External id": 3717049,"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": 1625851448440.544, "dur": 0.750, + "args": { + "External id": 3717050,"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": 1625851448444.861, "dur": 1.134, + "args": { + "External id": 3717051,"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": 1625851448465.364, "dur": 16820.654, + "args": { + "External id": 3717052,"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": 1625851448487.132, "dur": 16792.030, + "args": { + "External id": 3717053,"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": 1625851448505.426, "dur": 14.057, + "args": { + "External id": 3717054,"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": 1625851448522.403, "dur": 16724.551, + "args": { + "External id": 3717055,"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": 1625851448524.833, "dur": 16721.563, + "args": { + "External id": 3717056,"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": 1625851448531.397, "dur": 5.899, + "args": { + "External id": 3717057,"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": 1625851448538.877, "dur": 16704.273, + "args": { + "External id": 3717058,"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": 1625851465461.764, "dur": 37.841, + "args": { + "External id": 3717059,"Sequence number": 37295117, "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": 1625851465461.764, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 1336756, "tid": 1336756, + "ts": 1625851465486.524, "dur": 8.022, + "args": { + "External id": 3717060,"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": 1625851465490.313, "dur": 4.027, + "args": { + "External id": 3717061,"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": 1625851465565.456, "dur": 72.364, + "args": { + "External id": 3717062,"Record function id": 0, "Ev Idx": 7773 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 1336756, "tid": 1336756, + "ts": 1625851465639.373, "dur": 1102.450, + "args": { + "External id": 3717063,"Record function id": 0, "Ev Idx": 7774 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 1336756, "tid": 1336756, + "ts": 1625851465690.050, "dur": 1037.916, + "args": { + "External id": 3717064,"Sequence number": 37295118, "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": 1625851465690.050, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 1336756, "tid": 1336756, + "ts": 1625851465759.117, "dur": 43.259, + "args": { + "External id": 3717065,"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": 1625851465815.287, "dur": 105.344, + "args": { + "External id": 3717066,"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": 1625851465931.187, "dur": 38.716, + "args": { + "External id": 3717067,"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": 1625851465978.962, "dur": 66.540, + "args": { + "External id": 3717068,"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": 1625851466076.628, "dur": 28.478, + "args": { + "External id": 3717069,"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": 1625851466123.968, "dur": 16.689, + "args": { + "External id": 3717070,"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": 1625851466160.401, "dur": 131.548, + "args": { + "External id": 3717071,"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": 1625851466210.114, "dur": 11.734, + "args": { + "External id": 3717072,"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": 1625851466215.563, "dur": 5.568, + "args": { + "External id": 3717073,"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": 1625851466224.710, "dur": 5.723, + "args": { + "External id": 3717074,"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": 1625851466231.893, "dur": 1.609, + "args": { + "External id": 3717075,"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": 1625851466236.038, "dur": 5.168, + "args": { + "External id": 3717076,"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": 1625851466302.476, "dur": 46.797, + "args": { + "External id": 3717077,"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": 1625851466380.798, "dur": 28.737, + "args": { + "External id": 3717078,"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": 1625851466420.239, "dur": 40.456, + "args": { + "External id": 3717079,"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": 1625851466470.274, "dur": 35.975, + "args": { + "External id": 3717080,"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": 1625851466530.373, "dur": 29.131, + "args": { + "External id": 3717081,"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": 1625851466565.314, "dur": 34.337, + "args": { + "External id": 3717082,"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": 1625851466620.053, "dur": 19.020, + "args": { + "External id": 3717083,"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": 1625851466805.797, "dur": 77.262, + "args": { + "External id": 3717084,"Record function id": 0, "Ev Idx": 7795 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 1336756, "tid": 1336756, + "ts": 1625851466954.450, "dur": 83.233, + "args": { + "External id": 3717085,"Record function id": 0, "Ev Idx": 7796 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.23)", "pid": 1336756, "tid": 1336756, + "ts": 1625851467049.419, "dur": 18234.762, + "args": { + "External id": 3717086,"Record function id": 0, "Ev Idx": 7797 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.23)", "pid": 1336756, "tid": 1336756, + "ts": 1625851467058.883, "dur": 862.388, + "args": { + "External id": 3717087,"Record function id": 0, "Ev Idx": 7798 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1625851467137.209, "dur": 9.634, + "args": { + "External id": 3717088,"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": 1625851467160.575, "dur": 43.210, + "args": { + "External id": 3717089,"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": 1625851467166.161, "dur": 2.563, + "args": { + "External id": 3717090,"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": 1625851467173.692, "dur": 0.786, + "args": { + "External id": 3717091,"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": 1625851467175.958, "dur": 0.541, + "args": { + "External id": 3717092,"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": 1625851467178.358, "dur": 0.453, + "args": { + "External id": 3717093,"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": 1625851467182.657, "dur": 0.802, + "args": { + "External id": 3717094,"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": 1625851467185.345, "dur": 0.679, + "args": { + "External id": 3717095,"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": 1625851467187.838, "dur": 4.099, + "args": { + "External id": 3717096,"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": 1625851467193.614, "dur": 0.262, + "args": { + "External id": 3717097,"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": 1625851467195.498, "dur": 0.709, + "args": { + "External id": 3717098,"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": 1625851467216.904, "dur": 42.372, + "args": { + "External id": 3717099,"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": 1625851467291.126, "dur": 118.759, + "args": { + "External id": 3717100,"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": 1625851467301.520, "dur": 4.112, + "args": { + "External id": 3717101,"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": 1625851467310.479, "dur": 10.183, + "args": { + "External id": 3717102,"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": 1625851467314.778, "dur": 5.480, + "args": { + "External id": 3717103,"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": 1625851467318.403, "dur": 0.510, + "args": { + "External id": 3717104,"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": 1625851467328.094, "dur": 34.736, + "args": { + "External id": 3717105,"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": 1625851467330.941, "dur": 2.615, + "args": { + "External id": 3717106,"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": 1625851467335.584, "dur": 0.324, + "args": { + "External id": 3717107,"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": 1625851467337.453, "dur": 0.169, + "args": { + "External id": 3717108,"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": 1625851467341.495, "dur": 2.161, + "args": { + "External id": 3717109,"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": 1625851467345.183, "dur": 0.489, + "args": { + "External id": 3717110,"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": 1625851467347.528, "dur": 0.342, + "args": { + "External id": 3717111,"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": 1625851467351.544, "dur": 0.486, + "args": { + "External id": 3717112,"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": 1625851467353.503, "dur": 0.267, + "args": { + "External id": 3717113,"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": 1625851467355.268, "dur": 2.419, + "args": { + "External id": 3717114,"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": 1625851467378.122, "dur": 24.215, + "args": { + "External id": 3717115,"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": 1625851467462.250, "dur": 366.014, + "args": { + "External id": 3717116,"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": 1625851467495.664, "dur": 327.557, + "args": { + "External id": 3717117,"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": 1625851467505.131, "dur": 312.064, + "args": { + "External id": 3717118,"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": 1625851467852.271, "dur": 2.565, + "args": { + "External id": 3717119,"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": 1625851467941.688, "dur": 17141.132, + "args": { + "External id": 3717120,"Record function id": 0, "Ev Idx": 7831 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1625851468126.754, "dur": 6.767, + "args": { + "External id": 3717121,"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": 1625851468137.436, "dur": 1.320, + "args": { + "External id": 3717122,"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": 1625851468140.626, "dur": 2.994, + "args": { + "External id": 3717123,"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": 1625851468147.341, "dur": 1.232, + "args": { + "External id": 3717124,"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": 1625851468149.994, "dur": 0.791, + "args": { + "External id": 3717125,"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": 1625851468152.202, "dur": 0.819, + "args": { + "External id": 3717126,"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": 1625851468154.706, "dur": 1.039, + "args": { + "External id": 3717127,"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": 1625851468159.265, "dur": 2.262, + "args": { + "External id": 3717128,"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": 1625851468163.015, "dur": 0.478, + "args": { + "External id": 3717129,"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": 1625851468164.775, "dur": 0.687, + "args": { + "External id": 3717130,"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": 1625851468186.703, "dur": 16857.101, + "args": { + "External id": 3717131,"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": 1625851468202.563, "dur": 16834.659, + "args": { + "External id": 3717132,"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": 1625851468216.062, "dur": 14.229, + "args": { + "External id": 3717133,"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": 1625851468235.511, "dur": 16767.695, + "args": { + "External id": 3717134,"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": 1625851468237.779, "dur": 16764.793, + "args": { + "External id": 3717135,"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": 1625851468243.594, "dur": 5.411, + "args": { + "External id": 3717136,"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": 1625851468250.608, "dur": 16728.982, + "args": { + "External id": 3717137,"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": 1625851485223.310, "dur": 37.203, + "args": { + "External id": 3717138,"Sequence number": 37295119, "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": 1625851485223.310, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 1336756, "tid": 1336756, + "ts": 1625851485248.249, "dur": 7.105, + "args": { + "External id": 3717139,"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": 1625851485251.175, "dur": 3.986, + "args": { + "External id": 3717140,"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": 1625851485323.814, "dur": 75.046, + "args": { + "External id": 3717141,"Record function id": 0, "Ev Idx": 7852 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 1336756, "tid": 1336756, + "ts": 1625851485400.331, "dur": 1106.165, + "args": { + "External id": 3717142,"Record function id": 0, "Ev Idx": 7853 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 1336756, "tid": 1336756, + "ts": 1625851485442.284, "dur": 1052.078, + "args": { + "External id": 3717143,"Sequence number": 37295120, "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": 1625851485442.284, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 1336756, "tid": 1336756, + "ts": 1625851485511.356, "dur": 38.795, + "args": { + "External id": 3717144,"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": 1625851485562.614, "dur": 105.967, + "args": { + "External id": 3717145,"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": 1625851485698.698, "dur": 44.200, + "args": { + "External id": 3717146,"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": 1625851485753.543, "dur": 31.353, + "args": { + "External id": 3717147,"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": 1625851485809.828, "dur": 28.503, + "args": { + "External id": 3717148,"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": 1625851485858.525, "dur": 17.672, + "args": { + "External id": 3717149,"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": 1625851485896.190, "dur": 172.315, + "args": { + "External id": 3717150,"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": 1625851485948.677, "dur": 11.470, + "args": { + "External id": 3717151,"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": 1625851485953.550, "dur": 5.754, + "args": { + "External id": 3717152,"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": 1625851485962.615, "dur": 5.638, + "args": { + "External id": 3717153,"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": 1625851485969.569, "dur": 1.124, + "args": { + "External id": 3717154,"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": 1625851485972.781, "dur": 4.811, + "args": { + "External id": 3717155,"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": 1625851486081.696, "dur": 52.458, + "args": { + "External id": 3717156,"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": 1625851486167.079, "dur": 27.511, + "args": { + "External id": 3717157,"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": 1625851486204.635, "dur": 42.222, + "args": { + "External id": 3717158,"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": 1625851486255.366, "dur": 34.255, + "args": { + "External id": 3717159,"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": 1625851486311.649, "dur": 29.623, + "args": { + "External id": 3717160,"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": 1625851486346.510, "dur": 33.417, + "args": { + "External id": 3717161,"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": 1625851486402.713, "dur": 19.201, + "args": { + "External id": 3717162,"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": 1625851486569.165, "dur": 76.128, + "args": { + "External id": 3717163,"Record function id": 0, "Ev Idx": 7874 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 1336756, "tid": 1336756, + "ts": 1625851486738.947, "dur": 49.788, + "args": { + "External id": 3717164,"Record function id": 0, "Ev Idx": 7875 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.24)", "pid": 1336756, "tid": 1336756, + "ts": 1625851486798.593, "dur": 18293.096, + "args": { + "External id": 3717165,"Record function id": 0, "Ev Idx": 7876 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.24)", "pid": 1336756, "tid": 1336756, + "ts": 1625851486806.921, "dur": 896.467, + "args": { + "External id": 3717166,"Record function id": 0, "Ev Idx": 7877 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1625851486888.083, "dur": 9.369, + "args": { + "External id": 3717167,"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": 1625851486910.375, "dur": 35.140, + "args": { + "External id": 3717168,"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": 1625851486915.623, "dur": 2.157, + "args": { + "External id": 3717169,"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": 1625851486922.057, "dur": 0.551, + "args": { + "External id": 3717170,"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": 1625851486924.143, "dur": 0.661, + "args": { + "External id": 3717171,"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": 1625851486925.712, "dur": 0.450, + "args": { + "External id": 3717172,"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": 1625851486928.913, "dur": 0.428, + "args": { + "External id": 3717173,"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": 1625851486930.292, "dur": 0.386, + "args": { + "External id": 3717174,"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": 1625851486932.054, "dur": 4.018, + "args": { + "External id": 3717175,"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": 1625851486937.185, "dur": 0.388, + "args": { + "External id": 3717176,"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": 1625851486938.598, "dur": 0.469, + "args": { + "External id": 3717177,"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": 1625851486959.643, "dur": 79.117, + "args": { + "External id": 3717178,"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": 1625851487074.174, "dur": 121.361, + "args": { + "External id": 3717179,"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": 1625851487085.909, "dur": 5.662, + "args": { + "External id": 3717180,"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": 1625851487097.035, "dur": 11.021, + "args": { + "External id": 3717181,"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": 1625851487101.387, "dur": 6.279, + "args": { + "External id": 3717182,"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": 1625851487104.967, "dur": 1.159, + "args": { + "External id": 3717183,"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": 1625851487115.035, "dur": 33.972, + "args": { + "External id": 3717184,"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": 1625851487117.282, "dur": 3.076, + "args": { + "External id": 3717185,"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": 1625851487121.478, "dur": 0.560, + "args": { + "External id": 3717186,"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": 1625851487123.071, "dur": 0.316, + "args": { + "External id": 3717187,"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": 1625851487126.909, "dur": 2.599, + "args": { + "External id": 3717188,"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": 1625851487130.529, "dur": 0.988, + "args": { + "External id": 3717189,"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": 1625851487132.748, "dur": 0.395, + "args": { + "External id": 3717190,"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": 1625851487137.028, "dur": 1.060, + "args": { + "External id": 3717191,"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": 1625851487139.235, "dur": 0.713, + "args": { + "External id": 3717192,"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": 1625851487141.145, "dur": 2.584, + "args": { + "External id": 3717193,"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": 1625851487161.813, "dur": 25.835, + "args": { + "External id": 3717194,"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": 1625851487251.457, "dur": 347.078, + "args": { + "External id": 3717195,"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": 1625851487284.495, "dur": 309.096, + "args": { + "External id": 3717196,"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": 1625851487294.413, "dur": 293.833, + "args": { + "External id": 3717197,"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": 1625851487621.999, "dur": 2.176, + "args": { + "External id": 3717198,"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": 1625851487725.528, "dur": 17141.667, + "args": { + "External id": 3717199,"Record function id": 0, "Ev Idx": 7910 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1625851487831.196, "dur": 6.583, + "args": { + "External id": 3717200,"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": 1625851487841.019, "dur": 1.763, + "args": { + "External id": 3717201,"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": 1625851487844.538, "dur": 2.901, + "args": { + "External id": 3717202,"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": 1625851487849.398, "dur": 1.255, + "args": { + "External id": 3717203,"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": 1625851487861.518, "dur": 1.413, + "args": { + "External id": 3717204,"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": 1625851487865.988, "dur": 1.060, + "args": { + "External id": 3717205,"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": 1625851487870.990, "dur": 1.547, + "args": { + "External id": 3717206,"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": 1625851487873.977, "dur": 2.216, + "args": { + "External id": 3717207,"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": 1625851487877.542, "dur": 0.948, + "args": { + "External id": 3717208,"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": 1625851487880.079, "dur": 1.211, + "args": { + "External id": 3717209,"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": 1625851487903.046, "dur": 16925.746, + "args": { + "External id": 3717210,"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": 1625851487917.716, "dur": 16904.191, + "args": { + "External id": 3717211,"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": 1625851487934.867, "dur": 14.428, + "args": { + "External id": 3717212,"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": 1625851487952.534, "dur": 16835.501, + "args": { + "External id": 3717213,"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": 1625851487954.960, "dur": 16832.620, + "args": { + "External id": 3717214,"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": 1625851487960.813, "dur": 6.006, + "args": { + "External id": 3717215,"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": 1625851487968.537, "dur": 16816.194, + "args": { + "External id": 3717216,"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": 1625851505030.024, "dur": 37.241, + "args": { + "External id": 3717217,"Sequence number": 37295121, "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": 1625851505030.024, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 1336756, "tid": 1336756, + "ts": 1625851505054.294, "dur": 7.674, + "args": { + "External id": 3717218,"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": 1625851505057.407, "dur": 4.154, + "args": { + "External id": 3717219,"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": 1625851505130.709, "dur": 76.666, + "args": { + "External id": 3717220,"Record function id": 0, "Ev Idx": 7931 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 1336756, "tid": 1336756, + "ts": 1625851505208.992, "dur": 1094.995, + "args": { + "External id": 3717221,"Record function id": 0, "Ev Idx": 7932 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 1336756, "tid": 1336756, + "ts": 1625851505249.704, "dur": 1041.960, + "args": { + "External id": 3717222,"Sequence number": 37295122, "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": 1625851505249.704, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 1336756, "tid": 1336756, + "ts": 1625851505316.342, "dur": 40.429, + "args": { + "External id": 3717223,"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": 1625851505369.244, "dur": 102.495, + "args": { + "External id": 3717224,"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": 1625851505482.272, "dur": 38.749, + "args": { + "External id": 3717225,"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": 1625851505530.321, "dur": 32.286, + "args": { + "External id": 3717226,"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": 1625851505587.383, "dur": 26.695, + "args": { + "External id": 3717227,"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": 1625851505638.617, "dur": 17.333, + "args": { + "External id": 3717228,"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": 1625851505673.382, "dur": 149.654, + "args": { + "External id": 3717229,"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": 1625851505741.417, "dur": 12.698, + "args": { + "External id": 3717230,"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": 1625851505746.682, "dur": 6.456, + "args": { + "External id": 3717231,"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": 1625851505756.618, "dur": 5.845, + "args": { + "External id": 3717232,"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": 1625851505763.639, "dur": 1.359, + "args": { + "External id": 3717233,"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": 1625851505767.604, "dur": 4.152, + "args": { + "External id": 3717234,"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": 1625851505833.408, "dur": 48.879, + "args": { + "External id": 3717235,"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": 1625851505914.078, "dur": 29.809, + "args": { + "External id": 3717236,"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": 1625851505952.795, "dur": 77.900, + "args": { + "External id": 3717237,"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": 1625851506043.957, "dur": 40.080, + "args": { + "External id": 3717238,"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": 1625851506108.801, "dur": 30.138, + "args": { + "External id": 3717239,"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": 1625851506144.193, "dur": 35.091, + "args": { + "External id": 3717240,"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": 1625851506200.030, "dur": 18.705, + "args": { + "External id": 3717241,"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": 1625851506367.209, "dur": 79.876, + "args": { + "External id": 3717242,"Record function id": 0, "Ev Idx": 7953 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 1336756, "tid": 1336756, + "ts": 1625851506520.082, "dur": 46.212, + "args": { + "External id": 3717243,"Record function id": 0, "Ev Idx": 7954 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.25)", "pid": 1336756, "tid": 1336756, + "ts": 1625851506575.347, "dur": 18439.472, + "args": { + "External id": 3717244,"Record function id": 0, "Ev Idx": 7955 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.25)", "pid": 1336756, "tid": 1336756, + "ts": 1625851506584.198, "dur": 900.639, + "args": { + "External id": 3717245,"Record function id": 0, "Ev Idx": 7956 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1625851506666.168, "dur": 7.645, + "args": { + "External id": 3717246,"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": 1625851506704.170, "dur": 41.096, + "args": { + "External id": 3717247,"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": 1625851506709.318, "dur": 2.568, + "args": { + "External id": 3717248,"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": 1625851506716.214, "dur": 0.235, + "args": { + "External id": 3717249,"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": 1625851506717.352, "dur": 0.267, + "args": { + "External id": 3717250,"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": 1625851506723.591, "dur": 0.223, + "args": { + "External id": 3717251,"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": 1625851506728.737, "dur": 0.172, + "args": { + "External id": 3717252,"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": 1625851506729.762, "dur": 0.584, + "args": { + "External id": 3717253,"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": 1625851506731.482, "dur": 3.507, + "args": { + "External id": 3717254,"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": 1625851506736.225, "dur": 0.193, + "args": { + "External id": 3717255,"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": 1625851506738.103, "dur": 0.616, + "args": { + "External id": 3717256,"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": 1625851506758.637, "dur": 42.495, + "args": { + "External id": 3717257,"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": 1625851506833.716, "dur": 114.328, + "args": { + "External id": 3717258,"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": 1625851506845.574, "dur": 4.694, + "args": { + "External id": 3717259,"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": 1625851506855.362, "dur": 10.515, + "args": { + "External id": 3717260,"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": 1625851506859.817, "dur": 5.632, + "args": { + "External id": 3717261,"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": 1625851506863.393, "dur": 0.674, + "args": { + "External id": 3717262,"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": 1625851506872.713, "dur": 30.074, + "args": { + "External id": 3717263,"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": 1625851506874.568, "dur": 2.658, + "args": { + "External id": 3717264,"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": 1625851506878.588, "dur": 0.512, + "args": { + "External id": 3717265,"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": 1625851506880.496, "dur": 0.487, + "args": { + "External id": 3717266,"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": 1625851506883.946, "dur": 2.190, + "args": { + "External id": 3717267,"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": 1625851506887.639, "dur": 0.384, + "args": { + "External id": 3717268,"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": 1625851506888.884, "dur": 0.359, + "args": { + "External id": 3717269,"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": 1625851506892.594, "dur": 0.322, + "args": { + "External id": 3717270,"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": 1625851506893.924, "dur": 0.143, + "args": { + "External id": 3717271,"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": 1625851506895.612, "dur": 2.373, + "args": { + "External id": 3717272,"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": 1625851506916.122, "dur": 24.329, + "args": { + "External id": 3717273,"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": 1625851507040.115, "dur": 354.233, + "args": { + "External id": 3717274,"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": 1625851507074.545, "dur": 314.850, + "args": { + "External id": 3717275,"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": 1625851507084.762, "dur": 299.272, + "args": { + "External id": 3717276,"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": 1625851507416.657, "dur": 2.212, + "args": { + "External id": 3717277,"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": 1625851507504.669, "dur": 17278.827, + "args": { + "External id": 3717278,"Record function id": 0, "Ev Idx": 7989 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1625851507604.318, "dur": 6.076, + "args": { + "External id": 3717279,"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": 1625851507613.673, "dur": 1.515, + "args": { + "External id": 3717280,"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": 1625851507616.923, "dur": 2.543, + "args": { + "External id": 3717281,"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": 1625851507621.184, "dur": 1.213, + "args": { + "External id": 3717282,"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": 1625851507623.883, "dur": 0.792, + "args": { + "External id": 3717283,"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": 1625851507626.104, "dur": 0.963, + "args": { + "External id": 3717284,"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": 1625851507630.857, "dur": 1.111, + "args": { + "External id": 3717285,"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": 1625851507633.451, "dur": 2.060, + "args": { + "External id": 3717286,"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": 1625851507636.883, "dur": 1.326, + "args": { + "External id": 3717287,"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": 1625851507640.053, "dur": 1.055, + "args": { + "External id": 3717288,"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": 1625851507661.368, "dur": 17083.079, + "args": { + "External id": 3717289,"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": 1625851507695.161, "dur": 17042.683, + "args": { + "External id": 3717290,"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": 1625851507718.952, "dur": 14.431, + "args": { + "External id": 3717291,"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": 1625851507736.277, "dur": 16967.719, + "args": { + "External id": 3717292,"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": 1625851507738.828, "dur": 16964.684, + "args": { + "External id": 3717293,"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": 1625851507744.939, "dur": 5.761, + "args": { + "External id": 3717294,"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": 1625851507752.317, "dur": 16948.474, + "args": { + "External id": 3717295,"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": 1625851524924.183, "dur": 38.436, + "args": { + "External id": 3717296,"Sequence number": 37295123, "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": 1625851524924.183, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 1336756, "tid": 1336756, + "ts": 1625851524950.069, "dur": 7.428, + "args": { + "External id": 3717297,"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": 1625851524953.296, "dur": 3.986, + "args": { + "External id": 3717298,"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": 1625851525055.549, "dur": 78.071, + "args": { + "External id": 3717299,"Record function id": 0, "Ev Idx": 8010 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 1336756, "tid": 1336756, + "ts": 1625851525135.258, "dur": 1108.087, + "args": { + "External id": 3717300,"Record function id": 0, "Ev Idx": 8011 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 1336756, "tid": 1336756, + "ts": 1625851525176.201, "dur": 1053.439, + "args": { + "External id": 3717301,"Sequence number": 37295124, "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": 1625851525176.201, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 1336756, "tid": 1336756, + "ts": 1625851525248.027, "dur": 42.559, + "args": { + "External id": 3717302,"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": 1625851525303.281, "dur": 103.293, + "args": { + "External id": 3717303,"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": 1625851525416.389, "dur": 38.958, + "args": { + "External id": 3717304,"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": 1625851525464.205, "dur": 31.233, + "args": { + "External id": 3717305,"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": 1625851525520.661, "dur": 27.434, + "args": { + "External id": 3717306,"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": 1625851525567.935, "dur": 16.986, + "args": { + "External id": 3717307,"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": 1625851525603.786, "dur": 150.512, + "args": { + "External id": 3717308,"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": 1625851525653.791, "dur": 11.300, + "args": { + "External id": 3717309,"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": 1625851525658.613, "dur": 5.769, + "args": { + "External id": 3717310,"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": 1625851525667.508, "dur": 4.675, + "args": { + "External id": 3717311,"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": 1625851525673.388, "dur": 1.590, + "args": { + "External id": 3717312,"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": 1625851525693.897, "dur": 5.316, + "args": { + "External id": 3717313,"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": 1625851525765.362, "dur": 59.431, + "args": { + "External id": 3717314,"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": 1625851525853.775, "dur": 31.702, + "args": { + "External id": 3717315,"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": 1625851525893.822, "dur": 40.924, + "args": { + "External id": 3717316,"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": 1625851525942.978, "dur": 34.791, + "args": { + "External id": 3717317,"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": 1625851526039.267, "dur": 32.056, + "args": { + "External id": 3717318,"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": 1625851526077.946, "dur": 38.577, + "args": { + "External id": 3717319,"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": 1625851526137.273, "dur": 18.332, + "args": { + "External id": 3717320,"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": 1625851526306.372, "dur": 73.496, + "args": { + "External id": 3717321,"Record function id": 0, "Ev Idx": 8032 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 1336756, "tid": 1336756, + "ts": 1625851526449.549, "dur": 47.217, + "args": { + "External id": 3717322,"Record function id": 0, "Ev Idx": 8033 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.26)", "pid": 1336756, "tid": 1336756, + "ts": 1625851526505.491, "dur": 18758.188, + "args": { + "External id": 3717323,"Record function id": 0, "Ev Idx": 8034 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.26)", "pid": 1336756, "tid": 1336756, + "ts": 1625851526515.290, "dur": 907.427, + "args": { + "External id": 3717324,"Record function id": 0, "Ev Idx": 8035 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1625851526592.926, "dur": 7.776, + "args": { + "External id": 3717325,"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": 1625851526613.414, "dur": 34.339, + "args": { + "External id": 3717326,"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": 1625851526618.620, "dur": 2.257, + "args": { + "External id": 3717327,"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": 1625851526625.198, "dur": 0.460, + "args": { + "External id": 3717328,"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": 1625851526626.652, "dur": 0.436, + "args": { + "External id": 3717329,"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": 1625851526628.051, "dur": 0.443, + "args": { + "External id": 3717330,"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": 1625851526631.794, "dur": 0.226, + "args": { + "External id": 3717331,"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": 1625851526633.038, "dur": 0.290, + "args": { + "External id": 3717332,"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": 1625851526634.254, "dur": 3.753, + "args": { + "External id": 3717333,"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": 1625851526639.127, "dur": 0.587, + "args": { + "External id": 3717334,"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": 1625851526640.943, "dur": 0.307, + "args": { + "External id": 3717335,"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": 1625851526659.118, "dur": 55.005, + "args": { + "External id": 3717336,"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": 1625851526749.247, "dur": 115.471, + "args": { + "External id": 3717337,"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": 1625851526760.947, "dur": 5.537, + "args": { + "External id": 3717338,"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": 1625851526771.728, "dur": 10.848, + "args": { + "External id": 3717339,"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": 1625851526776.035, "dur": 6.125, + "args": { + "External id": 3717340,"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": 1625851526780.034, "dur": 0.608, + "args": { + "External id": 3717341,"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": 1625851526790.506, "dur": 33.181, + "args": { + "External id": 3717342,"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": 1625851526792.837, "dur": 2.967, + "args": { + "External id": 3717343,"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": 1625851526796.908, "dur": 0.518, + "args": { + "External id": 3717344,"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": 1625851526798.262, "dur": 0.743, + "args": { + "External id": 3717345,"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": 1625851526802.532, "dur": 1.420, + "args": { + "External id": 3717346,"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": 1625851526805.387, "dur": 0.153, + "args": { + "External id": 3717347,"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": 1625851526811.007, "dur": 0.200, + "args": { + "External id": 3717348,"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": 1625851526813.592, "dur": 0.166, + "args": { + "External id": 3717349,"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": 1625851526814.928, "dur": 0.378, + "args": { + "External id": 3717350,"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": 1625851526816.540, "dur": 2.696, + "args": { + "External id": 3717351,"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": 1625851526833.991, "dur": 23.422, + "args": { + "External id": 3717352,"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": 1625851526917.395, "dur": 407.597, + "args": { + "External id": 3717353,"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": 1625851526950.909, "dur": 368.770, + "args": { + "External id": 3717354,"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": 1625851526960.731, "dur": 352.715, + "args": { + "External id": 3717355,"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": 1625851527350.974, "dur": 2.758, + "args": { + "External id": 3717356,"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": 1625851527443.286, "dur": 17621.011, + "args": { + "External id": 3717357,"Record function id": 0, "Ev Idx": 8068 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1625851527544.203, "dur": 6.292, + "args": { + "External id": 3717358,"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": 1625851527553.740, "dur": 1.080, + "args": { + "External id": 3717359,"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": 1625851527556.412, "dur": 1.362, + "args": { + "External id": 3717360,"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": 1625851527559.537, "dur": 1.383, + "args": { + "External id": 3717361,"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": 1625851527562.413, "dur": 1.093, + "args": { + "External id": 3717362,"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": 1625851527564.802, "dur": 1.086, + "args": { + "External id": 3717363,"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": 1625851527569.680, "dur": 1.176, + "args": { + "External id": 3717364,"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": 1625851527572.411, "dur": 2.422, + "args": { + "External id": 3717365,"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": 1625851527576.300, "dur": 1.140, + "args": { + "External id": 3717366,"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": 1625851527578.828, "dur": 0.945, + "args": { + "External id": 3717367,"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": 1625851527600.433, "dur": 17425.776, + "args": { + "External id": 3717368,"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": 1625851527622.327, "dur": 17396.997, + "args": { + "External id": 3717369,"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": 1625851527639.062, "dur": 13.406, + "args": { + "External id": 3717370,"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": 1625851527655.256, "dur": 17298.545, + "args": { + "External id": 3717371,"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": 1625851527657.524, "dur": 17295.654, + "args": { + "External id": 3717372,"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": 1625851527663.402, "dur": 5.983, + "args": { + "External id": 3717373,"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": 1625851527671.031, "dur": 17279.249, + "args": { + "External id": 3717374,"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": 1625851545204.147, "dur": 35.725, + "args": { + "External id": 3717375,"Sequence number": 37295125, "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": 1625851545204.147, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 1336756, "tid": 1336756, + "ts": 1625851545227.421, "dur": 7.678, + "args": { + "External id": 3717376,"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": 1625851545230.574, "dur": 4.260, + "args": { + "External id": 3717377,"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": 1625851545303.588, "dur": 77.406, + "args": { + "External id": 3717378,"Record function id": 0, "Ev Idx": 8089 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 1336756, "tid": 1336756, + "ts": 1625851545382.548, "dur": 1105.495, + "args": { + "External id": 3717379,"Record function id": 0, "Ev Idx": 8090 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 1336756, "tid": 1336756, + "ts": 1625851545422.742, "dur": 1052.265, + "args": { + "External id": 3717380,"Sequence number": 37295126, "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": 1625851545422.742, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 1336756, "tid": 1336756, + "ts": 1625851545487.746, "dur": 40.983, + "args": { + "External id": 3717381,"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": 1625851545541.445, "dur": 106.593, + "args": { + "External id": 3717382,"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": 1625851545657.411, "dur": 58.426, + "args": { + "External id": 3717383,"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": 1625851545728.377, "dur": 35.185, + "args": { + "External id": 3717384,"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": 1625851545791.617, "dur": 31.005, + "args": { + "External id": 3717385,"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": 1625851545842.545, "dur": 16.383, + "args": { + "External id": 3717386,"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": 1625851545876.422, "dur": 163.190, + "args": { + "External id": 3717387,"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": 1625851545925.911, "dur": 10.571, + "args": { + "External id": 3717388,"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": 1625851545930.430, "dur": 5.394, + "args": { + "External id": 3717389,"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": 1625851545939.208, "dur": 4.688, + "args": { + "External id": 3717390,"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": 1625851545945.361, "dur": 1.827, + "args": { + "External id": 3717391,"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": 1625851545949.569, "dur": 3.881, + "args": { + "External id": 3717392,"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": 1625851546052.919, "dur": 56.502, + "args": { + "External id": 3717393,"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": 1625851546144.031, "dur": 32.006, + "args": { + "External id": 3717394,"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": 1625851546184.636, "dur": 41.346, + "args": { + "External id": 3717395,"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": 1625851546235.149, "dur": 35.127, + "args": { + "External id": 3717396,"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": 1625851546294.400, "dur": 28.651, + "args": { + "External id": 3717397,"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": 1625851546329.084, "dur": 34.337, + "args": { + "External id": 3717398,"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": 1625851546382.853, "dur": 22.191, + "args": { + "External id": 3717399,"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": 1625851546550.759, "dur": 75.379, + "args": { + "External id": 3717400,"Record function id": 0, "Ev Idx": 8111 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::cast_forward_inputs", "pid": 1336756, "tid": 1336756, + "ts": 1625851546716.559, "dur": 50.511, + "args": { + "External id": 3717401,"Record function id": 0, "Ev Idx": 8112 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::pre_forward (model.layers.27)", "pid": 1336756, "tid": 1336756, + "ts": 1625851546776.205, "dur": 18440.105, + "args": { + "External id": 3717402,"Record function id": 0, "Ev Idx": 8113 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::all_gather (model.layers.27)", "pid": 1336756, "tid": 1336756, + "ts": 1625851546784.766, "dur": 931.174, + "args": { + "External id": 3717403,"Record function id": 0, "Ev Idx": 8114 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1625851546870.636, "dur": 9.794, + "args": { + "External id": 3717404,"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": 1625851546893.488, "dur": 35.334, + "args": { + "External id": 3717405,"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": 1625851546898.829, "dur": 2.520, + "args": { + "External id": 3717406,"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": 1625851546905.469, "dur": 0.875, + "args": { + "External id": 3717407,"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": 1625851546907.421, "dur": 0.535, + "args": { + "External id": 3717408,"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": 1625851546908.816, "dur": 0.564, + "args": { + "External id": 3717409,"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": 1625851546912.618, "dur": 0.652, + "args": { + "External id": 3717410,"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": 1625851546914.205, "dur": 0.649, + "args": { + "External id": 3717411,"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": 1625851546915.928, "dur": 2.395, + "args": { + "External id": 3717412,"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": 1625851546919.210, "dur": 0.597, + "args": { + "External id": 3717413,"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": 1625851546921.436, "dur": 0.437, + "args": { + "External id": 3717414,"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": 1625851546940.484, "dur": 38.765, + "args": { + "External id": 3717415,"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": 1625851547051.332, "dur": 119.195, + "args": { + "External id": 3717416,"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": 1625851547063.366, "dur": 5.800, + "args": { + "External id": 3717417,"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": 1625851547074.363, "dur": 10.968, + "args": { + "External id": 3717418,"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": 1625851547078.684, "dur": 6.267, + "args": { + "External id": 3717419,"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": 1625851547082.202, "dur": 1.169, + "args": { + "External id": 3717420,"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": 1625851547092.509, "dur": 29.373, + "args": { + "External id": 3717421,"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": 1625851547094.813, "dur": 2.963, + "args": { + "External id": 3717422,"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": 1625851547099.002, "dur": 0.629, + "args": { + "External id": 3717423,"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": 1625851547100.584, "dur": 0.682, + "args": { + "External id": 3717424,"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": 1625851547104.406, "dur": 0.997, + "args": { + "External id": 3717425,"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": 1625851547106.365, "dur": 0.637, + "args": { + "External id": 3717426,"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": 1625851547107.797, "dur": 0.411, + "args": { + "External id": 3717427,"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": 1625851547110.769, "dur": 0.543, + "args": { + "External id": 3717428,"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": 1625851547112.430, "dur": 0.846, + "args": { + "External id": 3717429,"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": 1625851547114.629, "dur": 2.730, + "args": { + "External id": 3717430,"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": 1625851547135.359, "dur": 27.153, + "args": { + "External id": 3717431,"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": 1625851547225.441, "dur": 385.213, + "args": { + "External id": 3717432,"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": 1625851547259.845, "dur": 345.762, + "args": { + "External id": 3717433,"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": 1625851547270.049, "dur": 330.563, + "args": { + "External id": 3717434,"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": 1625851547632.476, "dur": 2.390, + "args": { + "External id": 3717435,"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": 1625851547737.375, "dur": 17275.682, + "args": { + "External id": 3717436,"Record function id": 0, "Ev Idx": 8147 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1625851547846.120, "dur": 6.506, + "args": { + "External id": 3717437,"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": 1625851547855.963, "dur": 1.329, + "args": { + "External id": 3717438,"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": 1625851547858.966, "dur": 1.184, + "args": { + "External id": 3717439,"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": 1625851547875.357, "dur": 1.312, + "args": { + "External id": 3717440,"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": 1625851547878.247, "dur": 1.094, + "args": { + "External id": 3717441,"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": 1625851547880.640, "dur": 1.325, + "args": { + "External id": 3717442,"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": 1625851547885.679, "dur": 1.301, + "args": { + "External id": 3717443,"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": 1625851547888.238, "dur": 2.131, + "args": { + "External id": 3717444,"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": 1625851547891.572, "dur": 0.842, + "args": { + "External id": 3717445,"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": 1625851547893.671, "dur": 0.847, + "args": { + "External id": 3717446,"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": 1625851547916.465, "dur": 17036.227, + "args": { + "External id": 3717447,"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": 1625851547931.879, "dur": 17014.242, + "args": { + "External id": 3717448,"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": 1625851547948.160, "dur": 13.293, + "args": { + "External id": 3717449,"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": 1625851547964.239, "dur": 16948.120, + "args": { + "External id": 3717450,"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": 1625851547966.774, "dur": 16944.843, + "args": { + "External id": 3717451,"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": 1625851547972.691, "dur": 5.569, + "args": { + "External id": 3717452,"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": 1625851547980.036, "dur": 16928.613, + "args": { + "External id": 3717453,"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": 1625851565154.831, "dur": 37.950, + "args": { + "External id": 3717454,"Sequence number": 37295127, "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": 1625851565154.831, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view_as", "pid": 1336756, "tid": 1336756, + "ts": 1625851565179.891, "dur": 8.065, + "args": { + "External id": 3717455,"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": 1625851565183.203, "dur": 4.488, + "args": { + "External id": 3717456,"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": 1625851565255.557, "dur": 75.191, + "args": { + "External id": 3717457,"Record function id": 0, "Ev Idx": 8168 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 1/1", "pid": 1336756, "tid": 1336756, + "ts": 1625851565332.145, "dur": 1090.911, + "args": { + "External id": 3717458,"Record function id": 0, "Ev Idx": 8169 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 1336756, "tid": 1336756, + "ts": 1625851565373.437, "dur": 1037.044, + "args": { + "External id": 3717459,"Sequence number": 37295128, "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": 1625851565373.437, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 1336756, "tid": 1336756, + "ts": 1625851565437.916, "dur": 40.271, + "args": { + "External id": 3717460,"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": 1625851565491.380, "dur": 104.262, + "args": { + "External id": 3717461,"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": 1625851565604.968, "dur": 37.480, + "args": { + "External id": 3717462,"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": 1625851565652.305, "dur": 49.784, + "args": { + "External id": 3717463,"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": 1625851565732.763, "dur": 29.199, + "args": { + "External id": 3717464,"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": 1625851565781.196, "dur": 16.513, + "args": { + "External id": 3717465,"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": 1625851565814.719, "dur": 129.463, + "args": { + "External id": 3717466,"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": 1625851565864.560, "dur": 11.832, + "args": { + "External id": 3717467,"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": 1625851565869.302, "dur": 6.240, + "args": { + "External id": 3717468,"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": 1625851565879.210, "dur": 5.288, + "args": { + "External id": 3717469,"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": 1625851565885.773, "dur": 1.747, + "args": { + "External id": 3717470,"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": 1625851565890.074, "dur": 3.978, + "args": { + "External id": 3717471,"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": 1625851565956.062, "dur": 86.665, + "args": { + "External id": 3717472,"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": 1625851566080.313, "dur": 31.484, + "args": { + "External id": 3717473,"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": 1625851566120.479, "dur": 45.526, + "args": { + "External id": 3717474,"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": 1625851566175.533, "dur": 34.824, + "args": { + "External id": 3717475,"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": 1625851566234.412, "dur": 29.712, + "args": { + "External id": 3717476,"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": 1625851566270.024, "dur": 34.220, + "args": { + "External id": 3717477,"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": 1625851566324.637, "dur": 17.989, + "args": { + "External id": 3717478,"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": 1625851566484.784, "dur": 34.387, + "args": { + "External id": 3717479,"Record function id": 0, "Ev Idx": 8190 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunction", "pid": 1336756, "tid": 1336756, + "ts": 1625851566663.327, "dur": 315.560, + "args": { + "External id": 3717480,"Sequence number": 37295129, "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": 1625851566663.327, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1336756, + "ts": 1625851566712.952, "dur": 8.112, + "args": { + "External id": 3717481,"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": 1625851566714.637, "dur": 6.042, + "args": { + "External id": 3717482,"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": 1625851566731.601, "dur": 12.495, + "args": { + "External id": 3717483,"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": 1625851566735.377, "dur": 8.113, + "args": { + "External id": 3717484,"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": 1625851566753.986, "dur": 5.603, + "args": { + "External id": 3717485,"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": 1625851566958.215, "dur": 6.248, + "args": { + "External id": 3717486,"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": 1625851566961.752, "dur": 2.373, + "args": { + "External id": 3717487,"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": 1625851567047.893, "dur": 139.740, + "args": { + "External id": 3717488,"Sequence number": 37295130, "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": 1625851567050.893, "dur": 17.983, + "args": { + "External id": 3717489,"Sequence number": 37295130, "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": 1625851567050.893, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1336756, + "ts": 1625851567057.572, "dur": 8.708, + "args": { + "External id": 3717490,"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": 1625851567063.510, "dur": 2.202, + "args": { + "External id": 3717491,"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": 1625851567071.360, "dur": 115.938, + "args": { + "External id": 3717492,"Sequence number": 37295131, "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": 1625851567074.294, "dur": 8.632, + "args": { + "External id": 3717493,"Sequence number": 37295131, "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": 1625851567075.495, "dur": 7.275, + "args": { + "External id": 3717494,"Sequence number": 37295131, "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": 1625851567075.495, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1625851567086.628, "dur": 91.445, + "args": { + "External id": 3717495,"Sequence number": 37295132, "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": 1625851567086.628, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 1336756, "tid": 1336756, + "ts": 1625851567181.620, "dur": 4.694, + "args": { + "External id": 3717496,"Sequence number": 37295133, "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": 1625851567181.620, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336756, "tid": 1336756, + "ts": 1625851567198.200, "dur": 70.310, + "args": { + "External id": 3717497,"Sequence number": 37295134, "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": 1625851567199.183, "dur": 10.630, + "args": { + "External id": 3717498,"Sequence number": 37295134, "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": 1625851567199.183, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1336756, + "ts": 1625851567201.013, "dur": 7.515, + "args": { + "External id": 3717499,"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": 1625851567207.427, "dur": 0.889, + "args": { + "External id": 3717500,"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": 1625851567210.721, "dur": 57.542, + "args": { + "External id": 3717501,"Sequence number": 37295135, "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": 1625851567212.124, "dur": 3.887, + "args": { + "External id": 3717502,"Sequence number": 37295135, "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": 1625851567212.772, "dur": 3.100, + "args": { + "External id": 3717503,"Sequence number": 37295135, "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": 1625851567212.772, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1625851567216.592, "dur": 44.897, + "args": { + "External id": 3717504,"Sequence number": 37295136, "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": 1625851567216.592, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 1336756, "tid": 1336756, + "ts": 1625851567263.062, "dur": 4.821, + "args": { + "External id": 3717505,"Sequence number": 37295137, "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": 1625851567263.062, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336756, "tid": 1336756, + "ts": 1625851567277.186, "dur": 63.684, + "args": { + "External id": 3717506,"Sequence number": 37295138, "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": 1625851567277.965, "dur": 5.286, + "args": { + "External id": 3717507,"Sequence number": 37295138, "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": 1625851567277.965, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1336756, + "ts": 1625851567279.469, "dur": 2.474, + "args": { + "External id": 3717508,"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": 1625851567281.077, "dur": 0.683, + "args": { + "External id": 3717509,"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": 1625851567286.366, "dur": 54.264, + "args": { + "External id": 3717510,"Sequence number": 37295139, "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": 1625851567287.245, "dur": 4.132, + "args": { + "External id": 3717511,"Sequence number": 37295139, "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": 1625851567287.939, "dur": 3.334, + "args": { + "External id": 3717512,"Sequence number": 37295139, "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": 1625851567287.939, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1625851567291.835, "dur": 40.204, + "args": { + "External id": 3717513,"Sequence number": 37295140, "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": 1625851567291.835, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 1336756, "tid": 1336756, + "ts": 1625851567333.613, "dur": 6.701, + "args": { + "External id": 3717514,"Sequence number": 37295141, "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": 1625851567333.613, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1336756, + "ts": 1625851567365.857, "dur": 4.200, + "args": { + "External id": 3717515,"Sequence number": 37295142, "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": 1625851567366.823, "dur": 3.087, + "args": { + "External id": 3717516,"Sequence number": 37295142, "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": 1625851567366.823, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1336756, + "ts": 1625851567377.176, "dur": 5.504, + "args": { + "External id": 3717517,"Sequence number": 37295143, "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": 1625851567378.688, "dur": 3.840, + "args": { + "External id": 3717518,"Sequence number": 37295143, "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": 1625851567378.688, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1336756, + "ts": 1625851567388.692, "dur": 3.724, + "args": { + "External id": 3717519,"Sequence number": 37295144, "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": 1625851567390.070, "dur": 2.015, + "args": { + "External id": 3717520,"Sequence number": 37295144, "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": 1625851567390.070, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunction", "pid": 1336756, "tid": 1336756, + "ts": 1625851567430.825, "dur": 182.310, + "args": { + "External id": 3717521,"Sequence number": 37295145, "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": 1625851567430.825, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336756, "tid": 1336756, + "ts": 1625851567454.240, "dur": 9.292, + "args": { + "External id": 3717522,"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": 1625851567457.610, "dur": 5.373, + "args": { + "External id": 3717523,"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": 1625851567626.551, "dur": 141.645, + "args": { + "External id": 3717524,"Sequence number": 37295146, "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": 1625851567626.551, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336756, "tid": 1336756, + "ts": 1625851567641.615, "dur": 6.618, + "args": { + "External id": 3717525,"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": 1625851567643.921, "dur": 3.947, + "args": { + "External id": 3717526,"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": 1625851567800.921, "dur": 237.171, + "args": { + "External id": 3717527,"Sequence number": 37295147, "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": 1625851567800.921, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 1336756, "tid": 1336756, + "ts": 1625851567833.800, "dur": 135.755, + "args": { + "External id": 3717528,"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": 1625851567887.263, "dur": 8.261, + "args": { + "External id": 3717529,"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": 1625851567889.759, "dur": 5.345, + "args": { + "External id": 3717530,"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": 1625851567898.310, "dur": 4.425, + "args": { + "External id": 3717531,"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": 1625851567906.109, "dur": 1.991, + "args": { + "External id": 3717532,"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": 1625851567910.626, "dur": 3.396, + "args": { + "External id": 3717533,"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": 1625851568019.292, "dur": 5.844, + "args": { + "External id": 3717534,"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": 1625851568043.990, "dur": 6.079, + "args": { + "External id": 3717535,"Sequence number": 37295148, "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": 1625851568045.325, "dur": 4.580, + "args": { + "External id": 3717536,"Sequence number": 37295148, "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": 1625851568045.325, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336756, "tid": 1336756, + "ts": 1625851568065.383, "dur": 124.544, + "args": { + "External id": 3717537,"Sequence number": 37295149, "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": 1625851568069.015, "dur": 8.913, + "args": { + "External id": 3717538,"Sequence number": 37295149, "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": 1625851568069.015, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1336756, + "ts": 1625851568072.205, "dur": 4.457, + "args": { + "External id": 3717539,"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": 1625851568074.411, "dur": 1.966, + "args": { + "External id": 3717540,"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": 1625851568079.297, "dur": 110.325, + "args": { + "External id": 3717541,"Sequence number": 37295150, "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": 1625851568081.803, "dur": 8.282, + "args": { + "External id": 3717542,"Sequence number": 37295150, "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": 1625851568084.658, "dur": 5.278, + "args": { + "External id": 3717543,"Sequence number": 37295150, "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": 1625851568084.658, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1625851568091.113, "dur": 91.853, + "args": { + "External id": 3717544,"Sequence number": 37295151, "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": 1625851568091.113, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 1336756, "tid": 1336756, + "ts": 1625851568185.407, "dur": 3.390, + "args": { + "External id": 3717545,"Sequence number": 37295152, "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": 1625851568185.407, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunction", "pid": 1336756, "tid": 1336756, + "ts": 1625851568227.199, "dur": 241.910, + "args": { + "External id": 3717546,"Sequence number": 37295153, "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": 1625851568227.199, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1336756, + "ts": 1625851568249.207, "dur": 7.460, + "args": { + "External id": 3717547,"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": 1625851568254.789, "dur": 1.697, + "args": { + "External id": 3717548,"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": 1625851568263.837, "dur": 3.552, + "args": { + "External id": 3717549,"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": 1625851568265.005, "dur": 2.279, + "args": { + "External id": 3717550,"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": 1625851568265.812, "dur": 1.358, + "args": { + "External id": 3717551,"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": 1625851568275.069, "dur": 9.405, + "args": { + "External id": 3717552,"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": 1625851568279.397, "dur": 4.765, + "args": { + "External id": 3717553,"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": 1625851568290.825, "dur": 4.148, + "args": { + "External id": 3717554,"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": 1625851568300.355, "dur": 3.213, + "args": { + "External id": 3717555,"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": 1625851568443.894, "dur": 3.386, + "args": { + "External id": 3717556,"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": 1625851568444.838, "dur": 2.142, + "args": { + "External id": 3717557,"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": 1625851568449.765, "dur": 2.804, + "args": { + "External id": 3717558,"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": 1625851568450.915, "dur": 1.530, + "args": { + "External id": 3717559,"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": 1625851568492.631, "dur": 95.783, + "args": { + "External id": 3717560,"Sequence number": 37295154, "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": 1625851568493.762, "dur": 8.085, + "args": { + "External id": 3717561,"Sequence number": 37295154, "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": 1625851568493.762, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1336756, + "ts": 1625851568496.289, "dur": 4.166, + "args": { + "External id": 3717562,"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": 1625851568498.606, "dur": 1.588, + "args": { + "External id": 3717563,"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": 1625851568502.661, "dur": 85.421, + "args": { + "External id": 3717564,"Sequence number": 37295155, "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": 1625851568506.351, "dur": 4.503, + "args": { + "External id": 3717565,"Sequence number": 37295155, "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": 1625851568507.727, "dur": 2.995, + "args": { + "External id": 3717566,"Sequence number": 37295155, "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": 1625851568507.727, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1625851568511.713, "dur": 68.089, + "args": { + "External id": 3717567,"Sequence number": 37295156, "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": 1625851568511.713, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 1336756, "tid": 1336756, + "ts": 1625851568581.990, "dur": 5.506, + "args": { + "External id": 3717568,"Sequence number": 37295157, "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": 1625851568581.990, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336756, "tid": 1336756, + "ts": 1625851568597.456, "dur": 71.987, + "args": { + "External id": 3717569,"Sequence number": 37295158, "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": 1625851568600.177, "dur": 6.405, + "args": { + "External id": 3717570,"Sequence number": 37295158, "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": 1625851568600.177, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1336756, + "ts": 1625851568602.689, "dur": 2.403, + "args": { + "External id": 3717571,"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": 1625851568603.980, "dur": 0.917, + "args": { + "External id": 3717572,"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": 1625851568607.327, "dur": 61.854, + "args": { + "External id": 3717573,"Sequence number": 37295159, "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": 1625851568608.616, "dur": 6.988, + "args": { + "External id": 3717574,"Sequence number": 37295159, "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": 1625851568611.542, "dur": 3.919, + "args": { + "External id": 3717575,"Sequence number": 37295159, "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": 1625851568611.542, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1625851568616.321, "dur": 48.278, + "args": { + "External id": 3717576,"Sequence number": 37295160, "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": 1625851568616.321, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 1336756, "tid": 1336756, + "ts": 1625851568666.376, "dur": 2.447, + "args": { + "External id": 3717577,"Sequence number": 37295161, "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": 1625851568666.376, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "SwiGLULinearFunction", "pid": 1336756, "tid": 1336756, + "ts": 1625851568714.883, "dur": 175.184, + "args": { + "External id": 3717578,"Sequence number": 37295162, "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": 1625851568714.883, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1625851568761.145, "dur": 7.611, + "args": { + "External id": 3717579,"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": 1625851568805.422, "dur": 69.445, + "args": { + "External id": 3717580,"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": 1625851568806.504, "dur": 8.585, + "args": { + "External id": 3717581,"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": 1625851568808.085, "dur": 5.773, + "args": { + "External id": 3717582,"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": 1625851568812.549, "dur": 1.100, + "args": { + "External id": 3717583,"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": 1625851568816.005, "dur": 58.537, + "args": { + "External id": 3717584,"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": 1625851568819.763, "dur": 2.770, + "args": { + "External id": 3717585,"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": 1625851568820.798, "dur": 1.625, + "args": { + "External id": 3717586,"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": 1625851568823.613, "dur": 47.030, + "args": { + "External id": 3717587,"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": 1625851568872.682, "dur": 1.186, + "args": { + "External id": 3717588,"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": 1625851568901.373, "dur": 27.658, + "args": { + "External id": 3717589,"Sequence number": 37295163, "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": 1625851568901.373, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunction", "pid": 1336756, "tid": 1336756, + "ts": 1625851568964.581, "dur": 245.928, + "args": { + "External id": 3717590,"Sequence number": 37295164, "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": 1625851568964.581, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1336756, + "ts": 1625851569032.157, "dur": 6.950, + "args": { + "External id": 3717591,"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": 1625851569035.637, "dur": 3.107, + "args": { + "External id": 3717592,"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": 1625851569047.842, "dur": 8.286, + "args": { + "External id": 3717593,"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": 1625851569050.352, "dur": 5.316, + "args": { + "External id": 3717594,"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": 1625851569062.390, "dur": 4.016, + "args": { + "External id": 3717595,"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": 1625851569193.462, "dur": 3.143, + "args": { + "External id": 3717596,"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": 1625851569194.525, "dur": 1.937, + "args": { + "External id": 3717597,"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": 1625851569232.888, "dur": 92.885, + "args": { + "External id": 3717598,"Sequence number": 37295165, "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": 1625851569234.104, "dur": 10.435, + "args": { + "External id": 3717599,"Sequence number": 37295165, "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": 1625851569234.104, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1336756, + "ts": 1625851569238.979, "dur": 3.918, + "args": { + "External id": 3717600,"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": 1625851569240.929, "dur": 1.753, + "args": { + "External id": 3717601,"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": 1625851569245.749, "dur": 79.715, + "args": { + "External id": 3717602,"Sequence number": 37295166, "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": 1625851569247.499, "dur": 6.031, + "args": { + "External id": 3717603,"Sequence number": 37295166, "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": 1625851569250.664, "dur": 2.742, + "args": { + "External id": 3717604,"Sequence number": 37295166, "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": 1625851569250.664, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1625851569254.361, "dur": 63.418, + "args": { + "External id": 3717605,"Sequence number": 37295167, "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": 1625851569254.361, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 1336756, "tid": 1336756, + "ts": 1625851569319.519, "dur": 5.220, + "args": { + "External id": 3717606,"Sequence number": 37295168, "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": 1625851569319.519, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336756, "tid": 1336756, + "ts": 1625851569334.327, "dur": 71.342, + "args": { + "External id": 3717607,"Sequence number": 37295169, "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": 1625851569335.184, "dur": 11.546, + "args": { + "External id": 3717608,"Sequence number": 37295169, "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": 1625851569335.184, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1336756, + "ts": 1625851569341.902, "dur": 3.693, + "args": { + "External id": 3717609,"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": 1625851569344.058, "dur": 1.158, + "args": { + "External id": 3717610,"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": 1625851569347.644, "dur": 57.830, + "args": { + "External id": 3717611,"Sequence number": 37295170, "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": 1625851569348.577, "dur": 5.641, + "args": { + "External id": 3717612,"Sequence number": 37295170, "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": 1625851569349.683, "dur": 4.394, + "args": { + "External id": 3717613,"Sequence number": 37295170, "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": 1625851569349.683, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1625851569354.824, "dur": 45.489, + "args": { + "External id": 3717614,"Sequence number": 37295171, "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": 1625851569354.824, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 1336756, "tid": 1336756, + "ts": 1625851569402.068, "dur": 3.052, + "args": { + "External id": 3717615,"Sequence number": 37295172, "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": 1625851569402.068, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336756, "tid": 1336756, + "ts": 1625851569413.394, "dur": 61.737, + "args": { + "External id": 3717616,"Sequence number": 37295173, "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": 1625851569414.183, "dur": 7.499, + "args": { + "External id": 3717617,"Sequence number": 37295173, "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": 1625851569414.183, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1336756, + "ts": 1625851569415.567, "dur": 5.087, + "args": { + "External id": 3717618,"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": 1625851569419.525, "dur": 0.838, + "args": { + "External id": 3717619,"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": 1625851569422.160, "dur": 52.781, + "args": { + "External id": 3717620,"Sequence number": 37295174, "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": 1625851569423.310, "dur": 4.117, + "args": { + "External id": 3717621,"Sequence number": 37295174, "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": 1625851569424.103, "dur": 3.201, + "args": { + "External id": 3717622,"Sequence number": 37295174, "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": 1625851569424.103, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1625851569430.080, "dur": 40.271, + "args": { + "External id": 3717623,"Sequence number": 37295175, "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": 1625851569430.080, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 1336756, "tid": 1336756, + "ts": 1625851569471.940, "dur": 2.733, + "args": { + "External id": 3717624,"Sequence number": 37295176, "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": 1625851569471.940, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1336756, + "ts": 1625851569490.967, "dur": 3.921, + "args": { + "External id": 3717625,"Sequence number": 37295177, "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": 1625851569491.972, "dur": 2.774, + "args": { + "External id": 3717626,"Sequence number": 37295177, "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": 1625851569491.972, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1336756, + "ts": 1625851569501.354, "dur": 9.209, + "args": { + "External id": 3717627,"Sequence number": 37295178, "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": 1625851569504.292, "dur": 6.111, + "args": { + "External id": 3717628,"Sequence number": 37295178, "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": 1625851569504.292, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1336756, + "ts": 1625851569514.941, "dur": 2.740, + "args": { + "External id": 3717629,"Sequence number": 37295179, "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": 1625851569515.773, "dur": 1.769, + "args": { + "External id": 3717630,"Sequence number": 37295179, "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": 1625851569515.773, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunction", "pid": 1336756, "tid": 1336756, + "ts": 1625851569546.009, "dur": 198.711, + "args": { + "External id": 3717631,"Sequence number": 37295180, "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": 1625851569546.009, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336756, "tid": 1336756, + "ts": 1625851569565.086, "dur": 32.493, + "args": { + "External id": 3717632,"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": 1625851569592.604, "dur": 4.495, + "args": { + "External id": 3717633,"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": 1625851569762.243, "dur": 115.576, + "args": { + "External id": 3717634,"Sequence number": 37295181, "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": 1625851569762.243, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336756, "tid": 1336756, + "ts": 1625851569778.629, "dur": 7.884, + "args": { + "External id": 3717635,"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": 1625851569781.067, "dur": 5.035, + "args": { + "External id": 3717636,"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": 1625851569904.015, "dur": 221.179, + "args": { + "External id": 3717637,"Sequence number": 37295182, "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": 1625851569904.015, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 1336756, "tid": 1336756, + "ts": 1625851569931.271, "dur": 165.988, + "args": { + "External id": 3717638,"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": 1625851569980.182, "dur": 43.381, + "args": { + "External id": 3717639,"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": 1625851569982.313, "dur": 40.392, + "args": { + "External id": 3717640,"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": 1625851570027.298, "dur": 4.343, + "args": { + "External id": 3717641,"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": 1625851570032.829, "dur": 1.554, + "args": { + "External id": 3717642,"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": 1625851570036.728, "dur": 3.381, + "args": { + "External id": 3717643,"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": 1625851570109.071, "dur": 4.955, + "args": { + "External id": 3717644,"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": 1625851570130.570, "dur": 8.490, + "args": { + "External id": 3717645,"Sequence number": 37295183, "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": 1625851570131.951, "dur": 6.933, + "args": { + "External id": 3717646,"Sequence number": 37295183, "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": 1625851570131.951, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336756, "tid": 1336756, + "ts": 1625851570157.341, "dur": 117.841, + "args": { + "External id": 3717647,"Sequence number": 37295184, "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": 1625851570159.103, "dur": 9.828, + "args": { + "External id": 3717648,"Sequence number": 37295184, "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": 1625851570159.103, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1336756, + "ts": 1625851570162.258, "dur": 5.385, + "args": { + "External id": 3717649,"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": 1625851570165.066, "dur": 2.259, + "args": { + "External id": 3717650,"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": 1625851570170.051, "dur": 104.785, + "args": { + "External id": 3717651,"Sequence number": 37295185, "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": 1625851570174.007, "dur": 5.792, + "args": { + "External id": 3717652,"Sequence number": 37295185, "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": 1625851570174.918, "dur": 4.697, + "args": { + "External id": 3717653,"Sequence number": 37295185, "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": 1625851570174.918, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1625851570180.604, "dur": 84.597, + "args": { + "External id": 3717654,"Sequence number": 37295186, "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": 1625851570180.604, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 1336756, "tid": 1336756, + "ts": 1625851570267.933, "dur": 6.104, + "args": { + "External id": 3717655,"Sequence number": 37295187, "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": 1625851570267.933, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunction", "pid": 1336756, "tid": 1336756, + "ts": 1625851570311.048, "dur": 209.561, + "args": { + "External id": 3717656,"Sequence number": 37295188, "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": 1625851570311.048, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1336756, + "ts": 1625851570331.837, "dur": 2.945, + "args": { + "External id": 3717657,"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": 1625851570332.786, "dur": 1.588, + "args": { + "External id": 3717658,"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": 1625851570338.319, "dur": 5.818, + "args": { + "External id": 3717659,"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": 1625851570339.586, "dur": 4.449, + "args": { + "External id": 3717660,"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": 1625851570342.499, "dur": 1.422, + "args": { + "External id": 3717661,"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": 1625851570351.544, "dur": 7.518, + "args": { + "External id": 3717662,"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": 1625851570353.572, "dur": 5.190, + "args": { + "External id": 3717663,"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": 1625851570364.789, "dur": 3.690, + "args": { + "External id": 3717664,"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": 1625851570371.989, "dur": 3.997, + "args": { + "External id": 3717665,"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": 1625851570497.712, "dur": 3.175, + "args": { + "External id": 3717666,"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": 1625851570498.476, "dur": 2.242, + "args": { + "External id": 3717667,"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": 1625851570505.567, "dur": 1.915, + "args": { + "External id": 3717668,"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": 1625851570506.531, "dur": 0.849, + "args": { + "External id": 3717669,"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": 1625851570540.513, "dur": 93.730, + "args": { + "External id": 3717670,"Sequence number": 37295189, "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": 1625851570541.606, "dur": 7.868, + "args": { + "External id": 3717671,"Sequence number": 37295189, "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": 1625851570541.606, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1336756, + "ts": 1625851570544.431, "dur": 3.622, + "args": { + "External id": 3717672,"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": 1625851570546.229, "dur": 1.619, + "args": { + "External id": 3717673,"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": 1625851570552.776, "dur": 81.076, + "args": { + "External id": 3717674,"Sequence number": 37295190, "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": 1625851570554.332, "dur": 3.092, + "args": { + "External id": 3717675,"Sequence number": 37295190, "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": 1625851570554.868, "dur": 2.434, + "args": { + "External id": 3717676,"Sequence number": 37295190, "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": 1625851570554.868, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1625851570558.343, "dur": 68.066, + "args": { + "External id": 3717677,"Sequence number": 37295191, "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": 1625851570558.343, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 1336756, "tid": 1336756, + "ts": 1625851570628.451, "dur": 4.773, + "args": { + "External id": 3717678,"Sequence number": 37295192, "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": 1625851570628.451, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336756, "tid": 1336756, + "ts": 1625851570642.838, "dur": 93.945, + "args": { + "External id": 3717679,"Sequence number": 37295193, "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": 1625851570643.793, "dur": 6.260, + "args": { + "External id": 3717680,"Sequence number": 37295193, "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": 1625851570643.793, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1336756, + "ts": 1625851570645.891, "dur": 3.046, + "args": { + "External id": 3717681,"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": 1625851570647.996, "dur": 0.769, + "args": { + "External id": 3717682,"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": 1625851570650.535, "dur": 85.917, + "args": { + "External id": 3717683,"Sequence number": 37295194, "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": 1625851570653.618, "dur": 6.933, + "args": { + "External id": 3717684,"Sequence number": 37295194, "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": 1625851570654.510, "dur": 5.876, + "args": { + "External id": 3717685,"Sequence number": 37295194, "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": 1625851570654.510, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1625851570661.154, "dur": 66.849, + "args": { + "External id": 3717686,"Sequence number": 37295195, "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": 1625851570661.154, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 1336756, "tid": 1336756, + "ts": 1625851570730.718, "dur": 5.214, + "args": { + "External id": 3717687,"Sequence number": 37295196, "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": 1625851570730.718, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "SwiGLULinearFunction", "pid": 1336756, "tid": 1336756, + "ts": 1625851570763.970, "dur": 147.645, + "args": { + "External id": 3717688,"Sequence number": 37295197, "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": 1625851570763.970, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1625851570799.647, "dur": 4.584, + "args": { + "External id": 3717689,"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": 1625851570834.676, "dur": 62.857, + "args": { + "External id": 3717690,"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": 1625851570835.454, "dur": 5.444, + "args": { + "External id": 3717691,"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": 1625851570836.538, "dur": 3.422, + "args": { + "External id": 3717692,"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": 1625851570838.269, "dur": 1.456, + "args": { + "External id": 3717693,"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": 1625851570843.926, "dur": 53.292, + "args": { + "External id": 3717694,"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": 1625851570845.575, "dur": 2.290, + "args": { + "External id": 3717695,"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": 1625851570846.286, "dur": 1.415, + "args": { + "External id": 3717696,"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": 1625851570848.998, "dur": 44.201, + "args": { + "External id": 3717697,"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": 1625851570895.591, "dur": 1.056, + "args": { + "External id": 3717698,"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": 1625851570920.098, "dur": 24.981, + "args": { + "External id": 3717699,"Sequence number": 37295198, "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": 1625851570920.098, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunction", "pid": 1336756, "tid": 1336756, + "ts": 1625851570979.423, "dur": 219.676, + "args": { + "External id": 3717700,"Sequence number": 37295199, "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": 1625851570979.423, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1336756, + "ts": 1625851571033.716, "dur": 4.179, + "args": { + "External id": 3717701,"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": 1625851571034.603, "dur": 2.798, + "args": { + "External id": 3717702,"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": 1625851571046.013, "dur": 7.759, + "args": { + "External id": 3717703,"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": 1625851571048.406, "dur": 4.921, + "args": { + "External id": 3717704,"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": 1625851571059.766, "dur": 3.905, + "args": { + "External id": 3717705,"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": 1625851571181.753, "dur": 3.331, + "args": { + "External id": 3717706,"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": 1625851571182.695, "dur": 2.088, + "args": { + "External id": 3717707,"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": 1625851571221.400, "dur": 92.244, + "args": { + "External id": 3717708,"Sequence number": 37295200, "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": 1625851571222.326, "dur": 7.936, + "args": { + "External id": 3717709,"Sequence number": 37295200, "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": 1625851571222.326, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1336756, + "ts": 1625851571225.263, "dur": 3.566, + "args": { + "External id": 3717710,"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": 1625851571227.091, "dur": 1.498, + "args": { + "External id": 3717711,"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": 1625851571231.529, "dur": 81.842, + "args": { + "External id": 3717712,"Sequence number": 37295201, "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": 1625851571235.304, "dur": 4.045, + "args": { + "External id": 3717713,"Sequence number": 37295201, "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": 1625851571236.227, "dur": 3.000, + "args": { + "External id": 3717714,"Sequence number": 37295201, "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": 1625851571236.227, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1625851571240.267, "dur": 64.695, + "args": { + "External id": 3717715,"Sequence number": 37295202, "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": 1625851571240.267, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 1336756, "tid": 1336756, + "ts": 1625851571307.308, "dur": 5.365, + "args": { + "External id": 3717716,"Sequence number": 37295203, "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": 1625851571307.308, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336756, "tid": 1336756, + "ts": 1625851571323.063, "dur": 63.660, + "args": { + "External id": 3717717,"Sequence number": 37295204, "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": 1625851571326.061, "dur": 6.138, + "args": { + "External id": 3717718,"Sequence number": 37295204, "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": 1625851571326.061, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1336756, + "ts": 1625851571328.430, "dur": 2.454, + "args": { + "External id": 3717719,"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": 1625851571329.944, "dur": 0.760, + "args": { + "External id": 3717720,"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": 1625851571332.721, "dur": 53.735, + "args": { + "External id": 3717721,"Sequence number": 37295205, "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": 1625851571334.139, "dur": 5.385, + "args": { + "External id": 3717722,"Sequence number": 37295205, "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": 1625851571337.332, "dur": 2.056, + "args": { + "External id": 3717723,"Sequence number": 37295205, "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": 1625851571337.332, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1625851571340.019, "dur": 41.509, + "args": { + "External id": 3717724,"Sequence number": 37295206, "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": 1625851571340.019, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 1336756, "tid": 1336756, + "ts": 1625851571382.988, "dur": 3.120, + "args": { + "External id": 3717725,"Sequence number": 37295207, "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": 1625851571382.988, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336756, "tid": 1336756, + "ts": 1625851571393.959, "dur": 64.811, + "args": { + "External id": 3717726,"Sequence number": 37295208, "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": 1625851571394.674, "dur": 9.923, + "args": { + "External id": 3717727,"Sequence number": 37295208, "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": 1625851571394.674, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1336756, + "ts": 1625851571398.138, "dur": 5.276, + "args": { + "External id": 3717728,"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": 1625851571399.901, "dur": 3.289, + "args": { + "External id": 3717729,"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": 1625851571405.239, "dur": 53.201, + "args": { + "External id": 3717730,"Sequence number": 37295209, "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": 1625851571406.174, "dur": 6.726, + "args": { + "External id": 3717731,"Sequence number": 37295209, "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": 1625851571409.524, "dur": 3.266, + "args": { + "External id": 3717732,"Sequence number": 37295209, "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": 1625851571409.524, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1625851571413.596, "dur": 38.375, + "args": { + "External id": 3717733,"Sequence number": 37295210, "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": 1625851571413.596, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 1336756, "tid": 1336756, + "ts": 1625851571453.710, "dur": 4.425, + "args": { + "External id": 3717734,"Sequence number": 37295211, "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": 1625851571453.710, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1336756, + "ts": 1625851571472.839, "dur": 6.676, + "args": { + "External id": 3717735,"Sequence number": 37295212, "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": 1625851571474.392, "dur": 4.967, + "args": { + "External id": 3717736,"Sequence number": 37295212, "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": 1625851571474.392, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1336756, + "ts": 1625851571486.091, "dur": 3.205, + "args": { + "External id": 3717737,"Sequence number": 37295213, "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": 1625851571487.178, "dur": 1.981, + "args": { + "External id": 3717738,"Sequence number": 37295213, "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": 1625851571487.178, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1336756, + "ts": 1625851571493.682, "dur": 3.695, + "args": { + "External id": 3717739,"Sequence number": 37295214, "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": 1625851571495.189, "dur": 2.040, + "args": { + "External id": 3717740,"Sequence number": 37295214, "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": 1625851571495.189, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunction", "pid": 1336756, "tid": 1336756, + "ts": 1625851571525.292, "dur": 141.185, + "args": { + "External id": 3717741,"Sequence number": 37295215, "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": 1625851571525.292, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336756, "tid": 1336756, + "ts": 1625851571543.561, "dur": 9.210, + "args": { + "External id": 3717742,"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": 1625851571545.942, "dur": 6.407, + "args": { + "External id": 3717743,"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": 1625851571695.302, "dur": 113.797, + "args": { + "External id": 3717744,"Sequence number": 37295216, "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": 1625851571695.302, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336756, "tid": 1336756, + "ts": 1625851571710.207, "dur": 8.200, + "args": { + "External id": 3717745,"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": 1625851571712.668, "dur": 5.149, + "args": { + "External id": 3717746,"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": 1625851571838.049, "dur": 213.888, + "args": { + "External id": 3717747,"Sequence number": 37295217, "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": 1625851571838.049, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 1336756, "tid": 1336756, + "ts": 1625851571864.398, "dur": 157.107, + "args": { + "External id": 3717748,"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": 1625851571908.574, "dur": 7.726, + "args": { + "External id": 3717749,"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": 1625851571911.078, "dur": 4.621, + "args": { + "External id": 3717750,"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": 1625851571918.928, "dur": 4.204, + "args": { + "External id": 3717751,"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": 1625851571924.242, "dur": 1.318, + "args": { + "External id": 3717752,"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": 1625851571928.351, "dur": 2.942, + "args": { + "External id": 3717753,"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": 1625851572035.801, "dur": 4.974, + "args": { + "External id": 3717754,"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": 1625851572057.094, "dur": 6.412, + "args": { + "External id": 3717755,"Sequence number": 37295218, "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": 1625851572059.000, "dur": 4.227, + "args": { + "External id": 3717756,"Sequence number": 37295218, "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": 1625851572059.000, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336756, "tid": 1336756, + "ts": 1625851572077.062, "dur": 119.498, + "args": { + "External id": 3717757,"Sequence number": 37295219, "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": 1625851572078.175, "dur": 12.760, + "args": { + "External id": 3717758,"Sequence number": 37295219, "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": 1625851572078.175, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1336756, + "ts": 1625851572082.967, "dur": 6.505, + "args": { + "External id": 3717759,"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": 1625851572087.170, "dur": 2.062, + "args": { + "External id": 3717760,"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": 1625851572092.046, "dur": 104.099, + "args": { + "External id": 3717761,"Sequence number": 37295220, "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": 1625851572094.063, "dur": 3.455, + "args": { + "External id": 3717762,"Sequence number": 37295220, "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": 1625851572094.681, "dur": 2.716, + "args": { + "External id": 3717763,"Sequence number": 37295220, "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": 1625851572094.681, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1625851572098.311, "dur": 89.265, + "args": { + "External id": 3717764,"Sequence number": 37295221, "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": 1625851572098.311, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 1336756, "tid": 1336756, + "ts": 1625851572189.716, "dur": 5.651, + "args": { + "External id": 3717765,"Sequence number": 37295222, "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": 1625851572189.716, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunction", "pid": 1336756, "tid": 1336756, + "ts": 1625851572231.818, "dur": 210.067, + "args": { + "External id": 3717766,"Sequence number": 37295223, "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": 1625851572231.818, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1336756, + "ts": 1625851572249.852, "dur": 2.325, + "args": { + "External id": 3717767,"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": 1625851572250.526, "dur": 1.180, + "args": { + "External id": 3717768,"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": 1625851572256.142, "dur": 5.211, + "args": { + "External id": 3717769,"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": 1625851572259.350, "dur": 1.899, + "args": { + "External id": 3717770,"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": 1625851572260.317, "dur": 0.828, + "args": { + "External id": 3717771,"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": 1625851572268.205, "dur": 6.688, + "args": { + "External id": 3717772,"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": 1625851572270.304, "dur": 4.185, + "args": { + "External id": 3717773,"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": 1625851572281.038, "dur": 3.490, + "args": { + "External id": 3717774,"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": 1625851572288.151, "dur": 3.797, + "args": { + "External id": 3717775,"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": 1625851572420.902, "dur": 3.029, + "args": { + "External id": 3717776,"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": 1625851572422.262, "dur": 1.443, + "args": { + "External id": 3717777,"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": 1625851572426.273, "dur": 2.235, + "args": { + "External id": 3717778,"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": 1625851572427.342, "dur": 1.047, + "args": { + "External id": 3717779,"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": 1625851572460.908, "dur": 96.460, + "args": { + "External id": 3717780,"Sequence number": 37295224, "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": 1625851572461.975, "dur": 9.699, + "args": { + "External id": 3717781,"Sequence number": 37295224, "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": 1625851572461.975, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1336756, + "ts": 1625851572464.573, "dur": 5.700, + "args": { + "External id": 3717782,"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": 1625851572468.679, "dur": 1.399, + "args": { + "External id": 3717783,"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": 1625851572472.552, "dur": 84.468, + "args": { + "External id": 3717784,"Sequence number": 37295225, "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": 1625851572473.833, "dur": 3.076, + "args": { + "External id": 3717785,"Sequence number": 37295225, "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": 1625851572474.742, "dur": 2.039, + "args": { + "External id": 3717786,"Sequence number": 37295225, "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": 1625851572474.742, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1625851572480.020, "dur": 68.347, + "args": { + "External id": 3717787,"Sequence number": 37295226, "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": 1625851572480.020, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 1336756, "tid": 1336756, + "ts": 1625851572550.786, "dur": 5.682, + "args": { + "External id": 3717788,"Sequence number": 37295227, "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": 1625851572550.786, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336756, "tid": 1336756, + "ts": 1625851572565.648, "dur": 100.975, + "args": { + "External id": 3717789,"Sequence number": 37295228, "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": 1625851572566.153, "dur": 17.352, + "args": { + "External id": 3717790,"Sequence number": 37295228, "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": 1625851572566.153, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1336756, + "ts": 1625851572568.084, "dur": 14.073, + "args": { + "External id": 3717791,"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": 1625851572578.976, "dur": 2.937, + "args": { + "External id": 3717792,"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": 1625851572584.368, "dur": 81.932, + "args": { + "External id": 3717793,"Sequence number": 37295229, "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": 1625851572585.547, "dur": 3.861, + "args": { + "External id": 3717794,"Sequence number": 37295229, "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": 1625851572586.071, "dur": 3.210, + "args": { + "External id": 3717795,"Sequence number": 37295229, "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": 1625851572586.071, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1625851572590.200, "dur": 69.394, + "args": { + "External id": 3717796,"Sequence number": 37295230, "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": 1625851572590.200, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 1336756, "tid": 1336756, + "ts": 1625851572661.203, "dur": 4.763, + "args": { + "External id": 3717797,"Sequence number": 37295231, "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": 1625851572661.203, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "SwiGLULinearFunction", "pid": 1336756, "tid": 1336756, + "ts": 1625851572705.887, "dur": 166.855, + "args": { + "External id": 3717798,"Sequence number": 37295232, "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": 1625851572705.887, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1625851572740.929, "dur": 5.383, + "args": { + "External id": 3717799,"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": 1625851572780.640, "dur": 78.364, + "args": { + "External id": 3717800,"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": 1625851572781.335, "dur": 5.249, + "args": { + "External id": 3717801,"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": 1625851572782.667, "dur": 2.920, + "args": { + "External id": 3717802,"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": 1625851572784.527, "dur": 0.905, + "args": { + "External id": 3717803,"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": 1625851572787.269, "dur": 71.440, + "args": { + "External id": 3717804,"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": 1625851572788.674, "dur": 3.075, + "args": { + "External id": 3717805,"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": 1625851572789.670, "dur": 1.966, + "args": { + "External id": 3717806,"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": 1625851572792.266, "dur": 62.571, + "args": { + "External id": 3717807,"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": 1625851572856.625, "dur": 1.397, + "args": { + "External id": 3717808,"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": 1625851572881.238, "dur": 26.728, + "args": { + "External id": 3717809,"Sequence number": 37295233, "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": 1625851572881.238, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunction", "pid": 1336756, "tid": 1336756, + "ts": 1625851572944.673, "dur": 226.180, + "args": { + "External id": 3717810,"Sequence number": 37295234, "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": 1625851572944.673, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1336756, + "ts": 1625851572962.004, "dur": 2.700, + "args": { + "External id": 3717811,"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": 1625851572962.837, "dur": 1.658, + "args": { + "External id": 3717812,"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": 1625851572971.867, "dur": 6.624, + "args": { + "External id": 3717813,"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": 1625851572973.833, "dur": 4.256, + "args": { + "External id": 3717814,"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": 1625851573017.325, "dur": 5.084, + "args": { + "External id": 3717815,"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": 1625851573149.403, "dur": 10.599, + "args": { + "External id": 3717816,"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": 1625851573154.430, "dur": 5.328, + "args": { + "External id": 3717817,"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": 1625851573192.603, "dur": 89.340, + "args": { + "External id": 3717818,"Sequence number": 37295235, "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": 1625851573193.528, "dur": 10.160, + "args": { + "External id": 3717819,"Sequence number": 37295235, "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": 1625851573193.528, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1336756, + "ts": 1625851573196.427, "dur": 5.667, + "args": { + "External id": 3717820,"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": 1625851573200.407, "dur": 1.493, + "args": { + "External id": 3717821,"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": 1625851573204.531, "dur": 77.200, + "args": { + "External id": 3717822,"Sequence number": 37295236, "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": 1625851573206.096, "dur": 3.650, + "args": { + "External id": 3717823,"Sequence number": 37295236, "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": 1625851573206.703, "dur": 2.929, + "args": { + "External id": 3717824,"Sequence number": 37295236, "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": 1625851573206.703, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1625851573210.338, "dur": 65.245, + "args": { + "External id": 3717825,"Sequence number": 37295237, "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": 1625851573210.338, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 1336756, "tid": 1336756, + "ts": 1625851573277.931, "dur": 3.114, + "args": { + "External id": 3717826,"Sequence number": 37295238, "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": 1625851573277.931, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336756, "tid": 1336756, + "ts": 1625851573290.320, "dur": 62.495, + "args": { + "External id": 3717827,"Sequence number": 37295239, "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": 1625851573290.791, "dur": 5.712, + "args": { + "External id": 3717828,"Sequence number": 37295239, "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": 1625851573290.791, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1336756, + "ts": 1625851573292.457, "dur": 2.986, + "args": { + "External id": 3717829,"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": 1625851573294.183, "dur": 1.101, + "args": { + "External id": 3717830,"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": 1625851573299.257, "dur": 53.339, + "args": { + "External id": 3717831,"Sequence number": 37295240, "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": 1625851573300.153, "dur": 5.588, + "args": { + "External id": 3717832,"Sequence number": 37295240, "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": 1625851573301.047, "dur": 4.535, + "args": { + "External id": 3717833,"Sequence number": 37295240, "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": 1625851573301.047, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1625851573306.216, "dur": 39.103, + "args": { + "External id": 3717834,"Sequence number": 37295241, "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": 1625851573306.216, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 1336756, "tid": 1336756, + "ts": 1625851573347.057, "dur": 5.202, + "args": { + "External id": 3717835,"Sequence number": 37295242, "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": 1625851573347.057, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336756, "tid": 1336756, + "ts": 1625851573359.922, "dur": 63.518, + "args": { + "External id": 3717836,"Sequence number": 37295243, "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": 1625851573360.695, "dur": 11.489, + "args": { + "External id": 3717837,"Sequence number": 37295243, "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": 1625851573360.695, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1336756, + "ts": 1625851573366.489, "dur": 4.596, + "args": { + "External id": 3717838,"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": 1625851573370.019, "dur": 0.871, + "args": { + "External id": 3717839,"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": 1625851573372.758, "dur": 50.368, + "args": { + "External id": 3717840,"Sequence number": 37295244, "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": 1625851573375.730, "dur": 3.496, + "args": { + "External id": 3717841,"Sequence number": 37295244, "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": 1625851573376.320, "dur": 2.749, + "args": { + "External id": 3717842,"Sequence number": 37295244, "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": 1625851573376.320, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1625851573379.887, "dur": 37.528, + "args": { + "External id": 3717843,"Sequence number": 37295245, "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": 1625851573379.887, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 1336756, "tid": 1336756, + "ts": 1625851573418.785, "dur": 4.044, + "args": { + "External id": 3717844,"Sequence number": 37295246, "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": 1625851573418.785, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1336756, + "ts": 1625851573440.732, "dur": 3.865, + "args": { + "External id": 3717845,"Sequence number": 37295247, "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": 1625851573441.617, "dur": 2.833, + "args": { + "External id": 3717846,"Sequence number": 37295247, "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": 1625851573441.617, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1336756, + "ts": 1625851573450.801, "dur": 3.102, + "args": { + "External id": 3717847,"Sequence number": 37295248, "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": 1625851573451.625, "dur": 2.140, + "args": { + "External id": 3717848,"Sequence number": 37295248, "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": 1625851573451.625, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1336756, + "ts": 1625851573458.224, "dur": 5.565, + "args": { + "External id": 3717849,"Sequence number": 37295249, "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": 1625851573461.117, "dur": 2.535, + "args": { + "External id": 3717850,"Sequence number": 37295249, "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": 1625851573461.117, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "RotaryEmbeddingFunction", "pid": 1336756, "tid": 1336756, + "ts": 1625851573494.488, "dur": 147.473, + "args": { + "External id": 3717851,"Sequence number": 37295250, "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": 1625851573494.488, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336756, "tid": 1336756, + "ts": 1625851573513.442, "dur": 7.967, + "args": { + "External id": 3717852,"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": 1625851573515.763, "dur": 5.233, + "args": { + "External id": 3717853,"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": 1625851573653.406, "dur": 127.987, + "args": { + "External id": 3717854,"Sequence number": 37295251, "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": 1625851573653.406, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty_like", "pid": 1336756, "tid": 1336756, + "ts": 1625851573667.299, "dur": 6.610, + "args": { + "External id": 3717855,"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": 1625851573669.122, "dur": 4.382, + "args": { + "External id": 3717856,"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": 1625851573812.113, "dur": 223.354, + "args": { + "External id": 3717857,"Sequence number": 37295252, "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": 1625851573812.113, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "flash_attn::_flash_attn_forward", "pid": 1336756, "tid": 1336756, + "ts": 1625851573838.118, "dur": 125.011, + "args": { + "External id": 3717858,"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": 1625851573885.636, "dur": 7.884, + "args": { + "External id": 3717859,"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": 1625851573888.109, "dur": 4.883, + "args": { + "External id": 3717860,"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": 1625851573898.260, "dur": 3.995, + "args": { + "External id": 3717861,"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": 1625851573903.611, "dur": 1.474, + "args": { + "External id": 3717862,"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": 1625851573907.400, "dur": 5.346, + "args": { + "External id": 3717863,"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": 1625851573973.767, "dur": 4.553, + "args": { + "External id": 3717864,"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": 1625851574042.606, "dur": 6.602, + "args": { + "External id": 3717865,"Sequence number": 37295253, "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": 1625851574044.034, "dur": 5.003, + "args": { + "External id": 3717866,"Sequence number": 37295253, "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": 1625851574044.034, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336756, "tid": 1336756, + "ts": 1625851574061.876, "dur": 106.492, + "args": { + "External id": 3717867,"Sequence number": 37295254, "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": 1625851574063.168, "dur": 9.917, + "args": { + "External id": 3717868,"Sequence number": 37295254, "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": 1625851574063.168, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1336756, + "ts": 1625851574067.562, "dur": 4.137, + "args": { + "External id": 3717869,"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": 1625851574069.985, "dur": 1.453, + "args": { + "External id": 3717870,"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": 1625851574074.150, "dur": 93.837, + "args": { + "External id": 3717871,"Sequence number": 37295255, "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": 1625851574075.648, "dur": 5.030, + "args": { + "External id": 3717872,"Sequence number": 37295255, "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": 1625851574078.498, "dur": 2.040, + "args": { + "External id": 3717873,"Sequence number": 37295255, "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": 1625851574078.498, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1625851574081.588, "dur": 79.703, + "args": { + "External id": 3717874,"Sequence number": 37295256, "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": 1625851574081.588, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 1336756, "tid": 1336756, + "ts": 1625851574163.713, "dur": 3.574, + "args": { + "External id": 3717875,"Sequence number": 37295257, "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": 1625851574163.713, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "LayerNormFunction", "pid": 1336756, "tid": 1336756, + "ts": 1625851574203.304, "dur": 206.030, + "args": { + "External id": 3717876,"Sequence number": 37295258, "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": 1625851574203.304, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::reshape", "pid": 1336756, "tid": 1336756, + "ts": 1625851574221.464, "dur": 4.901, + "args": { + "External id": 3717877,"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": 1625851574224.823, "dur": 1.374, + "args": { + "External id": 3717878,"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": 1625851574230.118, "dur": 3.084, + "args": { + "External id": 3717879,"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": 1625851574231.200, "dur": 1.898, + "args": { + "External id": 3717880,"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": 1625851574231.830, "dur": 1.179, + "args": { + "External id": 3717881,"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": 1625851574240.585, "dur": 7.049, + "args": { + "External id": 3717882,"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": 1625851574242.870, "dur": 4.370, + "args": { + "External id": 3717883,"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": 1625851574255.657, "dur": 3.360, + "args": { + "External id": 3717884,"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": 1625851574262.449, "dur": 2.768, + "args": { + "External id": 3717885,"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": 1625851574386.506, "dur": 6.060, + "args": { + "External id": 3717886,"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": 1625851574387.333, "dur": 4.949, + "args": { + "External id": 3717887,"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": 1625851574395.035, "dur": 2.491, + "args": { + "External id": 3717888,"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": 1625851574396.270, "dur": 1.155, + "args": { + "External id": 3717889,"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": 1625851574427.314, "dur": 87.832, + "args": { + "External id": 3717890,"Sequence number": 37295259, "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": 1625851574428.086, "dur": 8.387, + "args": { + "External id": 3717891,"Sequence number": 37295259, "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": 1625851574428.086, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1336756, + "ts": 1625851574432.107, "dur": 3.133, + "args": { + "External id": 3717892,"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": 1625851574433.956, "dur": 1.090, + "args": { + "External id": 3717893,"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": 1625851574437.532, "dur": 77.339, + "args": { + "External id": 3717894,"Sequence number": 37295260, "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": 1625851574439.195, "dur": 7.667, + "args": { + "External id": 3717895,"Sequence number": 37295260, "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": 1625851574441.979, "dur": 4.742, + "args": { + "External id": 3717896,"Sequence number": 37295260, "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": 1625851574441.979, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1625851574447.654, "dur": 60.779, + "args": { + "External id": 3717897,"Sequence number": 37295261, "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": 1625851574447.654, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 1336756, "tid": 1336756, + "ts": 1625851574510.741, "dur": 3.570, + "args": { + "External id": 3717898,"Sequence number": 37295262, "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": 1625851574510.741, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::linear", "pid": 1336756, "tid": 1336756, + "ts": 1625851574523.324, "dur": 73.956, + "args": { + "External id": 3717899,"Sequence number": 37295263, "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": 1625851574524.047, "dur": 12.222, + "args": { + "External id": 3717900,"Sequence number": 37295263, "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": 1625851574524.047, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::transpose", "pid": 1336756, "tid": 1336756, + "ts": 1625851574530.145, "dur": 4.913, + "args": { + "External id": 3717901,"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": 1625851574534.155, "dur": 0.745, + "args": { + "External id": 3717902,"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": 1625851574536.982, "dur": 60.045, + "args": { + "External id": 3717903,"Sequence number": 37295264, "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": 1625851574537.948, "dur": 6.440, + "args": { + "External id": 3717904,"Sequence number": 37295264, "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": 1625851574538.674, "dur": 5.554, + "args": { + "External id": 3717905,"Sequence number": 37295264, "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": 1625851574538.674, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::mm", "pid": 1336756, "tid": 1336756, + "ts": 1625851574544.976, "dur": 45.006, + "args": { + "External id": 3717906,"Sequence number": 37295265, "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": 1625851574544.976, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_unsafe_view", "pid": 1336756, "tid": 1336756, + "ts": 1625851574591.509, "dur": 5.193, + "args": { + "External id": 3717907,"Sequence number": 37295266, "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": 1625851574591.509, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "SwiGLULinearFunction", "pid": 1336756, "tid": 1336756, + "ts": 1625851574617.304, "dur": 173.378, + "args": { + "External id": 3717908,"Sequence number": 37295267, "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": 1625851574617.304, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::empty", "pid": 1336756, "tid": 1336756, + "ts": 1625851574653.430, "dur": 4.371, + "args": { + "External id": 3717909,"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": 1625851574709.249, "dur": 66.551, + "args": { + "External id": 3717910,"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": 1625851574710.139, "dur": 6.598, + "args": { + "External id": 3717911,"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": 1625851574711.704, "dur": 3.964, + "args": { + "External id": 3717912,"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": 1625851574714.087, "dur": 1.242, + "args": { + "External id": 3717913,"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": 1625851574717.733, "dur": 57.804, + "args": { + "External id": 3717914,"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": 1625851574718.952, "dur": 5.452, + "args": { + "External id": 3717915,"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": 1625851574722.840, "dur": 1.443, + "args": { + "External id": 3717916,"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": 1625851574724.900, "dur": 46.808, + "args": { + "External id": 3717917,"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": 1625851574773.399, "dur": 1.453, + "args": { + "External id": 3717918,"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": 1625851574799.401, "dur": 26.892, + "args": { + "External id": 3717919,"Sequence number": 37295268, "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": 1625851574799.401, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::stack", "pid": 1336756, "tid": 1336756, + "ts": 1625851574844.777, "dur": 46.132, + "args": { + "External id": 3717920,"Sequence number": 37295269, "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": 1625851574844.777, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::cat", "pid": 1336756, "tid": 1336756, + "ts": 1625851574852.739, "dur": 33.463, + "args": { + "External id": 3717921,"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": 1625851574887.878, "dur": 1.337, + "args": { + "External id": 3717922,"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": 1625851574930.442, "dur": 46.159, + "args": { + "External id": 3717923,"Record function id": 0, "Ev Idx": 8634 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "Torch-Compiled Region: 2/0", "pid": 1336756, "tid": 1336756, + "ts": 1625851574977.923, "dur": 246.077, + "args": { + "External id": 3717924,"Record function id": 0, "Ev Idx": 8635 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "CompiledFunction", "pid": 1336756, "tid": 1336756, + "ts": 1625851575054.968, "dur": 160.892, + "args": { + "External id": 3717925,"Sequence number": 37295270, "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": 1625851575054.968, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "layer_norm_fwd_kernel_0", "pid": 1336756, "tid": 1336756, + "ts": 1625851575130.214, "dur": 44.433, + "args": { + "External id": 3717926,"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": 1625851575319.150, "dur": 41.063, + "args": { + "External id": 3717927,"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": 1625851575322.171, "dur": 5.393, + "args": { + "External id": 3717928,"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": 1625851575330.498, "dur": 29.415, + "args": { + "External id": 3717929,"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": 1625851575333.904, "dur": 25.604, + "args": { + "External id": 3717930,"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": 1625851575364.533, "dur": 23.386, + "args": { + "External id": 3717931,"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": 1625851575365.811, "dur": 3.126, + "args": { + "External id": 3717932,"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": 1625851575369.448, "dur": 18.144, + "args": { + "External id": 3717933,"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": 1625851575372.434, "dur": 14.743, + "args": { + "External id": 3717934,"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": 1625851575390.780, "dur": 18.325, + "args": { + "External id": 3717935,"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": 1625851575391.841, "dur": 3.302, + "args": { + "External id": 3717936,"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": 1625851575396.031, "dur": 12.802, + "args": { + "External id": 3717937,"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": 1625851575396.796, "dur": 11.639, + "args": { + "External id": 3717938,"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": 1625851575419.175, "dur": 0.743, + "args": { + "External id": 3717939,"Sequence number": 37295271, "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": 1625851575428.432, "dur": 11.556, + "args": { + "External id": 3717940,"Sequence number": 37295271, "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": 1625851575436.201, "dur": 2.182, + "args": { + "External id": 3717941,"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": 1625851575445.939, "dur": 6.986, + "args": { + "External id": 3717942,"Sequence number": 37295271, "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": 1625851575449.955, "dur": 1.267, + "args": { + "External id": 3717943,"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": 1625851575454.135, "dur": 3.406, + "args": { + "External id": 3717944,"Sequence number": 37295271, "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": 1625851575456.053, "dur": 0.714, + "args": { + "External id": 3717945,"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": 1625851575458.675, "dur": 3.305, + "args": { + "External id": 3717946,"Sequence number": 37295271, "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": 1625851575460.915, "dur": 0.569, + "args": { + "External id": 3717947,"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": 1625851575464.961, "dur": 2.975, + "args": { + "External id": 3717948,"Sequence number": 37295271, "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": 1625851575466.640, "dur": 0.745, + "args": { + "External id": 3717949,"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": 1625851575469.056, "dur": 3.468, + "args": { + "External id": 3717950,"Sequence number": 37295271, "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": 1625851575471.072, "dur": 0.780, + "args": { + "External id": 3717951,"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": 1625851575473.572, "dur": 3.533, + "args": { + "External id": 3717952,"Sequence number": 37295271, "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": 1625851575475.496, "dur": 1.115, + "args": { + "External id": 3717953,"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": 1625851575480.474, "dur": 5.827, + "args": { + "External id": 3717954,"Sequence number": 37295271, "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": 1625851575484.616, "dur": 0.857, + "args": { + "External id": 3717955,"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": 1625851575490.235, "dur": 3.006, + "args": { + "External id": 3717956,"Sequence number": 37295271, "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": 1625851575492.134, "dur": 0.569, + "args": { + "External id": 3717957,"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": 1625851575496.541, "dur": 9.075, + "args": { + "External id": 3717958,"Sequence number": 37295271, "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": 1625851575503.780, "dur": 0.674, + "args": { + "External id": 3717959,"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": 1625851575506.773, "dur": 2.858, + "args": { + "External id": 3717960,"Sequence number": 37295271, "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": 1625851575508.020, "dur": 1.059, + "args": { + "External id": 3717961,"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": 1625851575511.963, "dur": 6.574, + "args": { + "External id": 3717962,"Sequence number": 37295271, "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": 1625851575511.963, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1625851575516.089, "dur": 0.926, + "args": { + "External id": 3717963,"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": 1625851575522.041, "dur": 5.037, + "args": { + "External id": 3717964,"Sequence number": 37295272, "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": 1625851575522.041, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1625851575525.647, "dur": 0.735, + "args": { + "External id": 3717965,"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": 1625851575528.186, "dur": 5.630, + "args": { + "External id": 3717966,"Sequence number": 37295273, "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": 1625851575528.186, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1625851575532.247, "dur": 0.769, + "args": { + "External id": 3717967,"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": 1625851575535.089, "dur": 4.921, + "args": { + "External id": 3717968,"Sequence number": 37295274, "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": 1625851575535.089, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1625851575538.311, "dur": 1.000, + "args": { + "External id": 3717969,"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": 1625851575544.928, "dur": 46.050, + "args": { + "External id": 3717970,"Sequence number": 37295275, "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": 1625851575549.558, "dur": 41.190, + "args": { + "External id": 3717971,"Sequence number": 37295275, "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": 1625851575552.091, "dur": 7.642, + "args": { + "External id": 3717972,"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": 1625851575553.987, "dur": 5.111, + "args": { + "External id": 3717973,"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": 1625851575561.351, "dur": 28.948, + "args": { + "External id": 3717974,"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": 1625851575616.186, "dur": 4.425, + "args": { + "External id": 3717975,"Sequence number": 37295275, "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": 1625851575616.186, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1625851575622.869, "dur": 1.495, + "args": { + "External id": 3717976,"Sequence number": 37295276, "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": 1625851575651.240, "dur": 71525.733, + "args": { + "External id": 3717977,"Sequence number": 37295276, "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": 1625851575651.240, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::contiguous", "pid": 1336756, "tid": 1336756, + "ts": 1625851575665.824, "dur": 45.687, + "args": { + "External id": 3717978,"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": 1625851575666.579, "dur": 44.740, + "args": { + "External id": 3717979,"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": 1625851575668.294, "dur": 5.109, + "args": { + "External id": 3717980,"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": 1625851575669.504, "dur": 3.537, + "args": { + "External id": 3717981,"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": 1625851575674.142, "dur": 36.442, + "args": { + "External id": 3717982,"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": 1625851575730.972, "dur": 28.809, + "args": { + "External id": 3717983,"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": 1625851575732.194, "dur": 7.200, + "args": { + "External id": 3717984,"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": 1625851575734.581, "dur": 4.487, + "args": { + "External id": 3717985,"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": 1625851575740.555, "dur": 19.042, + "args": { + "External id": 3717986,"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": 1625851575741.489, "dur": 17.583, + "args": { + "External id": 3717987,"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": 1625851575763.337, "dur": 24.369, + "args": { + "External id": 3717988,"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": 1625851575764.751, "dur": 7.282, + "args": { + "External id": 3717989,"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": 1625851575768.756, "dur": 2.957, + "args": { + "External id": 3717990,"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": 1625851575772.560, "dur": 14.943, + "args": { + "External id": 3717991,"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": 1625851575773.385, "dur": 13.743, + "args": { + "External id": 3717992,"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": 1625851575792.133, "dur": 29.094, + "args": { + "External id": 3717993,"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": 1625851575793.591, "dur": 3.399, + "args": { + "External id": 3717994,"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": 1625851575805.858, "dur": 15.092, + "args": { + "External id": 3717995,"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": 1625851575806.481, "dur": 14.150, + "args": { + "External id": 3717996,"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": 1625851575830.185, "dur": 31.173, + "args": { + "External id": 3717997,"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": 1625851575866.149, "dur": 63.747, + "args": { + "External id": 3717998,"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": 1625851575869.770, "dur": 59.681, + "args": { + "External id": 3717999,"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": 1625851575876.637, "dur": 0.991, + "args": { + "External id": 3718000,"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": 1625851575879.638, "dur": 28.474, + "args": { + "External id": 3718001,"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": 1625851575881.607, "dur": 26.258, + "args": { + "External id": 3718002,"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": 1625851575884.182, "dur": 3.033, + "args": { + "External id": 3718003,"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": 1625851575888.082, "dur": 19.302, + "args": { + "External id": 3718004,"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": 1625851575935.542, "dur": 65181.192, + "args": { + "External id": 3718005,"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": 1625851575937.680, "dur": 65177.769, + "args": { + "External id": 3718006,"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": 1625851641129.005, "dur": 9.501, + "args": { + "External id": 3718007,"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": 1625851641135.068, "dur": 1.296, + "args": { + "External id": 3718008,"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": 1625851641145.902, "dur": 108.644, + "args": { + "External id": 3718009,"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": 1625851641147.689, "dur": 5.801, + "args": { + "External id": 3718010,"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": 1625851641149.662, "dur": 2.816, + "args": { + "External id": 3718011,"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": 1625851641151.473, "dur": 0.736, + "args": { + "External id": 3718012,"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": 1625851641154.698, "dur": 99.121, + "args": { + "External id": 3718013,"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": 1625851641156.491, "dur": 96.539, + "args": { + "External id": 3718014,"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": 1625851641258.072, "dur": 4.856, + "args": { + "External id": 3718015,"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": 1625851641260.257, "dur": 1.027, + "args": { + "External id": 3718016,"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": 1625851641273.741, "dur": 3.645, + "args": { + "External id": 3718017,"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": 1625851641288.953, "dur": 6.961, + "args": { + "External id": 3718018,"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": 1625851641291.338, "dur": 4.295, + "args": { + "External id": 3718019,"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": 1625851641450.469, "dur": 285.229, + "args": { + "External id": 3718020,"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": 1625851641456.279, "dur": 2.457, + "args": { + "External id": 3718021,"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": 1625851641463.893, "dur": 271.284, + "args": { + "External id": 3718022,"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": 1625851641466.574, "dur": 0.699, + "args": { + "External id": 3718023,"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": 1625851641470.163, "dur": 32.259, + "args": { + "External id": 3718024,"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": 1625851641505.550, "dur": 6.276, + "args": { + "External id": 3718025,"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": 1625851641510.466, "dur": 0.961, + "args": { + "External id": 3718026,"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": 1625851641514.389, "dur": 31.289, + "args": { + "External id": 3718027,"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": 1625851641515.870, "dur": 1.827, + "args": { + "External id": 3718028,"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": 1625851641520.214, "dur": 25.127, + "args": { + "External id": 3718029,"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": 1625851641525.210, "dur": 3.708, + "args": { + "External id": 3718030,"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": 1625851641550.588, "dur": 27.598, + "args": { + "External id": 3718031,"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": 1625851641581.058, "dur": 23.955, + "args": { + "External id": 3718032,"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": 1625851641609.244, "dur": 18.873, + "args": { + "External id": 3718033,"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": 1625851641630.543, "dur": 20.485, + "args": { + "External id": 3718034,"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": 1625851641653.776, "dur": 40.594, + "args": { + "External id": 3718035,"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": 1625851641656.094, "dur": 2.388, + "args": { + "External id": 3718036,"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": 1625851641660.581, "dur": 0.914, + "args": { + "External id": 3718037,"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": 1625851641700.559, "dur": 19.063, + "args": { + "External id": 3718038,"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": 1625851641721.717, "dur": 12.169, + "args": { + "External id": 3718039,"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": 1625851641744.151, "dur": 2.521, + "args": { + "External id": 3718040,"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": 1625851641753.629, "dur": 4.616, + "args": { + "External id": 3718041,"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": 1625851641756.265, "dur": 1.058, + "args": { + "External id": 3718042,"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": 1625851641850.750, "dur": 74.987, + "args": { + "External id": 3718043,"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": 1625851641931.077, "dur": 4.975, + "args": { + "External id": 3718044,"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": 1625851641933.732, "dur": 1.134, + "args": { + "External id": 3718045,"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": 1625851641939.915, "dur": 32.629, + "args": { + "External id": 3718046,"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": 1625851641977.672, "dur": 40.989, + "args": { + "External id": 3718047,"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": 1625851641979.554, "dur": 38.022, + "args": { + "External id": 3718048,"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": 1625851642015.037, "dur": 1.975, + "args": { + "External id": 3718049,"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": 1625851642024.503, "dur": 57.575, + "args": { + "External id": 3718050,"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": 1625851642025.902, "dur": 55.492, + "args": { + "External id": 3718051,"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": 1625851642088.235, "dur": 19.636, + "args": { + "External id": 3718052,"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": 1625851642117.160, "dur": 4.560, + "args": { + "External id": 3718053,"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": 1625851642119.872, "dur": 0.908, + "args": { + "External id": 3718054,"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": 1625851642126.259, "dur": 50.652, + "args": { + "External id": 3718055,"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": 1625851642127.252, "dur": 4.224, + "args": { + "External id": 3718056,"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": 1625851642128.375, "dur": 2.599, + "args": { + "External id": 3718057,"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": 1625851642130.178, "dur": 0.671, + "args": { + "External id": 3718058,"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": 1625851642134.231, "dur": 42.349, + "args": { + "External id": 3718059,"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": 1625851642134.778, "dur": 41.249, + "args": { + "External id": 3718060,"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": 1625851642181.504, "dur": 3.900, + "args": { + "External id": 3718061,"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": 1625851642183.476, "dur": 0.793, + "args": { + "External id": 3718062,"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": 1625851642191.953, "dur": 1.608, + "args": { + "External id": 3718063,"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": 1625851642202.207, "dur": 11.501, + "args": { + "External id": 3718064,"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": 1625851642206.500, "dur": 6.884, + "args": { + "External id": 3718065,"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": 1625851642314.940, "dur": 200.185, + "args": { + "External id": 3718066,"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": 1625851642316.950, "dur": 2.091, + "args": { + "External id": 3718067,"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": 1625851642320.744, "dur": 193.962, + "args": { + "External id": 3718068,"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": 1625851642322.200, "dur": 0.242, + "args": { + "External id": 3718069,"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": 1625851642323.755, "dur": 25.596, + "args": { + "External id": 3718070,"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": 1625851642351.266, "dur": 3.819, + "args": { + "External id": 3718071,"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": 1625851642353.760, "dur": 1.091, + "args": { + "External id": 3718072,"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": 1625851642358.599, "dur": 26.281, + "args": { + "External id": 3718073,"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": 1625851642360.173, "dur": 1.900, + "args": { + "External id": 3718074,"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": 1625851642363.321, "dur": 21.249, + "args": { + "External id": 3718075,"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": 1625851642368.434, "dur": 2.886, + "args": { + "External id": 3718076,"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": 1625851642386.533, "dur": 23.369, + "args": { + "External id": 3718077,"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": 1625851642411.583, "dur": 14.969, + "args": { + "External id": 3718078,"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": 1625851642429.901, "dur": 15.837, + "args": { + "External id": 3718079,"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": 1625851642447.161, "dur": 13.999, + "args": { + "External id": 3718080,"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": 1625851642462.610, "dur": 23.121, + "args": { + "External id": 3718081,"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": 1625851642466.928, "dur": 1.578, + "args": { + "External id": 3718082,"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": 1625851642470.245, "dur": 0.807, + "args": { + "External id": 3718083,"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": 1625851642487.025, "dur": 13.420, + "args": { + "External id": 3718084,"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": 1625851642501.619, "dur": 11.893, + "args": { + "External id": 3718085,"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": 1625851642521.623, "dur": 2.265, + "args": { + "External id": 3718086,"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": 1625851642532.235, "dur": 3.670, + "args": { + "External id": 3718087,"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": 1625851642534.767, "dur": 0.388, + "args": { + "External id": 3718088,"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": 1625851642603.591, "dur": 51.448, + "args": { + "External id": 3718089,"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": 1625851642662.315, "dur": 4.459, + "args": { + "External id": 3718090,"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": 1625851642664.567, "dur": 1.356, + "args": { + "External id": 3718091,"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": 1625851642668.477, "dur": 43.485, + "args": { + "External id": 3718092,"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": 1625851642718.661, "dur": 5.553, + "args": { + "External id": 3718093,"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": 1625851642719.921, "dur": 3.409, + "args": { + "External id": 3718094,"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": 1625851642721.865, "dur": 1.275, + "args": { + "External id": 3718095,"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": 1625851642729.423, "dur": 46.567, + "args": { + "External id": 3718096,"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": 1625851642731.226, "dur": 44.233, + "args": { + "External id": 3718097,"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": 1625851642779.991, "dur": 19.559, + "args": { + "External id": 3718098,"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": 1625851642805.777, "dur": 3.983, + "args": { + "External id": 3718099,"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": 1625851642808.184, "dur": 0.819, + "args": { + "External id": 3718100,"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": 1625851642813.861, "dur": 51.317, + "args": { + "External id": 3718101,"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": 1625851642814.803, "dur": 8.303, + "args": { + "External id": 3718102,"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": 1625851642817.978, "dur": 4.582, + "args": { + "External id": 3718103,"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": 1625851642819.151, "dur": 3.180, + "args": { + "External id": 3718104,"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": 1625851642824.030, "dur": 40.746, + "args": { + "External id": 3718105,"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": 1625851642824.551, "dur": 39.556, + "args": { + "External id": 3718106,"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": 1625851642869.739, "dur": 3.831, + "args": { + "External id": 3718107,"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": 1625851642871.867, "dur": 0.699, + "args": { + "External id": 3718108,"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": 1625851642879.555, "dur": 1.582, + "args": { + "External id": 3718109,"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": 1625851642890.776, "dur": 6.369, + "args": { + "External id": 3718110,"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": 1625851642892.431, "dur": 4.447, + "args": { + "External id": 3718111,"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": 1625851643022.979, "dur": 307.802, + "args": { + "External id": 3718112,"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": 1625851643025.811, "dur": 3.701, + "args": { + "External id": 3718113,"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": 1625851643031.657, "dur": 298.722, + "args": { + "External id": 3718114,"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": 1625851643033.150, "dur": 0.292, + "args": { + "External id": 3718115,"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": 1625851643036.863, "dur": 27.354, + "args": { + "External id": 3718116,"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": 1625851643066.149, "dur": 3.620, + "args": { + "External id": 3718117,"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": 1625851643068.173, "dur": 1.231, + "args": { + "External id": 3718118,"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": 1625851643073.237, "dur": 27.171, + "args": { + "External id": 3718119,"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": 1625851643074.445, "dur": 3.838, + "args": { + "External id": 3718120,"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": 1625851643079.601, "dur": 20.551, + "args": { + "External id": 3718121,"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": 1625851643082.770, "dur": 3.331, + "args": { + "External id": 3718122,"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": 1625851643102.093, "dur": 38.554, + "args": { + "External id": 3718123,"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": 1625851643142.468, "dur": 39.655, + "args": { + "External id": 3718124,"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": 1625851643184.966, "dur": 38.403, + "args": { + "External id": 3718125,"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": 1625851643224.930, "dur": 36.759, + "args": { + "External id": 3718126,"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": 1625851643263.397, "dur": 28.907, + "args": { + "External id": 3718127,"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": 1625851643267.669, "dur": 1.653, + "args": { + "External id": 3718128,"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": 1625851643271.399, "dur": 1.130, + "args": { + "External id": 3718129,"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": 1625851643293.733, "dur": 20.193, + "args": { + "External id": 3718130,"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": 1625851643314.988, "dur": 14.405, + "args": { + "External id": 3718131,"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": 1625851643337.802, "dur": 2.249, + "args": { + "External id": 3718132,"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": 1625851643349.973, "dur": 3.513, + "args": { + "External id": 3718133,"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": 1625851643352.257, "dur": 0.459, + "args": { + "External id": 3718134,"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": 1625851643432.675, "dur": 61.802, + "args": { + "External id": 3718135,"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": 1625851643499.394, "dur": 4.587, + "args": { + "External id": 3718136,"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": 1625851643501.929, "dur": 1.111, + "args": { + "External id": 3718137,"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": 1625851643505.715, "dur": 24.547, + "args": { + "External id": 3718138,"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": 1625851643534.817, "dur": 9.917, + "args": { + "External id": 3718139,"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": 1625851643536.337, "dur": 7.641, + "args": { + "External id": 3718140,"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": 1625851643541.000, "dur": 2.743, + "args": { + "External id": 3718141,"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": 1625851643547.475, "dur": 43.227, + "args": { + "External id": 3718142,"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": 1625851643548.919, "dur": 41.230, + "args": { + "External id": 3718143,"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": 1625851643594.757, "dur": 16.447, + "args": { + "External id": 3718144,"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": 1625851643650.868, "dur": 4.199, + "args": { + "External id": 3718145,"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": 1625851643653.386, "dur": 0.764, + "args": { + "External id": 3718146,"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": 1625851643659.188, "dur": 73.978, + "args": { + "External id": 3718147,"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": 1625851643662.261, "dur": 3.981, + "args": { + "External id": 3718148,"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": 1625851643662.956, "dur": 2.404, + "args": { + "External id": 3718149,"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": 1625851643664.222, "dur": 0.779, + "args": { + "External id": 3718150,"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": 1625851643667.013, "dur": 65.685, + "args": { + "External id": 3718151,"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": 1625851643667.431, "dur": 64.272, + "args": { + "External id": 3718152,"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": 1625851643739.490, "dur": 5.060, + "args": { + "External id": 3718153,"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": 1625851643742.316, "dur": 0.949, + "args": { + "External id": 3718154,"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": 1625851643753.621, "dur": 1.597, + "args": { + "External id": 3718155,"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": 1625851643763.502, "dur": 8.687, + "args": { + "External id": 3718156,"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": 1625851643765.203, "dur": 6.713, + "args": { + "External id": 3718157,"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": 1625851643865.667, "dur": 244.960, + "args": { + "External id": 3718158,"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": 1625851643867.642, "dur": 2.481, + "args": { + "External id": 3718159,"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": 1625851643874.492, "dur": 235.646, + "args": { + "External id": 3718160,"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": 1625851643876.026, "dur": 0.317, + "args": { + "External id": 3718161,"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": 1625851643877.254, "dur": 27.123, + "args": { + "External id": 3718162,"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": 1625851643906.135, "dur": 3.123, + "args": { + "External id": 3718163,"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": 1625851643908.242, "dur": 0.748, + "args": { + "External id": 3718164,"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": 1625851643910.047, "dur": 24.294, + "args": { + "External id": 3718165,"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": 1625851643910.955, "dur": 1.545, + "args": { + "External id": 3718166,"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": 1625851643913.645, "dur": 20.423, + "args": { + "External id": 3718167,"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": 1625851643918.702, "dur": 2.397, + "args": { + "External id": 3718168,"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": 1625851643938.200, "dur": 22.660, + "args": { + "External id": 3718169,"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": 1625851643962.351, "dur": 14.837, + "args": { + "External id": 3718170,"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": 1625851643980.509, "dur": 54.886, + "args": { + "External id": 3718171,"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": 1625851644037.677, "dur": 14.821, + "args": { + "External id": 3718172,"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": 1625851644054.637, "dur": 22.531, + "args": { + "External id": 3718173,"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": 1625851644056.514, "dur": 1.972, + "args": { + "External id": 3718174,"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": 1625851644061.374, "dur": 0.906, + "args": { + "External id": 3718175,"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": 1625851644078.762, "dur": 13.784, + "args": { + "External id": 3718176,"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": 1625851644096.158, "dur": 12.495, + "args": { + "External id": 3718177,"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": 1625851644118.243, "dur": 2.121, + "args": { + "External id": 3718178,"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": 1625851644130.271, "dur": 3.361, + "args": { + "External id": 3718179,"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": 1625851644132.499, "dur": 0.335, + "args": { + "External id": 3718180,"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": 1625851644203.173, "dur": 59.559, + "args": { + "External id": 3718181,"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": 1625851644267.493, "dur": 5.046, + "args": { + "External id": 3718182,"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": 1625851644270.176, "dur": 1.499, + "args": { + "External id": 3718183,"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": 1625851644274.491, "dur": 27.154, + "args": { + "External id": 3718184,"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": 1625851644309.031, "dur": 5.037, + "args": { + "External id": 3718185,"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": 1625851644310.594, "dur": 2.642, + "args": { + "External id": 3718186,"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": 1625851644312.284, "dur": 0.770, + "args": { + "External id": 3718187,"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": 1625851644316.800, "dur": 39.833, + "args": { + "External id": 3718188,"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": 1625851644317.879, "dur": 38.108, + "args": { + "External id": 3718189,"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": 1625851644360.459, "dur": 15.444, + "args": { + "External id": 3718190,"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": 1625851644381.305, "dur": 6.181, + "args": { + "External id": 3718191,"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": 1625851644385.814, "dur": 0.921, + "args": { + "External id": 3718192,"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": 1625851644391.381, "dur": 53.093, + "args": { + "External id": 3718193,"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": 1625851644392.051, "dur": 5.822, + "args": { + "External id": 3718194,"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": 1625851644392.780, "dur": 4.468, + "args": { + "External id": 3718195,"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": 1625851644394.161, "dur": 2.916, + "args": { + "External id": 3718196,"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": 1625851644398.381, "dur": 45.740, + "args": { + "External id": 3718197,"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": 1625851644401.430, "dur": 42.206, + "args": { + "External id": 3718198,"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": 1625851644448.269, "dur": 4.144, + "args": { + "External id": 3718199,"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": 1625851644450.561, "dur": 0.811, + "args": { + "External id": 3718200,"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": 1625851644457.860, "dur": 1.582, + "args": { + "External id": 3718201,"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": 1625851644466.841, "dur": 5.796, + "args": { + "External id": 3718202,"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": 1625851644468.549, "dur": 3.807, + "args": { + "External id": 3718203,"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": 1625851644556.800, "dur": 210.897, + "args": { + "External id": 3718204,"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": 1625851644559.207, "dur": 2.434, + "args": { + "External id": 3718205,"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": 1625851644563.129, "dur": 204.161, + "args": { + "External id": 3718206,"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": 1625851644564.255, "dur": 0.268, + "args": { + "External id": 3718207,"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": 1625851644567.628, "dur": 21.099, + "args": { + "External id": 3718208,"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": 1625851644590.160, "dur": 3.448, + "args": { + "External id": 3718209,"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": 1625851644592.080, "dur": 1.315, + "args": { + "External id": 3718210,"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": 1625851644594.420, "dur": 26.846, + "args": { + "External id": 3718211,"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": 1625851644595.832, "dur": 3.516, + "args": { + "External id": 3718212,"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": 1625851644600.743, "dur": 20.249, + "args": { + "External id": 3718213,"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": 1625851644605.053, "dur": 2.348, + "args": { + "External id": 3718214,"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": 1625851644622.706, "dur": 20.317, + "args": { + "External id": 3718215,"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": 1625851644644.217, "dur": 14.649, + "args": { + "External id": 3718216,"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": 1625851644661.580, "dur": 14.080, + "args": { + "External id": 3718217,"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": 1625851644692.681, "dur": 15.517, + "args": { + "External id": 3718218,"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": 1625851644709.832, "dur": 26.091, + "args": { + "External id": 3718219,"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": 1625851644711.954, "dur": 1.636, + "args": { + "External id": 3718220,"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": 1625851644715.497, "dur": 0.780, + "args": { + "External id": 3718221,"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": 1625851644740.304, "dur": 13.654, + "args": { + "External id": 3718222,"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": 1625851644754.948, "dur": 11.190, + "args": { + "External id": 3718223,"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": 1625851644774.674, "dur": 2.103, + "args": { + "External id": 3718224,"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": 1625851644784.830, "dur": 3.353, + "args": { + "External id": 3718225,"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": 1625851644786.926, "dur": 0.497, + "args": { + "External id": 3718226,"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": 1625851644854.239, "dur": 54.003, + "args": { + "External id": 3718227,"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": 1625851644912.709, "dur": 4.429, + "args": { + "External id": 3718228,"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": 1625851644915.273, "dur": 1.024, + "args": { + "External id": 3718229,"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": 1625851644921.084, "dur": 22.272, + "args": { + "External id": 3718230,"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": 1625851644947.523, "dur": 6.901, + "args": { + "External id": 3718231,"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": 1625851644948.862, "dur": 5.000, + "args": { + "External id": 3718232,"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": 1625851644950.584, "dur": 3.102, + "args": { + "External id": 3718233,"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": 1625851644956.904, "dur": 76.404, + "args": { + "External id": 3718234,"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": 1625851644957.997, "dur": 74.231, + "args": { + "External id": 3718235,"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": 1625851645039.044, "dur": 17.670, + "args": { + "External id": 3718236,"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": 1625851645065.311, "dur": 4.678, + "args": { + "External id": 3718237,"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": 1625851645067.826, "dur": 1.037, + "args": { + "External id": 3718238,"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": 1625851645074.147, "dur": 55.405, + "args": { + "External id": 3718239,"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": 1625851645075.128, "dur": 3.878, + "args": { + "External id": 3718240,"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": 1625851645076.164, "dur": 2.346, + "args": { + "External id": 3718241,"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": 1625851645077.524, "dur": 0.843, + "args": { + "External id": 3718242,"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": 1625851645082.172, "dur": 47.063, + "args": { + "External id": 3718243,"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": 1625851645082.698, "dur": 46.063, + "args": { + "External id": 3718244,"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": 1625851645133.228, "dur": 4.310, + "args": { + "External id": 3718245,"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": 1625851645135.729, "dur": 0.847, + "args": { + "External id": 3718246,"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": 1625851645142.812, "dur": 1.727, + "args": { + "External id": 3718247,"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": 1625851645152.016, "dur": 8.814, + "args": { + "External id": 3718248,"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": 1625851645155.869, "dur": 4.696, + "args": { + "External id": 3718249,"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": 1625851645252.700, "dur": 199.270, + "args": { + "External id": 3718250,"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": 1625851645254.772, "dur": 2.297, + "args": { + "External id": 3718251,"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": 1625851645260.762, "dur": 190.755, + "args": { + "External id": 3718252,"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": 1625851645261.926, "dur": 0.497, + "args": { + "External id": 3718253,"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": 1625851645263.622, "dur": 22.300, + "args": { + "External id": 3718254,"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": 1625851645287.476, "dur": 12.040, + "args": { + "External id": 3718255,"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": 1625851645296.651, "dur": 2.550, + "args": { + "External id": 3718256,"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": 1625851645300.322, "dur": 24.332, + "args": { + "External id": 3718257,"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": 1625851645304.066, "dur": 1.655, + "args": { + "External id": 3718258,"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": 1625851645306.746, "dur": 17.568, + "args": { + "External id": 3718259,"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": 1625851645308.997, "dur": 2.633, + "args": { + "External id": 3718260,"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": 1625851645326.220, "dur": 21.468, + "args": { + "External id": 3718261,"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": 1625851645348.954, "dur": 13.214, + "args": { + "External id": 3718262,"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": 1625851645364.429, "dur": 14.681, + "args": { + "External id": 3718263,"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": 1625851645380.477, "dur": 14.163, + "args": { + "External id": 3718264,"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": 1625851645398.453, "dur": 24.958, + "args": { + "External id": 3718265,"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": 1625851645400.316, "dur": 2.101, + "args": { + "External id": 3718266,"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": 1625851645406.215, "dur": 2.443, + "args": { + "External id": 3718267,"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": 1625851645424.731, "dur": 12.998, + "args": { + "External id": 3718268,"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": 1625851645438.652, "dur": 11.846, + "args": { + "External id": 3718269,"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": 1625851645457.849, "dur": 1.890, + "args": { + "External id": 3718270,"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": 1625851645467.951, "dur": 3.083, + "args": { + "External id": 3718271,"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": 1625851645469.894, "dur": 0.427, + "args": { + "External id": 3718272,"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": 1625851645530.453, "dur": 50.315, + "args": { + "External id": 3718273,"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": 1625851645587.740, "dur": 4.318, + "args": { + "External id": 3718274,"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": 1625851645590.202, "dur": 0.953, + "args": { + "External id": 3718275,"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": 1625851645593.559, "dur": 23.416, + "args": { + "External id": 3718276,"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": 1625851645620.977, "dur": 4.874, + "args": { + "External id": 3718277,"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": 1625851645621.987, "dur": 3.269, + "args": { + "External id": 3718278,"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": 1625851645623.436, "dur": 1.641, + "args": { + "External id": 3718279,"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": 1625851645630.468, "dur": 39.300, + "args": { + "External id": 3718280,"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": 1625851645631.501, "dur": 37.748, + "args": { + "External id": 3718281,"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": 1625851645673.103, "dur": 36.232, + "args": { + "External id": 3718282,"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": 1625851645716.990, "dur": 4.529, + "args": { + "External id": 3718283,"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": 1625851645719.498, "dur": 0.879, + "args": { + "External id": 3718284,"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": 1625851645725.911, "dur": 55.209, + "args": { + "External id": 3718285,"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": 1625851645726.918, "dur": 6.732, + "args": { + "External id": 3718286,"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": 1625851645730.652, "dur": 2.418, + "args": { + "External id": 3718287,"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": 1625851645732.264, "dur": 0.663, + "args": { + "External id": 3718288,"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": 1625851645734.168, "dur": 46.668, + "args": { + "External id": 3718289,"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": 1625851645735.146, "dur": 45.164, + "args": { + "External id": 3718290,"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": 1625851645785.380, "dur": 3.686, + "args": { + "External id": 3718291,"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": 1625851645787.559, "dur": 0.608, + "args": { + "External id": 3718292,"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": 1625851645794.599, "dur": 1.475, + "args": { + "External id": 3718293,"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": 1625851645806.259, "dur": 5.913, + "args": { + "External id": 3718294,"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": 1625851645807.875, "dur": 4.030, + "args": { + "External id": 3718295,"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": 1625851645891.142, "dur": 240.194, + "args": { + "External id": 3718296,"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": 1625851645895.431, "dur": 2.100, + "args": { + "External id": 3718297,"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": 1625851645898.767, "dur": 231.882, + "args": { + "External id": 3718298,"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": 1625851645900.009, "dur": 0.334, + "args": { + "External id": 3718299,"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": 1625851645901.294, "dur": 21.073, + "args": { + "External id": 3718300,"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": 1625851645925.855, "dur": 5.081, + "args": { + "External id": 3718301,"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": 1625851645929.877, "dur": 0.787, + "args": { + "External id": 3718302,"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": 1625851645931.698, "dur": 22.957, + "args": { + "External id": 3718303,"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": 1625851645933.124, "dur": 1.789, + "args": { + "External id": 3718304,"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": 1625851645936.143, "dur": 18.241, + "args": { + "External id": 3718305,"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": 1625851645938.549, "dur": 2.316, + "args": { + "External id": 3718306,"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": 1625851645956.020, "dur": 19.989, + "args": { + "External id": 3718307,"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": 1625851645977.500, "dur": 65.803, + "args": { + "External id": 3718308,"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": 1625851646047.671, "dur": 15.258, + "args": { + "External id": 3718309,"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": 1625851646064.195, "dur": 13.455, + "args": { + "External id": 3718310,"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": 1625851646081.856, "dur": 21.388, + "args": { + "External id": 3718311,"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": 1625851646084.081, "dur": 1.606, + "args": { + "External id": 3718312,"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": 1625851646087.483, "dur": 1.429, + "args": { + "External id": 3718313,"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": 1625851646104.659, "dur": 12.722, + "args": { + "External id": 3718314,"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": 1625851646118.536, "dur": 11.287, + "args": { + "External id": 3718315,"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": 1625851646138.748, "dur": 2.050, + "args": { + "External id": 3718316,"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": 1625851646149.421, "dur": 3.347, + "args": { + "External id": 3718317,"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": 1625851646151.541, "dur": 0.494, + "args": { + "External id": 3718318,"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": 1625851646219.955, "dur": 55.947, + "args": { + "External id": 3718319,"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": 1625851646280.508, "dur": 4.745, + "args": { + "External id": 3718320,"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": 1625851646283.565, "dur": 0.829, + "args": { + "External id": 3718321,"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": 1625851646286.677, "dur": 23.796, + "args": { + "External id": 3718322,"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": 1625851646314.396, "dur": 7.703, + "args": { + "External id": 3718323,"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": 1625851646315.796, "dur": 5.476, + "args": { + "External id": 3718324,"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": 1625851646319.601, "dur": 1.476, + "args": { + "External id": 3718325,"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": 1625851646324.507, "dur": 40.269, + "args": { + "External id": 3718326,"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": 1625851646325.481, "dur": 38.755, + "args": { + "External id": 3718327,"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": 1625851646368.215, "dur": 15.527, + "args": { + "External id": 3718328,"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": 1625851646388.652, "dur": 4.223, + "args": { + "External id": 3718329,"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": 1625851646390.862, "dur": 1.277, + "args": { + "External id": 3718330,"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": 1625851646396.609, "dur": 49.024, + "args": { + "External id": 3718331,"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": 1625851646399.848, "dur": 3.643, + "args": { + "External id": 3718332,"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": 1625851646400.619, "dur": 2.325, + "args": { + "External id": 3718333,"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": 1625851646401.903, "dur": 0.912, + "args": { + "External id": 3718334,"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": 1625851646404.078, "dur": 41.179, + "args": { + "External id": 3718335,"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": 1625851646404.902, "dur": 39.786, + "args": { + "External id": 3718336,"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": 1625851646449.436, "dur": 4.275, + "args": { + "External id": 3718337,"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": 1625851646451.787, "dur": 1.015, + "args": { + "External id": 3718338,"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": 1625851646460.445, "dur": 1.340, + "args": { + "External id": 3718339,"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": 1625851646468.301, "dur": 8.249, + "args": { + "External id": 3718340,"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": 1625851646469.965, "dur": 6.305, + "args": { + "External id": 3718341,"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": 1625851646550.641, "dur": 211.023, + "args": { + "External id": 3718342,"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": 1625851646552.561, "dur": 2.241, + "args": { + "External id": 3718343,"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": 1625851646558.569, "dur": 202.681, + "args": { + "External id": 3718344,"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": 1625851646560.230, "dur": 0.236, + "args": { + "External id": 3718345,"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": 1625851646561.376, "dur": 23.342, + "args": { + "External id": 3718346,"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": 1625851646586.049, "dur": 2.984, + "args": { + "External id": 3718347,"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": 1625851646587.638, "dur": 1.186, + "args": { + "External id": 3718348,"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": 1625851646589.925, "dur": 24.923, + "args": { + "External id": 3718349,"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": 1625851646591.274, "dur": 1.935, + "args": { + "External id": 3718350,"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": 1625851646594.304, "dur": 20.250, + "args": { + "External id": 3718351,"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": 1625851646599.371, "dur": 2.394, + "args": { + "External id": 3718352,"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": 1625851646618.682, "dur": 22.174, + "args": { + "External id": 3718353,"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": 1625851646642.340, "dur": 13.475, + "args": { + "External id": 3718354,"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": 1625851646658.222, "dur": 14.297, + "args": { + "External id": 3718355,"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": 1625851646673.696, "dur": 31.578, + "args": { + "External id": 3718356,"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": 1625851646707.788, "dur": 22.297, + "args": { + "External id": 3718357,"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": 1625851646709.626, "dur": 2.202, + "args": { + "External id": 3718358,"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": 1625851646713.769, "dur": 0.889, + "args": { + "External id": 3718359,"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": 1625851646731.499, "dur": 13.388, + "args": { + "External id": 3718360,"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": 1625851646748.591, "dur": 11.771, + "args": { + "External id": 3718361,"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": 1625851646768.370, "dur": 2.333, + "args": { + "External id": 3718362,"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": 1625851646779.009, "dur": 3.181, + "args": { + "External id": 3718363,"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": 1625851646780.946, "dur": 0.577, + "args": { + "External id": 3718364,"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": 1625851646846.784, "dur": 56.566, + "args": { + "External id": 3718365,"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": 1625851646908.336, "dur": 5.317, + "args": { + "External id": 3718366,"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": 1625851646911.043, "dur": 1.604, + "args": { + "External id": 3718367,"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": 1625851646914.932, "dur": 23.468, + "args": { + "External id": 3718368,"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": 1625851646945.382, "dur": 5.123, + "args": { + "External id": 3718369,"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": 1625851646946.885, "dur": 3.059, + "args": { + "External id": 3718370,"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": 1625851646948.738, "dur": 1.073, + "args": { + "External id": 3718371,"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": 1625851646953.044, "dur": 77.652, + "args": { + "External id": 3718372,"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": 1625851646954.491, "dur": 75.072, + "args": { + "External id": 3718373,"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": 1625851647036.179, "dur": 17.129, + "args": { + "External id": 3718374,"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": 1625851647058.402, "dur": 31.820, + "args": { + "External id": 3718375,"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": 1625851647063.595, "dur": 26.187, + "args": { + "External id": 3718376,"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": 1625851647071.368, "dur": 1.108, + "args": { + "External id": 3718377,"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": 1625851647095.907, "dur": 29.691, + "args": { + "External id": 3718378,"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": 1625851647097.759, "dur": 27.633, + "args": { + "External id": 3718379,"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": 1625851647102.638, "dur": 4.118, + "args": { + "External id": 3718380,"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": 1625851647107.963, "dur": 16.933, + "args": { + "External id": 3718381,"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": 1625851647142.190, "dur": 5.677, + "args": { + "External id": 3718382,"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": 1625851647144.451, "dur": 3.142, + "args": { + "External id": 3718383,"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": 1625851647148.975, "dur": 4.025, + "args": { + "External id": 3718384,"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": 1625851647151.928, "dur": 0.985, + "args": { + "External id": 3718385,"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": 1625851647196.242, "dur": 23.765, + "args": { + "External id": 3718386,"Sequence number": 37295277, "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": 1625851647196.242, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1336756, + "ts": 1625851647226.463, "dur": 5.771, + "args": { + "External id": 3718387,"Sequence number": 37295278, "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": 1625851647230.005, "dur": 1.017, + "args": { + "External id": 3718388,"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": 1625851647234.691, "dur": 6.089, + "args": { + "External id": 3718389,"Sequence number": 37295278, "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": 1625851647238.817, "dur": 0.797, + "args": { + "External id": 3718390,"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": 1625851647244.385, "dur": 3.587, + "args": { + "External id": 3718391,"Sequence number": 37295278, "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": 1625851647246.321, "dur": 1.110, + "args": { + "External id": 3718392,"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": 1625851647252.359, "dur": 6.189, + "args": { + "External id": 3718393,"Sequence number": 37295278, "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": 1625851647252.359, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1625851647255.913, "dur": 1.211, + "args": { + "External id": 3718394,"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": 1625851647259.452, "dur": 7.776, + "args": { + "External id": 3718395,"Sequence number": 37295279, "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": 1625851647259.452, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1625851647265.622, "dur": 0.860, + "args": { + "External id": 3718396,"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": 1625851647268.177, "dur": 5.181, + "args": { + "External id": 3718397,"Sequence number": 37295280, "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": 1625851647268.177, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1625851647271.751, "dur": 0.622, + "args": { + "External id": 3718398,"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": 1625851647274.398, "dur": 5.508, + "args": { + "External id": 3718399,"Sequence number": 37295281, "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": 1625851647274.398, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1625851647277.614, "dur": 1.532, + "args": { + "External id": 3718400,"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": 1625851647283.652, "dur": 31.365, + "args": { + "External id": 3718401,"Sequence number": 37295282, "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": 1625851647285.071, "dur": 29.687, + "args": { + "External id": 3718402,"Sequence number": 37295282, "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": 1625851647287.688, "dur": 8.028, + "args": { + "External id": 3718403,"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": 1625851647292.150, "dur": 2.965, + "args": { + "External id": 3718404,"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": 1625851647296.549, "dur": 17.801, + "args": { + "External id": 3718405,"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": 1625851647339.612, "dur": 4.428, + "args": { + "External id": 3718406,"Sequence number": 37295282, "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": 1625851647339.612, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1625851647346.295, "dur": 1.105, + "args": { + "External id": 3718407,"Sequence number": 37295283, "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": 1625851647379.237, "dur": 42097.576, + "args": { + "External id": 3718408,"Sequence number": 37295283, "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": 1625851647379.237, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::contiguous", "pid": 1336756, "tid": 1336756, + "ts": 1625851647393.984, "dur": 31.367, + "args": { + "External id": 3718409,"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": 1625851647394.774, "dur": 30.303, + "args": { + "External id": 3718410,"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": 1625851647396.406, "dur": 10.181, + "args": { + "External id": 3718411,"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": 1625851647402.663, "dur": 3.502, + "args": { + "External id": 3718412,"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": 1625851647407.263, "dur": 17.394, + "args": { + "External id": 3718413,"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": 1625851647440.539, "dur": 25.102, + "args": { + "External id": 3718414,"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": 1625851647441.808, "dur": 6.017, + "args": { + "External id": 3718415,"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": 1625851647443.831, "dur": 3.701, + "args": { + "External id": 3718416,"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": 1625851647449.032, "dur": 16.402, + "args": { + "External id": 3718417,"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": 1625851647450.522, "dur": 14.479, + "args": { + "External id": 3718418,"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": 1625851647469.180, "dur": 23.434, + "args": { + "External id": 3718419,"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": 1625851647469.860, "dur": 4.855, + "args": { + "External id": 3718420,"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": 1625851647471.349, "dur": 3.104, + "args": { + "External id": 3718421,"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": 1625851647475.267, "dur": 17.153, + "args": { + "External id": 3718422,"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": 1625851647477.982, "dur": 13.945, + "args": { + "External id": 3718423,"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": 1625851647498.273, "dur": 17.992, + "args": { + "External id": 3718424,"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": 1625851647500.310, "dur": 3.066, + "args": { + "External id": 3718425,"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": 1625851647503.908, "dur": 12.100, + "args": { + "External id": 3718426,"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": 1625851647504.669, "dur": 11.053, + "args": { + "External id": 3718427,"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": 1625851647520.718, "dur": 22.398, + "args": { + "External id": 3718428,"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": 1625851647545.513, "dur": 52.287, + "args": { + "External id": 3718429,"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": 1625851647547.261, "dur": 50.201, + "args": { + "External id": 3718430,"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": 1625851647553.960, "dur": 0.998, + "args": { + "External id": 3718431,"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": 1625851647556.412, "dur": 25.450, + "args": { + "External id": 3718432,"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": 1625851647560.231, "dur": 21.425, + "args": { + "External id": 3718433,"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": 1625851647562.840, "dur": 3.030, + "args": { + "External id": 3718434,"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": 1625851647566.651, "dur": 14.611, + "args": { + "External id": 3718435,"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": 1625851647601.001, "dur": 36144.604, + "args": { + "External id": 3718436,"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": 1625851647602.471, "dur": 36140.476, + "args": { + "External id": 3718437,"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": 1625851683777.095, "dur": 11.838, + "args": { + "External id": 3718438,"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": 1625851683785.673, "dur": 1.302, + "args": { + "External id": 3718439,"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": 1625851683796.595, "dur": 108.175, + "args": { + "External id": 3718440,"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": 1625851683798.217, "dur": 6.618, + "args": { + "External id": 3718441,"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": 1625851683801.058, "dur": 2.882, + "args": { + "External id": 3718442,"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": 1625851683803.115, "dur": 0.579, + "args": { + "External id": 3718443,"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": 1625851683806.214, "dur": 97.915, + "args": { + "External id": 3718444,"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": 1625851683807.902, "dur": 95.314, + "args": { + "External id": 3718445,"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": 1625851683908.024, "dur": 4.038, + "args": { + "External id": 3718446,"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": 1625851683910.185, "dur": 0.710, + "args": { + "External id": 3718447,"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": 1625851683921.682, "dur": 2.624, + "args": { + "External id": 3718448,"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": 1625851683933.464, "dur": 6.816, + "args": { + "External id": 3718449,"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": 1625851683935.542, "dur": 4.499, + "args": { + "External id": 3718450,"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": 1625851684095.617, "dur": 217.582, + "args": { + "External id": 3718451,"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": 1625851684100.261, "dur": 3.298, + "args": { + "External id": 3718452,"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": 1625851684107.533, "dur": 205.253, + "args": { + "External id": 3718453,"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": 1625851684109.083, "dur": 0.741, + "args": { + "External id": 3718454,"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": 1625851684110.961, "dur": 26.883, + "args": { + "External id": 3718455,"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": 1625851684139.737, "dur": 6.424, + "args": { + "External id": 3718456,"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": 1625851684144.784, "dur": 1.079, + "args": { + "External id": 3718457,"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": 1625851684147.121, "dur": 25.922, + "args": { + "External id": 3718458,"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": 1625851684148.731, "dur": 1.726, + "args": { + "External id": 3718459,"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": 1625851684151.765, "dur": 21.017, + "args": { + "External id": 3718460,"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": 1625851684155.069, "dur": 3.196, + "args": { + "External id": 3718461,"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": 1625851684177.138, "dur": 22.835, + "args": { + "External id": 3718462,"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": 1625851684201.581, "dur": 19.558, + "args": { + "External id": 3718463,"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": 1625851684224.627, "dur": 15.611, + "args": { + "External id": 3718464,"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": 1625851684241.940, "dur": 14.666, + "args": { + "External id": 3718465,"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": 1625851684258.837, "dur": 21.154, + "args": { + "External id": 3718466,"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": 1625851684260.808, "dur": 1.883, + "args": { + "External id": 3718467,"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": 1625851684264.656, "dur": 0.744, + "args": { + "External id": 3718468,"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": 1625851684284.263, "dur": 13.526, + "args": { + "External id": 3718469,"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": 1625851684299.052, "dur": 12.367, + "args": { + "External id": 3718470,"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": 1625851684319.493, "dur": 2.121, + "args": { + "External id": 3718471,"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": 1625851684327.955, "dur": 4.337, + "args": { + "External id": 3718472,"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": 1625851684330.625, "dur": 0.736, + "args": { + "External id": 3718473,"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": 1625851684401.808, "dur": 67.119, + "args": { + "External id": 3718474,"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": 1625851684474.174, "dur": 6.582, + "args": { + "External id": 3718475,"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": 1625851684477.060, "dur": 1.116, + "args": { + "External id": 3718476,"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": 1625851684484.712, "dur": 28.488, + "args": { + "External id": 3718477,"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": 1625851684518.760, "dur": 6.578, + "args": { + "External id": 3718478,"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": 1625851684520.698, "dur": 3.658, + "args": { + "External id": 3718479,"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": 1625851684522.711, "dur": 1.426, + "args": { + "External id": 3718480,"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": 1625851684528.256, "dur": 43.263, + "args": { + "External id": 3718481,"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": 1625851684529.488, "dur": 41.414, + "args": { + "External id": 3718482,"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": 1625851684575.693, "dur": 15.749, + "args": { + "External id": 3718483,"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": 1625851684599.407, "dur": 3.490, + "args": { + "External id": 3718484,"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": 1625851684601.140, "dur": 0.862, + "args": { + "External id": 3718485,"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": 1625851684607.275, "dur": 51.501, + "args": { + "External id": 3718486,"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": 1625851684608.447, "dur": 4.114, + "args": { + "External id": 3718487,"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": 1625851684609.197, "dur": 2.725, + "args": { + "External id": 3718488,"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": 1625851684610.826, "dur": 0.968, + "args": { + "External id": 3718489,"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": 1625851684615.627, "dur": 42.738, + "args": { + "External id": 3718490,"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": 1625851684616.153, "dur": 41.705, + "args": { + "External id": 3718491,"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": 1625851684662.599, "dur": 3.518, + "args": { + "External id": 3718492,"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": 1625851684664.473, "dur": 0.605, + "args": { + "External id": 3718493,"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": 1625851684671.799, "dur": 1.404, + "args": { + "External id": 3718494,"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": 1625851684697.161, "dur": 12.127, + "args": { + "External id": 3718495,"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": 1625851684701.213, "dur": 7.610, + "args": { + "External id": 3718496,"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": 1625851684798.902, "dur": 238.150, + "args": { + "External id": 3718497,"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": 1625851684805.883, "dur": 2.585, + "args": { + "External id": 3718498,"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": 1625851684809.736, "dur": 226.604, + "args": { + "External id": 3718499,"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": 1625851684812.983, "dur": 0.211, + "args": { + "External id": 3718500,"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": 1625851684814.247, "dur": 22.900, + "args": { + "External id": 3718501,"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": 1625851684838.902, "dur": 7.441, + "args": { + "External id": 3718502,"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": 1625851684843.271, "dur": 2.790, + "args": { + "External id": 3718503,"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": 1625851684849.712, "dur": 23.176, + "args": { + "External id": 3718504,"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": 1625851684851.056, "dur": 1.562, + "args": { + "External id": 3718505,"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": 1625851684853.657, "dur": 18.882, + "args": { + "External id": 3718506,"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": 1625851684856.061, "dur": 3.196, + "args": { + "External id": 3718507,"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": 1625851684874.213, "dur": 22.874, + "args": { + "External id": 3718508,"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": 1625851684898.543, "dur": 13.328, + "args": { + "External id": 3718509,"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": 1625851684914.716, "dur": 15.464, + "args": { + "External id": 3718510,"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": 1625851684931.391, "dur": 13.732, + "args": { + "External id": 3718511,"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": 1625851684946.490, "dur": 24.490, + "args": { + "External id": 3718512,"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": 1625851684950.706, "dur": 1.438, + "args": { + "External id": 3718513,"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": 1625851684953.929, "dur": 2.951, + "args": { + "External id": 3718514,"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": 1625851684972.284, "dur": 46.436, + "args": { + "External id": 3718515,"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": 1625851685020.926, "dur": 13.934, + "args": { + "External id": 3718516,"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": 1625851685045.425, "dur": 2.661, + "args": { + "External id": 3718517,"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": 1625851685056.751, "dur": 3.845, + "args": { + "External id": 3718518,"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": 1625851685058.992, "dur": 0.756, + "args": { + "External id": 3718519,"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": 1625851685126.618, "dur": 60.040, + "args": { + "External id": 3718520,"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": 1625851685193.960, "dur": 5.033, + "args": { + "External id": 3718521,"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": 1625851685196.768, "dur": 1.060, + "args": { + "External id": 3718522,"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": 1625851685200.374, "dur": 25.096, + "args": { + "External id": 3718523,"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": 1625851685230.118, "dur": 6.005, + "args": { + "External id": 3718524,"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": 1625851685231.783, "dur": 3.665, + "args": { + "External id": 3718525,"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": 1625851685233.554, "dur": 1.662, + "args": { + "External id": 3718526,"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": 1625851685240.990, "dur": 40.504, + "args": { + "External id": 3718527,"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": 1625851685242.174, "dur": 38.619, + "args": { + "External id": 3718528,"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": 1625851685285.332, "dur": 16.325, + "args": { + "External id": 3718529,"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": 1625851685307.169, "dur": 3.947, + "args": { + "External id": 3718530,"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": 1625851685309.359, "dur": 0.936, + "args": { + "External id": 3718531,"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": 1625851685314.604, "dur": 49.468, + "args": { + "External id": 3718532,"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": 1625851685315.664, "dur": 5.976, + "args": { + "External id": 3718533,"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": 1625851685318.804, "dur": 2.287, + "args": { + "External id": 3718534,"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": 1625851685320.105, "dur": 0.859, + "args": { + "External id": 3718535,"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": 1625851685322.396, "dur": 41.305, + "args": { + "External id": 3718536,"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": 1625851685323.009, "dur": 40.193, + "args": { + "External id": 3718537,"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": 1625851685368.508, "dur": 4.442, + "args": { + "External id": 3718538,"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": 1625851685370.928, "dur": 0.931, + "args": { + "External id": 3718539,"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": 1625851685378.388, "dur": 1.314, + "args": { + "External id": 3718540,"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": 1625851685390.119, "dur": 6.608, + "args": { + "External id": 3718541,"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": 1625851685391.901, "dur": 4.576, + "args": { + "External id": 3718542,"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": 1625851685478.405, "dur": 194.718, + "args": { + "External id": 3718543,"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": 1625851685482.876, "dur": 2.274, + "args": { + "External id": 3718544,"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": 1625851685486.467, "dur": 186.166, + "args": { + "External id": 3718545,"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": 1625851685487.389, "dur": 0.290, + "args": { + "External id": 3718546,"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": 1625851685488.632, "dur": 24.064, + "args": { + "External id": 3718547,"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": 1625851685514.079, "dur": 5.303, + "args": { + "External id": 3718548,"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": 1625851685518.210, "dur": 0.913, + "args": { + "External id": 3718549,"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": 1625851685522.702, "dur": 23.208, + "args": { + "External id": 3718550,"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": 1625851685524.145, "dur": 2.535, + "args": { + "External id": 3718551,"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": 1625851685527.882, "dur": 17.783, + "args": { + "External id": 3718552,"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": 1625851685530.467, "dur": 2.673, + "args": { + "External id": 3718553,"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": 1625851685547.287, "dur": 21.073, + "args": { + "External id": 3718554,"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": 1625851685569.958, "dur": 17.293, + "args": { + "External id": 3718555,"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": 1625851685590.124, "dur": 14.783, + "args": { + "External id": 3718556,"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": 1625851685606.133, "dur": 13.874, + "args": { + "External id": 3718557,"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": 1625851685621.541, "dur": 23.319, + "args": { + "External id": 3718558,"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": 1625851685625.656, "dur": 2.212, + "args": { + "External id": 3718559,"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": 1625851685629.691, "dur": 0.784, + "args": { + "External id": 3718560,"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": 1625851685646.035, "dur": 13.552, + "args": { + "External id": 3718561,"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": 1625851685660.411, "dur": 11.218, + "args": { + "External id": 3718562,"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": 1625851685697.875, "dur": 2.273, + "args": { + "External id": 3718563,"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": 1625851685711.091, "dur": 3.733, + "args": { + "External id": 3718564,"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": 1625851685713.519, "dur": 0.560, + "args": { + "External id": 3718565,"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": 1625851685790.393, "dur": 82.305, + "args": { + "External id": 3718566,"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": 1625851685877.301, "dur": 4.586, + "args": { + "External id": 3718567,"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": 1625851685880.087, "dur": 0.780, + "args": { + "External id": 3718568,"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": 1625851685883.151, "dur": 35.858, + "args": { + "External id": 3718569,"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": 1625851685923.125, "dur": 7.686, + "args": { + "External id": 3718570,"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": 1625851685924.704, "dur": 5.531, + "args": { + "External id": 3718571,"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": 1625851685928.762, "dur": 1.296, + "args": { + "External id": 3718572,"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": 1625851685933.259, "dur": 85.347, + "args": { + "External id": 3718573,"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": 1625851685934.296, "dur": 83.140, + "args": { + "External id": 3718574,"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": 1625851686024.286, "dur": 21.302, + "args": { + "External id": 3718575,"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": 1625851686052.028, "dur": 5.224, + "args": { + "External id": 3718576,"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": 1625851686054.948, "dur": 1.333, + "args": { + "External id": 3718577,"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": 1625851686060.903, "dur": 53.619, + "args": { + "External id": 3718578,"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": 1625851686063.886, "dur": 4.218, + "args": { + "External id": 3718579,"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": 1625851686064.912, "dur": 2.661, + "args": { + "External id": 3718580,"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": 1625851686066.553, "dur": 0.876, + "args": { + "External id": 3718581,"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": 1625851686068.997, "dur": 45.177, + "args": { + "External id": 3718582,"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": 1625851686069.769, "dur": 43.868, + "args": { + "External id": 3718583,"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": 1625851686118.228, "dur": 4.440, + "args": { + "External id": 3718584,"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": 1625851686120.432, "dur": 1.098, + "args": { + "External id": 3718585,"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": 1625851686130.608, "dur": 1.804, + "args": { + "External id": 3718586,"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": 1625851686139.825, "dur": 9.086, + "args": { + "External id": 3718587,"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": 1625851686141.483, "dur": 7.108, + "args": { + "External id": 3718588,"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": 1625851686232.839, "dur": 195.093, + "args": { + "External id": 3718589,"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": 1625851686234.931, "dur": 2.343, + "args": { + "External id": 3718590,"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": 1625851686241.178, "dur": 186.368, + "args": { + "External id": 3718591,"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": 1625851686242.570, "dur": 0.306, + "args": { + "External id": 3718592,"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": 1625851686243.851, "dur": 24.423, + "args": { + "External id": 3718593,"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": 1625851686269.976, "dur": 3.144, + "args": { + "External id": 3718594,"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": 1625851686271.908, "dur": 0.962, + "args": { + "External id": 3718595,"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": 1625851686273.974, "dur": 25.970, + "args": { + "External id": 3718596,"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": 1625851686275.396, "dur": 2.049, + "args": { + "External id": 3718597,"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": 1625851686278.598, "dur": 21.070, + "args": { + "External id": 3718598,"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": 1625851686283.667, "dur": 2.203, + "args": { + "External id": 3718599,"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": 1625851686303.924, "dur": 22.904, + "args": { + "External id": 3718600,"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": 1625851686328.253, "dur": 14.318, + "args": { + "External id": 3718601,"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": 1625851686345.075, "dur": 15.652, + "args": { + "External id": 3718602,"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": 1625851686362.038, "dur": 12.908, + "args": { + "External id": 3718603,"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": 1625851686376.724, "dur": 19.815, + "args": { + "External id": 3718604,"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": 1625851686378.235, "dur": 1.368, + "args": { + "External id": 3718605,"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": 1625851686381.806, "dur": 1.062, + "args": { + "External id": 3718606,"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": 1625851686397.845, "dur": 13.362, + "args": { + "External id": 3718607,"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": 1625851686414.279, "dur": 12.282, + "args": { + "External id": 3718608,"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": 1625851686433.941, "dur": 1.792, + "args": { + "External id": 3718609,"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": 1625851686443.280, "dur": 3.730, + "args": { + "External id": 3718610,"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": 1625851686446.036, "dur": 0.260, + "args": { + "External id": 3718611,"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": 1625851686505.995, "dur": 47.503, + "args": { + "External id": 3718612,"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": 1625851686558.042, "dur": 5.016, + "args": { + "External id": 3718613,"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": 1625851686561.017, "dur": 1.132, + "args": { + "External id": 3718614,"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": 1625851686564.323, "dur": 24.228, + "args": { + "External id": 3718615,"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": 1625851686595.248, "dur": 5.435, + "args": { + "External id": 3718616,"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": 1625851686596.415, "dur": 3.738, + "args": { + "External id": 3718617,"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": 1625851686598.679, "dur": 1.307, + "args": { + "External id": 3718618,"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": 1625851686602.948, "dur": 38.771, + "args": { + "External id": 3718619,"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": 1625851686603.964, "dur": 37.076, + "args": { + "External id": 3718620,"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": 1625851686645.180, "dur": 15.253, + "args": { + "External id": 3718621,"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": 1625851686665.315, "dur": 5.855, + "args": { + "External id": 3718622,"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": 1625851686669.397, "dur": 1.039, + "args": { + "External id": 3718623,"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": 1625851686674.632, "dur": 73.956, + "args": { + "External id": 3718624,"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": 1625851686675.197, "dur": 21.711, + "args": { + "External id": 3718625,"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": 1625851686692.518, "dur": 3.599, + "args": { + "External id": 3718626,"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": 1625851686694.821, "dur": 0.983, + "args": { + "External id": 3718627,"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": 1625851686697.575, "dur": 50.533, + "args": { + "External id": 3718628,"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": 1625851686701.104, "dur": 46.333, + "args": { + "External id": 3718629,"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": 1625851686753.724, "dur": 5.870, + "args": { + "External id": 3718630,"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": 1625851686755.734, "dur": 2.684, + "args": { + "External id": 3718631,"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": 1625851686765.789, "dur": 1.862, + "args": { + "External id": 3718632,"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": 1625851686774.624, "dur": 6.731, + "args": { + "External id": 3718633,"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": 1625851686776.856, "dur": 4.223, + "args": { + "External id": 3718634,"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": 1625851686862.879, "dur": 227.318, + "args": { + "External id": 3718635,"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": 1625851686865.085, "dur": 2.457, + "args": { + "External id": 3718636,"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": 1625851686868.776, "dur": 220.912, + "args": { + "External id": 3718637,"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": 1625851686870.219, "dur": 0.546, + "args": { + "External id": 3718638,"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": 1625851686871.914, "dur": 24.501, + "args": { + "External id": 3718639,"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": 1625851686897.698, "dur": 3.467, + "args": { + "External id": 3718640,"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": 1625851686900.022, "dur": 0.908, + "args": { + "External id": 3718641,"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": 1625851686901.915, "dur": 26.481, + "args": { + "External id": 3718642,"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": 1625851686903.131, "dur": 1.498, + "args": { + "External id": 3718643,"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": 1625851686905.760, "dur": 22.325, + "args": { + "External id": 3718644,"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": 1625851686912.804, "dur": 2.649, + "args": { + "External id": 3718645,"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": 1625851686929.646, "dur": 20.698, + "args": { + "External id": 3718646,"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": 1625851686951.384, "dur": 14.110, + "args": { + "External id": 3718647,"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": 1625851686967.898, "dur": 48.704, + "args": { + "External id": 3718648,"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": 1625851687018.884, "dur": 16.509, + "args": { + "External id": 3718649,"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": 1625851687037.179, "dur": 22.493, + "args": { + "External id": 3718650,"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": 1625851687038.950, "dur": 1.794, + "args": { + "External id": 3718651,"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": 1625851687043.443, "dur": 0.937, + "args": { + "External id": 3718652,"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": 1625851687063.332, "dur": 13.071, + "args": { + "External id": 3718653,"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": 1625851687077.328, "dur": 11.332, + "args": { + "External id": 3718654,"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": 1625851687097.105, "dur": 2.328, + "args": { + "External id": 3718655,"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": 1625851687108.037, "dur": 42.188, + "args": { + "External id": 3718656,"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": 1625851687148.733, "dur": 0.445, + "args": { + "External id": 3718657,"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": 1625851687219.240, "dur": 57.396, + "args": { + "External id": 3718658,"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": 1625851687281.525, "dur": 6.764, + "args": { + "External id": 3718659,"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": 1625851687284.062, "dur": 3.269, + "args": { + "External id": 3718660,"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": 1625851687292.051, "dur": 23.039, + "args": { + "External id": 3718661,"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": 1625851687319.529, "dur": 5.286, + "args": { + "External id": 3718662,"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": 1625851687320.862, "dur": 3.117, + "args": { + "External id": 3718663,"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": 1625851687322.772, "dur": 1.055, + "args": { + "External id": 3718664,"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": 1625851687327.438, "dur": 40.234, + "args": { + "External id": 3718665,"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": 1625851687328.425, "dur": 38.653, + "args": { + "External id": 3718666,"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": 1625851687371.529, "dur": 15.577, + "args": { + "External id": 3718667,"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": 1625851687394.383, "dur": 2.945, + "args": { + "External id": 3718668,"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": 1625851687396.093, "dur": 0.556, + "args": { + "External id": 3718669,"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": 1625851687400.664, "dur": 49.997, + "args": { + "External id": 3718670,"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": 1625851687401.536, "dur": 4.145, + "args": { + "External id": 3718671,"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": 1625851687402.212, "dur": 2.779, + "args": { + "External id": 3718672,"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": 1625851687403.612, "dur": 1.036, + "args": { + "External id": 3718673,"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": 1625851687408.392, "dur": 41.927, + "args": { + "External id": 3718674,"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": 1625851687408.841, "dur": 40.946, + "args": { + "External id": 3718675,"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": 1625851687454.212, "dur": 3.603, + "args": { + "External id": 3718676,"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": 1625851687455.996, "dur": 0.653, + "args": { + "External id": 3718677,"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": 1625851687462.469, "dur": 1.341, + "args": { + "External id": 3718678,"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": 1625851687470.103, "dur": 9.047, + "args": { + "External id": 3718679,"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": 1625851687474.002, "dur": 4.886, + "args": { + "External id": 3718680,"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": 1625851687556.672, "dur": 208.801, + "args": { + "External id": 3718681,"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": 1625851687558.595, "dur": 4.036, + "args": { + "External id": 3718682,"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": 1625851687563.609, "dur": 201.164, + "args": { + "External id": 3718683,"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": 1625851687564.919, "dur": 0.296, + "args": { + "External id": 3718684,"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": 1625851687566.353, "dur": 21.633, + "args": { + "External id": 3718685,"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": 1625851687589.301, "dur": 6.390, + "args": { + "External id": 3718686,"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": 1625851687594.336, "dur": 1.090, + "args": { + "External id": 3718687,"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": 1625851687596.588, "dur": 24.372, + "args": { + "External id": 3718688,"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": 1625851687599.735, "dur": 1.886, + "args": { + "External id": 3718689,"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": 1625851687602.788, "dur": 17.886, + "args": { + "External id": 3718690,"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": 1625851687605.790, "dur": 2.493, + "args": { + "External id": 3718691,"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": 1625851687622.275, "dur": 20.835, + "args": { + "External id": 3718692,"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": 1625851687644.151, "dur": 14.032, + "args": { + "External id": 3718693,"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": 1625851687661.390, "dur": 14.351, + "args": { + "External id": 3718694,"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": 1625851687692.941, "dur": 15.670, + "args": { + "External id": 3718695,"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": 1625851687710.677, "dur": 25.960, + "args": { + "External id": 3718696,"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": 1625851687714.563, "dur": 2.159, + "args": { + "External id": 3718697,"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": 1625851687721.212, "dur": 0.836, + "args": { + "External id": 3718698,"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": 1625851687738.062, "dur": 12.694, + "args": { + "External id": 3718699,"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": 1625851687751.677, "dur": 12.013, + "args": { + "External id": 3718700,"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": 1625851687772.413, "dur": 1.801, + "args": { + "External id": 3718701,"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": 1625851687782.132, "dur": 3.780, + "args": { + "External id": 3718702,"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": 1625851687784.576, "dur": 0.621, + "args": { + "External id": 3718703,"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": 1625851687847.614, "dur": 51.550, + "args": { + "External id": 3718704,"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": 1625851687905.958, "dur": 4.371, + "args": { + "External id": 3718705,"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": 1625851687908.324, "dur": 1.094, + "args": { + "External id": 3718706,"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": 1625851687911.744, "dur": 23.199, + "args": { + "External id": 3718707,"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": 1625851687938.911, "dur": 5.309, + "args": { + "External id": 3718708,"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": 1625851687940.102, "dur": 3.564, + "args": { + "External id": 3718709,"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": 1625851687941.895, "dur": 1.600, + "args": { + "External id": 3718710,"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": 1625851687948.751, "dur": 75.756, + "args": { + "External id": 3718711,"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": 1625851687950.060, "dur": 73.224, + "args": { + "External id": 3718712,"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": 1625851688030.080, "dur": 17.706, + "args": { + "External id": 3718713,"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": 1625851688054.172, "dur": 4.531, + "args": { + "External id": 3718714,"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": 1625851688056.556, "dur": 1.240, + "args": { + "External id": 3718715,"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": 1625851688062.557, "dur": 53.706, + "args": { + "External id": 3718716,"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": 1625851688063.318, "dur": 6.380, + "args": { + "External id": 3718717,"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": 1625851688066.543, "dur": 2.675, + "args": { + "External id": 3718718,"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": 1625851688068.091, "dur": 0.976, + "args": { + "External id": 3718719,"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": 1625851688070.245, "dur": 45.692, + "args": { + "External id": 3718720,"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": 1625851688071.008, "dur": 44.350, + "args": { + "External id": 3718721,"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": 1625851688120.422, "dur": 3.403, + "args": { + "External id": 3718722,"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": 1625851688122.042, "dur": 0.749, + "args": { + "External id": 3718723,"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": 1625851688129.685, "dur": 1.263, + "args": { + "External id": 3718724,"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": 1625851688139.746, "dur": 6.831, + "args": { + "External id": 3718725,"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": 1625851688141.525, "dur": 4.766, + "args": { + "External id": 3718726,"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": 1625851688227.504, "dur": 197.488, + "args": { + "External id": 3718727,"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": 1625851688231.620, "dur": 2.130, + "args": { + "External id": 3718728,"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": 1625851688234.978, "dur": 189.383, + "args": { + "External id": 3718729,"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": 1625851688236.030, "dur": 0.494, + "args": { + "External id": 3718730,"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": 1625851688237.668, "dur": 21.625, + "args": { + "External id": 3718731,"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": 1625851688262.938, "dur": 5.383, + "args": { + "External id": 3718732,"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": 1625851688267.166, "dur": 0.794, + "args": { + "External id": 3718733,"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": 1625851688269.357, "dur": 22.537, + "args": { + "External id": 3718734,"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": 1625851688270.281, "dur": 1.816, + "args": { + "External id": 3718735,"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": 1625851688273.154, "dur": 18.470, + "args": { + "External id": 3718736,"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": 1625851688276.047, "dur": 2.536, + "args": { + "External id": 3718737,"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": 1625851688293.180, "dur": 20.788, + "args": { + "External id": 3718738,"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": 1625851688315.191, "dur": 16.602, + "args": { + "External id": 3718739,"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": 1625851688334.431, "dur": 14.470, + "args": { + "External id": 3718740,"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": 1625851688350.022, "dur": 13.760, + "args": { + "External id": 3718741,"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": 1625851688367.695, "dur": 29.328, + "args": { + "External id": 3718742,"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": 1625851688369.419, "dur": 1.264, + "args": { + "External id": 3718743,"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": 1625851688380.363, "dur": 0.920, + "args": { + "External id": 3718744,"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": 1625851688398.519, "dur": 13.050, + "args": { + "External id": 3718745,"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": 1625851688412.490, "dur": 11.032, + "args": { + "External id": 3718746,"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": 1625851688430.533, "dur": 1.543, + "args": { + "External id": 3718747,"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": 1625851688439.446, "dur": 3.293, + "args": { + "External id": 3718748,"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": 1625851688441.719, "dur": 0.291, + "args": { + "External id": 3718749,"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": 1625851688506.698, "dur": 51.762, + "args": { + "External id": 3718750,"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": 1625851688563.095, "dur": 4.641, + "args": { + "External id": 3718751,"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": 1625851688565.606, "dur": 1.024, + "args": { + "External id": 3718752,"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": 1625851688569.053, "dur": 23.427, + "args": { + "External id": 3718753,"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": 1625851688599.443, "dur": 8.908, + "args": { + "External id": 3718754,"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": 1625851688600.702, "dur": 7.017, + "args": { + "External id": 3718755,"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": 1625851688604.831, "dur": 2.656, + "args": { + "External id": 3718756,"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": 1625851688610.644, "dur": 41.793, + "args": { + "External id": 3718757,"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": 1625851688611.666, "dur": 40.309, + "args": { + "External id": 3718758,"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": 1625851688656.047, "dur": 14.612, + "args": { + "External id": 3718759,"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": 1625851688675.407, "dur": 22.567, + "args": { + "External id": 3718760,"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": 1625851688695.684, "dur": 0.975, + "args": { + "External id": 3718761,"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": 1625851688705.278, "dur": 51.433, + "args": { + "External id": 3718762,"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": 1625851688705.949, "dur": 4.210, + "args": { + "External id": 3718763,"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": 1625851688707.059, "dur": 2.420, + "args": { + "External id": 3718764,"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": 1625851688708.527, "dur": 0.794, + "args": { + "External id": 3718765,"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": 1625851688710.712, "dur": 45.636, + "args": { + "External id": 3718766,"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": 1625851688711.507, "dur": 44.229, + "args": { + "External id": 3718767,"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": 1625851688763.396, "dur": 3.945, + "args": { + "External id": 3718768,"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": 1625851688765.216, "dur": 1.032, + "args": { + "External id": 3718769,"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": 1625851688773.024, "dur": 1.411, + "args": { + "External id": 3718770,"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": 1625851688781.322, "dur": 7.324, + "args": { + "External id": 3718771,"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": 1625851688783.402, "dur": 4.963, + "args": { + "External id": 3718772,"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": 1625851688869.491, "dur": 234.655, + "args": { + "External id": 3718773,"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": 1625851688871.604, "dur": 2.282, + "args": { + "External id": 3718774,"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": 1625851688877.360, "dur": 226.328, + "args": { + "External id": 3718775,"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": 1625851688878.416, "dur": 0.311, + "args": { + "External id": 3718776,"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": 1625851688879.798, "dur": 22.442, + "args": { + "External id": 3718777,"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": 1625851688903.360, "dur": 5.406, + "args": { + "External id": 3718778,"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": 1625851688905.669, "dur": 2.853, + "args": { + "External id": 3718779,"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": 1625851688909.594, "dur": 23.902, + "args": { + "External id": 3718780,"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": 1625851688910.530, "dur": 1.628, + "args": { + "External id": 3718781,"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": 1625851688913.226, "dur": 20.013, + "args": { + "External id": 3718782,"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": 1625851688918.321, "dur": 2.656, + "args": { + "External id": 3718783,"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": 1625851688934.850, "dur": 21.687, + "args": { + "External id": 3718784,"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": 1625851688957.773, "dur": 13.997, + "args": { + "External id": 3718785,"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": 1625851688974.158, "dur": 54.590, + "args": { + "External id": 3718786,"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": 1625851689031.602, "dur": 17.344, + "args": { + "External id": 3718787,"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": 1625851689050.891, "dur": 21.523, + "args": { + "External id": 3718788,"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": 1625851689052.975, "dur": 1.680, + "args": { + "External id": 3718789,"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": 1625851689056.573, "dur": 0.913, + "args": { + "External id": 3718790,"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": 1625851689076.320, "dur": 13.004, + "args": { + "External id": 3718791,"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": 1625851689090.482, "dur": 12.164, + "args": { + "External id": 3718792,"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": 1625851689111.152, "dur": 2.134, + "args": { + "External id": 3718793,"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": 1625851689121.941, "dur": 3.847, + "args": { + "External id": 3718794,"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": 1625851689124.401, "dur": 0.489, + "args": { + "External id": 3718795,"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": 1625851689190.535, "dur": 56.742, + "args": { + "External id": 3718796,"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": 1625851689252.003, "dur": 7.286, + "args": { + "External id": 3718797,"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": 1625851689254.654, "dur": 3.612, + "args": { + "External id": 3718798,"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": 1625851689263.275, "dur": 30.040, + "args": { + "External id": 3718799,"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": 1625851689297.228, "dur": 5.970, + "args": { + "External id": 3718800,"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": 1625851689298.881, "dur": 3.690, + "args": { + "External id": 3718801,"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": 1625851689301.094, "dur": 1.133, + "args": { + "External id": 3718802,"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": 1625851689305.553, "dur": 42.034, + "args": { + "External id": 3718803,"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": 1625851689306.934, "dur": 39.933, + "args": { + "External id": 3718804,"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": 1625851689351.511, "dur": 15.563, + "args": { + "External id": 3718805,"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": 1625851689373.504, "dur": 25.020, + "args": { + "External id": 3718806,"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": 1625851689375.953, "dur": 22.186, + "args": { + "External id": 3718807,"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": 1625851689381.337, "dur": 1.035, + "args": { + "External id": 3718808,"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": 1625851689403.204, "dur": 26.339, + "args": { + "External id": 3718809,"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": 1625851689404.926, "dur": 24.386, + "args": { + "External id": 3718810,"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": 1625851689409.374, "dur": 4.389, + "args": { + "External id": 3718811,"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": 1625851689414.852, "dur": 13.915, + "args": { + "External id": 3718812,"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": 1625851689443.125, "dur": 4.907, + "args": { + "External id": 3718813,"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": 1625851689444.902, "dur": 2.876, + "args": { + "External id": 3718814,"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": 1625851689449.231, "dur": 3.570, + "args": { + "External id": 3718815,"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": 1625851689452.091, "dur": 0.610, + "args": { + "External id": 3718816,"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": 1625851689491.427, "dur": 22.544, + "args": { + "External id": 3718817,"Sequence number": 37295284, "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": 1625851689515.732, "dur": 13.859, + "args": { + "External id": 3718818,"Sequence number": 37295285, "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": 1625851689515.732, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1336756, + "ts": 1625851689534.909, "dur": 5.453, + "args": { + "External id": 3718819,"Sequence number": 37295286, "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": 1625851689538.303, "dur": 0.884, + "args": { + "External id": 3718820,"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": 1625851689542.747, "dur": 8.856, + "args": { + "External id": 3718821,"Sequence number": 37295286, "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": 1625851689549.347, "dur": 1.002, + "args": { + "External id": 3718822,"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": 1625851689552.916, "dur": 3.080, + "args": { + "External id": 3718823,"Sequence number": 37295286, "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": 1625851689554.348, "dur": 1.039, + "args": { + "External id": 3718824,"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": 1625851689559.887, "dur": 6.215, + "args": { + "External id": 3718825,"Sequence number": 37295286, "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": 1625851689559.887, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1625851689563.599, "dur": 1.308, + "args": { + "External id": 3718826,"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": 1625851689567.086, "dur": 6.788, + "args": { + "External id": 3718827,"Sequence number": 37295287, "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": 1625851689567.086, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1625851689572.360, "dur": 0.776, + "args": { + "External id": 3718828,"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": 1625851689574.883, "dur": 5.507, + "args": { + "External id": 3718829,"Sequence number": 37295288, "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": 1625851689574.883, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1625851689578.483, "dur": 1.058, + "args": { + "External id": 3718830,"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": 1625851689581.334, "dur": 5.397, + "args": { + "External id": 3718831,"Sequence number": 37295289, "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": 1625851689581.334, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1625851689584.343, "dur": 1.500, + "args": { + "External id": 3718832,"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": 1625851689590.748, "dur": 30.491, + "args": { + "External id": 3718833,"Sequence number": 37295290, "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": 1625851689592.321, "dur": 28.688, + "args": { + "External id": 3718834,"Sequence number": 37295290, "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": 1625851689594.675, "dur": 7.254, + "args": { + "External id": 3718835,"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": 1625851689598.303, "dur": 2.978, + "args": { + "External id": 3718836,"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": 1625851689602.700, "dur": 17.887, + "args": { + "External id": 3718837,"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": 1625851689644.977, "dur": 3.816, + "args": { + "External id": 3718838,"Sequence number": 37295290, "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": 1625851689644.977, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1625851689650.872, "dur": 3.202, + "args": { + "External id": 3718839,"Sequence number": 37295291, "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": 1625851689704.746, "dur": 44005.371, + "args": { + "External id": 3718840,"Sequence number": 37295291, "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": 1625851689704.746, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::contiguous", "pid": 1336756, "tid": 1336756, + "ts": 1625851689720.898, "dur": 33.881, + "args": { + "External id": 3718841,"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": 1625851689724.051, "dur": 30.542, + "args": { + "External id": 3718842,"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": 1625851689725.844, "dur": 7.275, + "args": { + "External id": 3718843,"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": 1625851689727.499, "dur": 4.973, + "args": { + "External id": 3718844,"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": 1625851689733.870, "dur": 20.396, + "args": { + "External id": 3718845,"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": 1625851689770.216, "dur": 26.068, + "args": { + "External id": 3718846,"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": 1625851689771.185, "dur": 6.454, + "args": { + "External id": 3718847,"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": 1625851689773.126, "dur": 4.213, + "args": { + "External id": 3718848,"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": 1625851689779.008, "dur": 17.064, + "args": { + "External id": 3718849,"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": 1625851689780.561, "dur": 15.092, + "args": { + "External id": 3718850,"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": 1625851689799.443, "dur": 21.619, + "args": { + "External id": 3718851,"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": 1625851689800.552, "dur": 4.585, + "args": { + "External id": 3718852,"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": 1625851689802.108, "dur": 2.779, + "args": { + "External id": 3718853,"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": 1625851689807.919, "dur": 12.962, + "args": { + "External id": 3718854,"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": 1625851689808.509, "dur": 12.023, + "args": { + "External id": 3718855,"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": 1625851689827.066, "dur": 18.001, + "args": { + "External id": 3718856,"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": 1625851689828.790, "dur": 4.421, + "args": { + "External id": 3718857,"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": 1625851689833.777, "dur": 10.997, + "args": { + "External id": 3718858,"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": 1625851689834.455, "dur": 10.023, + "args": { + "External id": 3718859,"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": 1625851689849.493, "dur": 25.254, + "args": { + "External id": 3718860,"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": 1625851689877.527, "dur": 54.149, + "args": { + "External id": 3718861,"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": 1625851689881.879, "dur": 49.204, + "args": { + "External id": 3718862,"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": 1625851689887.359, "dur": 1.488, + "args": { + "External id": 3718863,"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": 1625851689890.124, "dur": 23.852, + "args": { + "External id": 3718864,"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": 1625851689891.847, "dur": 21.871, + "args": { + "External id": 3718865,"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": 1625851689896.160, "dur": 3.104, + "args": { + "External id": 3718866,"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": 1625851689900.212, "dur": 13.130, + "args": { + "External id": 3718867,"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": 1625851689935.631, "dur": 38003.740, + "args": { + "External id": 3718868,"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": 1625851689937.742, "dur": 38000.771, + "args": { + "External id": 3718869,"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": 1625851727948.800, "dur": 6.641, + "args": { + "External id": 3718870,"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": 1625851727952.658, "dur": 0.993, + "args": { + "External id": 3718871,"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": 1625851727962.738, "dur": 140.652, + "args": { + "External id": 3718872,"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": 1625851727964.186, "dur": 6.118, + "args": { + "External id": 3718873,"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": 1625851727966.211, "dur": 3.275, + "args": { + "External id": 3718874,"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": 1625851727968.201, "dur": 1.039, + "args": { + "External id": 3718875,"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": 1625851727971.606, "dur": 130.935, + "args": { + "External id": 3718876,"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": 1625851727973.200, "dur": 127.651, + "args": { + "External id": 3718877,"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": 1625851728110.004, "dur": 6.811, + "args": { + "External id": 3718878,"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": 1625851728113.366, "dur": 1.630, + "args": { + "External id": 3718879,"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": 1625851728126.368, "dur": 2.522, + "args": { + "External id": 3718880,"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": 1625851728137.862, "dur": 7.175, + "args": { + "External id": 3718881,"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": 1625851728140.127, "dur": 4.616, + "args": { + "External id": 3718882,"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": 1625851728274.482, "dur": 213.884, + "args": { + "External id": 3718883,"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": 1625851728277.922, "dur": 2.578, + "args": { + "External id": 3718884,"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": 1625851728284.703, "dur": 203.211, + "args": { + "External id": 3718885,"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": 1625851728286.479, "dur": 0.424, + "args": { + "External id": 3718886,"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": 1625851728290.460, "dur": 27.883, + "args": { + "External id": 3718887,"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": 1625851728319.986, "dur": 3.832, + "args": { + "External id": 3718888,"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": 1625851728322.389, "dur": 1.151, + "args": { + "External id": 3718889,"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": 1625851728324.937, "dur": 26.654, + "args": { + "External id": 3718890,"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": 1625851728325.822, "dur": 4.109, + "args": { + "External id": 3718891,"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": 1625851728331.325, "dur": 20.001, + "args": { + "External id": 3718892,"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": 1625851728335.212, "dur": 3.080, + "args": { + "External id": 3718893,"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": 1625851728355.733, "dur": 23.970, + "args": { + "External id": 3718894,"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": 1625851728381.233, "dur": 14.463, + "args": { + "External id": 3718895,"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": 1625851728398.647, "dur": 16.510, + "args": { + "External id": 3718896,"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": 1625851728416.846, "dur": 14.478, + "args": { + "External id": 3718897,"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": 1625851728433.438, "dur": 21.867, + "args": { + "External id": 3718898,"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": 1625851728435.154, "dur": 2.216, + "args": { + "External id": 3718899,"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": 1625851728439.570, "dur": 0.988, + "args": { + "External id": 3718900,"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": 1625851728459.296, "dur": 13.779, + "args": { + "External id": 3718901,"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": 1625851728474.278, "dur": 12.403, + "args": { + "External id": 3718902,"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": 1625851728494.375, "dur": 2.074, + "args": { + "External id": 3718903,"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": 1625851728503.229, "dur": 4.593, + "args": { + "External id": 3718904,"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": 1625851728505.533, "dur": 1.436, + "args": { + "External id": 3718905,"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": 1625851728579.983, "dur": 66.473, + "args": { + "External id": 3718906,"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": 1625851728651.837, "dur": 5.459, + "args": { + "External id": 3718907,"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": 1625851728654.038, "dur": 0.999, + "args": { + "External id": 3718908,"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": 1625851728661.513, "dur": 45.402, + "args": { + "External id": 3718909,"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": 1625851728713.935, "dur": 8.800, + "args": { + "External id": 3718910,"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": 1625851728715.878, "dur": 5.844, + "args": { + "External id": 3718911,"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": 1625851728718.442, "dur": 2.960, + "args": { + "External id": 3718912,"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": 1625851728726.312, "dur": 51.818, + "args": { + "External id": 3718913,"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": 1625851728727.641, "dur": 49.422, + "args": { + "External id": 3718914,"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": 1625851728782.824, "dur": 17.784, + "args": { + "External id": 3718915,"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": 1625851728809.823, "dur": 3.365, + "args": { + "External id": 3718916,"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": 1625851728811.583, "dur": 0.692, + "args": { + "External id": 3718917,"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": 1625851728817.484, "dur": 51.393, + "args": { + "External id": 3718918,"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": 1625851728818.408, "dur": 4.167, + "args": { + "External id": 3718919,"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": 1625851728819.209, "dur": 2.765, + "args": { + "External id": 3718920,"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": 1625851728820.819, "dur": 1.033, + "args": { + "External id": 3718921,"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": 1625851728825.608, "dur": 42.831, + "args": { + "External id": 3718922,"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": 1625851728826.114, "dur": 41.788, + "args": { + "External id": 3718923,"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": 1625851728872.738, "dur": 3.691, + "args": { + "External id": 3718924,"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": 1625851728874.774, "dur": 0.671, + "args": { + "External id": 3718925,"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": 1625851728882.748, "dur": 1.730, + "args": { + "External id": 3718926,"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": 1625851728891.744, "dur": 9.307, + "args": { + "External id": 3718927,"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": 1625851728895.967, "dur": 4.763, + "args": { + "External id": 3718928,"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": 1625851729032.598, "dur": 201.047, + "args": { + "External id": 3718929,"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": 1625851729034.877, "dur": 3.158, + "args": { + "External id": 3718930,"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": 1625851729041.779, "dur": 191.424, + "args": { + "External id": 3718931,"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": 1625851729043.149, "dur": 0.443, + "args": { + "External id": 3718932,"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": 1625851729044.989, "dur": 25.531, + "args": { + "External id": 3718933,"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": 1625851729071.926, "dur": 5.391, + "args": { + "External id": 3718934,"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": 1625851729074.327, "dur": 2.667, + "args": { + "External id": 3718935,"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": 1625851729080.697, "dur": 23.739, + "args": { + "External id": 3718936,"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": 1625851729081.501, "dur": 2.020, + "args": { + "External id": 3718937,"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": 1625851729084.544, "dur": 19.659, + "args": { + "External id": 3718938,"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": 1625851729087.561, "dur": 3.416, + "args": { + "External id": 3718939,"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": 1625851729106.060, "dur": 22.960, + "args": { + "External id": 3718940,"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": 1625851729130.292, "dur": 15.660, + "args": { + "External id": 3718941,"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": 1625851729148.984, "dur": 14.657, + "args": { + "External id": 3718942,"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": 1625851729164.919, "dur": 13.733, + "args": { + "External id": 3718943,"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": 1625851729180.423, "dur": 24.719, + "args": { + "External id": 3718944,"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": 1625851729184.656, "dur": 1.474, + "args": { + "External id": 3718945,"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": 1625851729188.325, "dur": 2.561, + "args": { + "External id": 3718946,"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": 1625851729206.501, "dur": 13.928, + "args": { + "External id": 3718947,"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": 1625851729221.359, "dur": 10.917, + "args": { + "External id": 3718948,"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": 1625851729240.495, "dur": 1.980, + "args": { + "External id": 3718949,"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": 1625851729251.239, "dur": 3.620, + "args": { + "External id": 3718950,"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": 1625851729253.714, "dur": 0.413, + "args": { + "External id": 3718951,"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": 1625851729326.373, "dur": 56.855, + "args": { + "External id": 3718952,"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": 1625851729390.940, "dur": 5.045, + "args": { + "External id": 3718953,"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": 1625851729393.992, "dur": 0.944, + "args": { + "External id": 3718954,"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": 1625851729397.735, "dur": 26.103, + "args": { + "External id": 3718955,"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": 1625851729428.525, "dur": 6.252, + "args": { + "External id": 3718956,"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": 1625851729429.982, "dur": 3.944, + "args": { + "External id": 3718957,"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": 1625851729431.876, "dur": 1.813, + "args": { + "External id": 3718958,"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": 1625851729439.408, "dur": 42.324, + "args": { + "External id": 3718959,"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": 1625851729440.677, "dur": 40.330, + "args": { + "External id": 3718960,"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": 1625851729485.281, "dur": 14.712, + "args": { + "External id": 3718961,"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": 1625851729505.367, "dur": 3.765, + "args": { + "External id": 3718962,"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": 1625851729507.395, "dur": 0.838, + "args": { + "External id": 3718963,"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": 1625851729512.922, "dur": 49.392, + "args": { + "External id": 3718964,"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": 1625851729513.967, "dur": 5.565, + "args": { + "External id": 3718965,"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": 1625851729516.674, "dur": 2.253, + "args": { + "External id": 3718966,"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": 1625851729518.088, "dur": 0.713, + "args": { + "External id": 3718967,"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": 1625851729520.202, "dur": 41.673, + "args": { + "External id": 3718968,"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": 1625851729520.829, "dur": 40.430, + "args": { + "External id": 3718969,"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": 1625851729566.385, "dur": 3.520, + "args": { + "External id": 3718970,"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": 1625851729568.029, "dur": 0.870, + "args": { + "External id": 3718971,"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": 1625851729574.889, "dur": 1.394, + "args": { + "External id": 3718972,"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": 1625851729585.289, "dur": 6.272, + "args": { + "External id": 3718973,"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": 1625851729587.037, "dur": 4.250, + "args": { + "External id": 3718974,"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": 1625851729670.511, "dur": 233.629, + "args": { + "External id": 3718975,"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": 1625851729675.104, "dur": 17.406, + "args": { + "External id": 3718976,"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": 1625851729713.248, "dur": 190.497, + "args": { + "External id": 3718977,"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": 1625851729714.744, "dur": 0.466, + "args": { + "External id": 3718978,"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": 1625851729716.440, "dur": 27.152, + "args": { + "External id": 3718979,"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": 1625851729745.137, "dur": 5.550, + "args": { + "External id": 3718980,"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": 1625851729749.323, "dur": 1.041, + "args": { + "External id": 3718981,"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": 1625851729753.977, "dur": 22.242, + "args": { + "External id": 3718982,"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": 1625851729755.022, "dur": 2.015, + "args": { + "External id": 3718983,"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": 1625851729758.208, "dur": 17.755, + "args": { + "External id": 3718984,"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": 1625851729760.952, "dur": 2.768, + "args": { + "External id": 3718985,"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": 1625851729777.795, "dur": 22.664, + "args": { + "External id": 3718986,"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": 1625851729801.877, "dur": 16.460, + "args": { + "External id": 3718987,"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": 1625851729821.201, "dur": 15.427, + "args": { + "External id": 3718988,"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": 1625851729838.029, "dur": 13.186, + "args": { + "External id": 3718989,"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": 1625851729852.967, "dur": 22.989, + "args": { + "External id": 3718990,"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": 1625851729856.799, "dur": 1.433, + "args": { + "External id": 3718991,"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": 1625851729860.455, "dur": 0.825, + "args": { + "External id": 3718992,"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": 1625851729877.276, "dur": 12.882, + "args": { + "External id": 3718993,"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": 1625851729891.218, "dur": 11.699, + "args": { + "External id": 3718994,"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": 1625851729911.669, "dur": 2.156, + "args": { + "External id": 3718995,"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": 1625851729922.889, "dur": 3.457, + "args": { + "External id": 3718996,"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": 1625851729925.319, "dur": 0.360, + "args": { + "External id": 3718997,"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": 1625851730036.129, "dur": 92.171, + "args": { + "External id": 3718998,"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": 1625851730134.514, "dur": 5.263, + "args": { + "External id": 3718999,"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": 1625851730137.657, "dur": 0.953, + "args": { + "External id": 3719000,"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": 1625851730141.212, "dur": 28.865, + "args": { + "External id": 3719001,"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": 1625851730175.304, "dur": 8.340, + "args": { + "External id": 3719002,"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": 1625851730177.155, "dur": 5.831, + "args": { + "External id": 3719003,"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": 1625851730181.385, "dur": 1.395, + "args": { + "External id": 3719004,"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": 1625851730186.589, "dur": 58.158, + "args": { + "External id": 3719005,"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": 1625851730191.605, "dur": 52.424, + "args": { + "External id": 3719006,"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": 1625851730248.342, "dur": 17.333, + "args": { + "External id": 3719007,"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": 1625851730271.294, "dur": 4.427, + "args": { + "External id": 3719008,"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": 1625851730273.501, "dur": 1.268, + "args": { + "External id": 3719009,"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": 1625851730279.694, "dur": 51.961, + "args": { + "External id": 3719010,"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": 1625851730282.940, "dur": 4.107, + "args": { + "External id": 3719011,"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": 1625851730283.637, "dur": 2.840, + "args": { + "External id": 3719012,"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": 1625851730285.212, "dur": 1.150, + "args": { + "External id": 3719013,"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": 1625851730287.809, "dur": 43.480, + "args": { + "External id": 3719014,"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": 1625851730288.526, "dur": 42.278, + "args": { + "External id": 3719015,"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": 1625851730335.260, "dur": 3.811, + "args": { + "External id": 3719016,"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": 1625851730337.151, "dur": 0.841, + "args": { + "External id": 3719017,"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": 1625851730347.564, "dur": 1.473, + "args": { + "External id": 3719018,"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": 1625851730356.472, "dur": 8.723, + "args": { + "External id": 3719019,"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": 1625851730358.489, "dur": 6.379, + "args": { + "External id": 3719020,"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": 1625851730456.470, "dur": 188.823, + "args": { + "External id": 3719021,"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": 1625851730458.601, "dur": 1.909, + "args": { + "External id": 3719022,"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": 1625851730464.044, "dur": 180.804, + "args": { + "External id": 3719023,"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": 1625851730465.535, "dur": 0.271, + "args": { + "External id": 3719024,"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": 1625851730467.171, "dur": 24.650, + "args": { + "External id": 3719025,"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": 1625851730493.226, "dur": 3.295, + "args": { + "External id": 3719026,"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": 1625851730495.290, "dur": 0.984, + "args": { + "External id": 3719027,"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": 1625851730497.379, "dur": 23.224, + "args": { + "External id": 3719028,"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": 1625851730498.119, "dur": 1.507, + "args": { + "External id": 3719029,"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": 1625851730500.681, "dur": 19.650, + "args": { + "External id": 3719030,"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": 1625851730505.664, "dur": 2.162, + "args": { + "External id": 3719031,"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": 1625851730524.465, "dur": 21.638, + "args": { + "External id": 3719032,"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": 1625851730547.617, "dur": 13.975, + "args": { + "External id": 3719033,"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": 1625851730564.480, "dur": 14.159, + "args": { + "External id": 3719034,"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": 1625851730580.011, "dur": 13.778, + "args": { + "External id": 3719035,"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": 1625851730595.615, "dur": 19.656, + "args": { + "External id": 3719036,"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": 1625851730597.171, "dur": 1.156, + "args": { + "External id": 3719037,"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": 1625851730600.686, "dur": 0.841, + "args": { + "External id": 3719038,"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": 1625851730616.541, "dur": 13.437, + "args": { + "External id": 3719039,"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": 1625851730633.452, "dur": 10.363, + "args": { + "External id": 3719040,"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": 1625851730651.128, "dur": 1.636, + "args": { + "External id": 3719041,"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": 1625851730660.681, "dur": 3.533, + "args": { + "External id": 3719042,"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": 1625851730662.965, "dur": 0.531, + "args": { + "External id": 3719043,"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": 1625851730750.360, "dur": 55.986, + "args": { + "External id": 3719044,"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": 1625851730811.587, "dur": 5.488, + "args": { + "External id": 3719045,"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": 1625851730814.293, "dur": 1.518, + "args": { + "External id": 3719046,"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": 1625851730818.526, "dur": 24.963, + "args": { + "External id": 3719047,"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": 1625851730850.378, "dur": 5.553, + "args": { + "External id": 3719048,"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": 1625851730851.680, "dur": 3.639, + "args": { + "External id": 3719049,"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": 1625851730853.979, "dur": 1.168, + "args": { + "External id": 3719050,"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": 1625851730858.370, "dur": 41.559, + "args": { + "External id": 3719051,"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": 1625851730859.692, "dur": 39.452, + "args": { + "External id": 3719052,"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": 1625851730903.505, "dur": 15.267, + "args": { + "External id": 3719053,"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": 1625851730924.761, "dur": 5.141, + "args": { + "External id": 3719054,"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": 1625851730928.514, "dur": 0.654, + "args": { + "External id": 3719055,"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": 1625851730933.609, "dur": 86.293, + "args": { + "External id": 3719056,"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": 1625851730934.278, "dur": 5.806, + "args": { + "External id": 3719057,"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": 1625851730935.080, "dur": 4.433, + "args": { + "External id": 3719058,"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": 1625851730936.653, "dur": 2.685, + "args": { + "External id": 3719059,"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": 1625851730940.759, "dur": 78.478, + "args": { + "External id": 3719060,"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": 1625851730943.501, "dur": 74.739, + "args": { + "External id": 3719061,"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": 1625851731026.477, "dur": 4.864, + "args": { + "External id": 3719062,"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": 1625851731028.939, "dur": 1.097, + "args": { + "External id": 3719063,"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": 1625851731038.091, "dur": 1.826, + "args": { + "External id": 3719064,"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": 1625851731047.127, "dur": 7.108, + "args": { + "External id": 3719065,"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": 1625851731049.182, "dur": 4.725, + "args": { + "External id": 3719066,"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": 1625851731144.406, "dur": 200.461, + "args": { + "External id": 3719067,"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": 1625851731147.009, "dur": 2.447, + "args": { + "External id": 3719068,"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": 1625851731159.323, "dur": 185.127, + "args": { + "External id": 3719069,"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": 1625851731160.716, "dur": 0.340, + "args": { + "External id": 3719070,"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": 1625851731164.721, "dur": 24.663, + "args": { + "External id": 3719071,"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": 1625851731190.864, "dur": 3.253, + "args": { + "External id": 3719072,"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": 1625851731192.893, "dur": 0.968, + "args": { + "External id": 3719073,"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": 1625851731194.923, "dur": 26.687, + "args": { + "External id": 3719074,"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": 1625851731198.273, "dur": 3.407, + "args": { + "External id": 3719075,"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": 1625851731202.838, "dur": 18.507, + "args": { + "External id": 3719076,"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": 1625851731205.594, "dur": 2.989, + "args": { + "External id": 3719077,"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": 1625851731222.866, "dur": 21.510, + "args": { + "External id": 3719078,"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": 1625851731245.620, "dur": 13.456, + "args": { + "External id": 3719079,"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": 1625851731261.664, "dur": 15.975, + "args": { + "External id": 3719080,"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": 1625851731278.940, "dur": 13.862, + "args": { + "External id": 3719081,"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": 1625851731294.442, "dur": 22.074, + "args": { + "External id": 3719082,"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": 1625851731295.995, "dur": 1.253, + "args": { + "External id": 3719083,"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": 1625851731301.766, "dur": 0.769, + "args": { + "External id": 3719084,"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": 1625851731317.844, "dur": 12.688, + "args": { + "External id": 3719085,"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": 1625851731331.678, "dur": 11.909, + "args": { + "External id": 3719086,"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": 1625851731350.401, "dur": 1.393, + "args": { + "External id": 3719087,"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": 1625851731358.999, "dur": 3.470, + "args": { + "External id": 3719088,"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": 1625851731361.498, "dur": 0.340, + "args": { + "External id": 3719089,"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": 1625851731422.020, "dur": 52.931, + "args": { + "External id": 3719090,"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": 1625851731479.397, "dur": 6.321, + "args": { + "External id": 3719091,"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": 1625851731483.777, "dur": 1.062, + "args": { + "External id": 3719092,"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": 1625851731487.120, "dur": 25.274, + "args": { + "External id": 3719093,"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": 1625851731516.598, "dur": 7.028, + "args": { + "External id": 3719094,"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": 1625851731518.110, "dur": 4.884, + "args": { + "External id": 3719095,"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": 1625851731519.948, "dur": 2.852, + "args": { + "External id": 3719096,"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": 1625851731526.208, "dur": 42.445, + "args": { + "External id": 3719097,"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": 1625851731529.385, "dur": 38.381, + "args": { + "External id": 3719098,"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": 1625851731572.507, "dur": 15.167, + "args": { + "External id": 3719099,"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": 1625851731592.938, "dur": 3.585, + "args": { + "External id": 3719100,"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": 1625851731595.120, "dur": 0.622, + "args": { + "External id": 3719101,"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": 1625851731600.229, "dur": 59.237, + "args": { + "External id": 3719102,"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": 1625851731601.147, "dur": 6.164, + "args": { + "External id": 3719103,"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": 1625851731602.033, "dur": 4.676, + "args": { + "External id": 3719104,"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": 1625851731605.672, "dur": 0.919, + "args": { + "External id": 3719105,"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": 1625851731617.387, "dur": 41.719, + "args": { + "External id": 3719106,"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": 1625851731618.318, "dur": 40.150, + "args": { + "External id": 3719107,"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": 1625851731663.124, "dur": 3.570, + "args": { + "External id": 3719108,"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": 1625851731665.029, "dur": 0.598, + "args": { + "External id": 3719109,"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": 1625851731671.693, "dur": 1.268, + "args": { + "External id": 3719110,"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": 1625851731699.095, "dur": 9.145, + "args": { + "External id": 3719111,"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": 1625851731701.069, "dur": 6.752, + "args": { + "External id": 3719112,"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": 1625851731793.863, "dur": 186.484, + "args": { + "External id": 3719113,"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": 1625851731796.008, "dur": 2.564, + "args": { + "External id": 3719114,"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": 1625851731799.706, "dur": 180.246, + "args": { + "External id": 3719115,"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": 1625851731800.903, "dur": 0.212, + "args": { + "External id": 3719116,"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": 1625851731804.671, "dur": 24.295, + "args": { + "External id": 3719117,"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": 1625851731830.349, "dur": 3.554, + "args": { + "External id": 3719118,"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": 1625851731832.624, "dur": 1.055, + "args": { + "External id": 3719119,"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": 1625851731834.819, "dur": 24.395, + "args": { + "External id": 3719120,"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": 1625851731835.515, "dur": 1.835, + "args": { + "External id": 3719121,"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": 1625851731838.701, "dur": 20.209, + "args": { + "External id": 3719122,"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": 1625851731843.644, "dur": 2.899, + "args": { + "External id": 3719123,"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": 1625851731860.585, "dur": 20.968, + "args": { + "External id": 3719124,"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": 1625851731882.761, "dur": 14.427, + "args": { + "External id": 3719125,"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": 1625851731899.614, "dur": 13.607, + "args": { + "External id": 3719126,"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": 1625851731914.488, "dur": 13.762, + "args": { + "External id": 3719127,"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": 1625851731932.030, "dur": 20.884, + "args": { + "External id": 3719128,"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": 1625851731933.523, "dur": 1.995, + "args": { + "External id": 3719129,"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": 1625851731937.821, "dur": 0.960, + "args": { + "External id": 3719130,"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": 1625851731954.031, "dur": 13.138, + "args": { + "External id": 3719131,"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": 1625851731968.162, "dur": 10.863, + "args": { + "External id": 3719132,"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": 1625851732024.680, "dur": 2.451, + "args": { + "External id": 3719133,"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": 1625851732036.519, "dur": 4.097, + "args": { + "External id": 3719134,"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": 1625851732039.311, "dur": 0.475, + "args": { + "External id": 3719135,"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": 1625851732108.897, "dur": 55.847, + "args": { + "External id": 3719136,"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": 1625851732169.477, "dur": 5.195, + "args": { + "External id": 3719137,"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": 1625851732172.188, "dur": 1.561, + "args": { + "External id": 3719138,"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": 1625851732176.024, "dur": 24.337, + "args": { + "External id": 3719139,"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": 1625851732204.816, "dur": 7.895, + "args": { + "External id": 3719140,"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": 1625851732206.410, "dur": 5.399, + "args": { + "External id": 3719141,"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": 1625851732210.663, "dur": 0.921, + "args": { + "External id": 3719142,"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": 1625851732215.130, "dur": 41.234, + "args": { + "External id": 3719143,"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": 1625851732216.341, "dur": 39.453, + "args": { + "External id": 3719144,"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": 1625851732260.009, "dur": 18.708, + "args": { + "External id": 3719145,"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": 1625851732283.708, "dur": 3.564, + "args": { + "External id": 3719146,"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": 1625851732285.363, "dur": 1.093, + "args": { + "External id": 3719147,"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": 1625851732293.005, "dur": 48.885, + "args": { + "External id": 3719148,"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": 1625851732294.015, "dur": 5.339, + "args": { + "External id": 3719149,"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": 1625851732294.760, "dur": 4.010, + "args": { + "External id": 3719150,"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": 1625851732296.063, "dur": 2.533, + "args": { + "External id": 3719151,"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": 1625851732300.105, "dur": 41.309, + "args": { + "External id": 3719152,"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": 1625851732300.971, "dur": 39.658, + "args": { + "External id": 3719153,"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": 1625851732345.682, "dur": 3.792, + "args": { + "External id": 3719154,"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": 1625851732347.540, "dur": 0.903, + "args": { + "External id": 3719155,"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": 1625851732356.464, "dur": 1.564, + "args": { + "External id": 3719156,"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": 1625851732364.300, "dur": 6.342, + "args": { + "External id": 3719157,"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": 1625851732366.248, "dur": 4.067, + "args": { + "External id": 3719158,"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": 1625851732443.654, "dur": 206.266, + "args": { + "External id": 3719159,"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": 1625851732445.859, "dur": 2.065, + "args": { + "External id": 3719160,"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": 1625851732448.859, "dur": 200.667, + "args": { + "External id": 3719161,"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": 1625851732451.978, "dur": 0.263, + "args": { + "External id": 3719162,"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": 1625851732455.877, "dur": 21.353, + "args": { + "External id": 3719163,"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": 1625851732478.458, "dur": 3.530, + "args": { + "External id": 3719164,"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": 1625851732480.686, "dur": 1.123, + "args": { + "External id": 3719165,"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": 1625851732482.894, "dur": 48.523, + "args": { + "External id": 3719166,"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": 1625851732483.626, "dur": 3.016, + "args": { + "External id": 3719167,"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": 1625851732487.604, "dur": 43.536, + "args": { + "External id": 3719168,"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": 1625851732515.540, "dur": 2.735, + "args": { + "External id": 3719169,"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": 1625851732532.686, "dur": 21.011, + "args": { + "External id": 3719170,"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": 1625851732554.823, "dur": 13.171, + "args": { + "External id": 3719171,"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": 1625851732573.197, "dur": 13.934, + "args": { + "External id": 3719172,"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": 1625851732588.390, "dur": 12.881, + "args": { + "External id": 3719173,"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": 1625851732602.927, "dur": 19.372, + "args": { + "External id": 3719174,"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": 1625851732604.275, "dur": 1.245, + "args": { + "External id": 3719175,"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": 1625851732607.638, "dur": 0.704, + "args": { + "External id": 3719176,"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": 1625851732623.421, "dur": 12.687, + "args": { + "External id": 3719177,"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": 1625851732637.010, "dur": 11.635, + "args": { + "External id": 3719178,"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": 1625851732658.341, "dur": 1.324, + "args": { + "External id": 3719179,"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": 1625851732667.054, "dur": 3.512, + "args": { + "External id": 3719180,"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": 1625851732669.241, "dur": 0.287, + "args": { + "External id": 3719181,"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": 1625851732751.213, "dur": 55.261, + "args": { + "External id": 3719182,"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": 1625851732811.324, "dur": 5.360, + "args": { + "External id": 3719183,"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": 1625851732814.066, "dur": 1.323, + "args": { + "External id": 3719184,"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": 1625851732818.110, "dur": 26.063, + "args": { + "External id": 3719185,"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": 1625851732848.910, "dur": 9.286, + "args": { + "External id": 3719186,"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": 1625851732852.750, "dur": 4.840, + "args": { + "External id": 3719187,"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": 1625851732854.686, "dur": 2.728, + "args": { + "External id": 3719188,"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": 1625851732860.890, "dur": 38.177, + "args": { + "External id": 3719189,"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": 1625851732861.833, "dur": 36.555, + "args": { + "External id": 3719190,"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": 1625851732902.454, "dur": 15.165, + "args": { + "External id": 3719191,"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": 1625851732923.298, "dur": 5.636, + "args": { + "External id": 3719192,"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": 1625851732927.386, "dur": 0.827, + "args": { + "External id": 3719193,"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": 1625851732932.511, "dur": 46.483, + "args": { + "External id": 3719194,"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": 1625851732933.111, "dur": 3.804, + "args": { + "External id": 3719195,"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": 1625851732933.590, "dur": 2.617, + "args": { + "External id": 3719196,"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": 1625851732935.413, "dur": 0.670, + "args": { + "External id": 3719197,"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": 1625851732937.396, "dur": 41.131, + "args": { + "External id": 3719198,"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": 1625851732938.518, "dur": 39.519, + "args": { + "External id": 3719199,"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": 1625851733021.254, "dur": 4.971, + "args": { + "External id": 3719200,"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": 1625851733023.774, "dur": 0.964, + "args": { + "External id": 3719201,"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": 1625851733033.355, "dur": 1.389, + "args": { + "External id": 3719202,"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": 1625851733041.593, "dur": 6.970, + "args": { + "External id": 3719203,"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": 1625851733043.265, "dur": 5.022, + "args": { + "External id": 3719204,"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": 1625851733138.079, "dur": 196.039, + "args": { + "External id": 3719205,"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": 1625851733140.257, "dur": 2.253, + "args": { + "External id": 3719206,"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": 1625851733145.778, "dur": 187.974, + "args": { + "External id": 3719207,"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": 1625851733147.235, "dur": 0.289, + "args": { + "External id": 3719208,"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": 1625851733148.902, "dur": 23.437, + "args": { + "External id": 3719209,"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": 1625851733173.741, "dur": 6.327, + "args": { + "External id": 3719210,"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": 1625851733175.994, "dur": 3.786, + "args": { + "External id": 3719211,"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": 1625851733181.287, "dur": 23.833, + "args": { + "External id": 3719212,"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": 1625851733182.185, "dur": 1.488, + "args": { + "External id": 3719213,"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": 1625851733186.934, "dur": 17.918, + "args": { + "External id": 3719214,"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": 1625851733189.736, "dur": 2.516, + "args": { + "External id": 3719215,"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": 1625851733206.406, "dur": 21.564, + "args": { + "External id": 3719216,"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": 1625851733229.251, "dur": 14.054, + "args": { + "External id": 3719217,"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": 1625851733246.254, "dur": 14.228, + "args": { + "External id": 3719218,"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": 1625851733261.759, "dur": 12.996, + "args": { + "External id": 3719219,"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": 1625851733276.341, "dur": 20.124, + "args": { + "External id": 3719220,"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": 1625851733278.336, "dur": 1.169, + "args": { + "External id": 3719221,"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": 1625851733281.262, "dur": 0.630, + "args": { + "External id": 3719222,"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": 1625851733305.024, "dur": 12.565, + "args": { + "External id": 3719223,"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": 1625851733318.566, "dur": 14.152, + "args": { + "External id": 3719224,"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": 1625851733340.163, "dur": 1.673, + "args": { + "External id": 3719225,"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": 1625851733349.982, "dur": 3.496, + "args": { + "External id": 3719226,"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": 1625851733352.365, "dur": 0.431, + "args": { + "External id": 3719227,"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": 1625851733417.308, "dur": 51.957, + "args": { + "External id": 3719228,"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": 1625851733474.052, "dur": 8.613, + "args": { + "External id": 3719229,"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": 1625851733479.065, "dur": 2.477, + "args": { + "External id": 3719230,"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": 1625851733483.980, "dur": 23.615, + "args": { + "External id": 3719231,"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": 1625851733512.136, "dur": 5.238, + "args": { + "External id": 3719232,"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": 1625851733513.609, "dur": 3.195, + "args": { + "External id": 3719233,"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": 1625851733515.250, "dur": 1.193, + "args": { + "External id": 3719234,"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": 1625851733519.706, "dur": 40.714, + "args": { + "External id": 3719235,"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": 1625851733520.743, "dur": 38.956, + "args": { + "External id": 3719236,"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": 1625851733566.332, "dur": 15.798, + "args": { + "External id": 3719237,"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": 1625851733586.779, "dur": 24.401, + "args": { + "External id": 3719238,"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": 1625851733588.931, "dur": 21.859, + "args": { + "External id": 3719239,"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": 1625851733593.959, "dur": 0.920, + "args": { + "External id": 3719240,"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": 1625851733615.798, "dur": 28.231, + "args": { + "External id": 3719241,"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": 1625851733617.555, "dur": 26.269, + "args": { + "External id": 3719242,"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": 1625851733622.103, "dur": 3.940, + "args": { + "External id": 3719243,"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": 1625851733627.138, "dur": 16.151, + "args": { + "External id": 3719244,"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": 1625851733657.090, "dur": 7.145, + "args": { + "External id": 3719245,"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": 1625851733661.271, "dur": 2.698, + "args": { + "External id": 3719246,"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": 1625851733665.376, "dur": 1.246, + "args": { + "External id": 3719247,"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": 1625851733665.814, "dur": 0.531, + "args": { + "External id": 3719248,"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": 1625851733729.196, "dur": 24.403, + "args": { + "External id": 3719249,"Sequence number": 37295292, "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": 1625851733756.015, "dur": 15.143, + "args": { + "External id": 3719250,"Sequence number": 37295293, "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": 1625851733756.015, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::slice", "pid": 1336756, "tid": 1336756, + "ts": 1625851733779.506, "dur": 6.307, + "args": { + "External id": 3719251,"Sequence number": 37295294, "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": 1625851733783.147, "dur": 1.316, + "args": { + "External id": 3719252,"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": 1625851733788.327, "dur": 11.808, + "args": { + "External id": 3719253,"Sequence number": 37295294, "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": 1625851733797.831, "dur": 0.994, + "args": { + "External id": 3719254,"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": 1625851733801.734, "dur": 2.993, + "args": { + "External id": 3719255,"Sequence number": 37295294, "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": 1625851733803.307, "dur": 0.835, + "args": { + "External id": 3719256,"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": 1625851733809.213, "dur": 8.475, + "args": { + "External id": 3719257,"Sequence number": 37295294, "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": 1625851733809.213, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1625851733814.953, "dur": 1.438, + "args": { + "External id": 3719258,"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": 1625851733818.714, "dur": 5.594, + "args": { + "External id": 3719259,"Sequence number": 37295295, "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": 1625851733818.714, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1625851733822.342, "dur": 1.161, + "args": { + "External id": 3719260,"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": 1625851733825.227, "dur": 7.026, + "args": { + "External id": 3719261,"Sequence number": 37295296, "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": 1625851733825.227, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1625851733830.458, "dur": 0.856, + "args": { + "External id": 3719262,"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": 1625851733833.265, "dur": 5.597, + "args": { + "External id": 3719263,"Sequence number": 37295297, "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": 1625851733833.265, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::as_strided", "pid": 1336756, "tid": 1336756, + "ts": 1625851733835.982, "dur": 2.053, + "args": { + "External id": 3719264,"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": 1625851733843.001, "dur": 30.818, + "args": { + "External id": 3719265,"Sequence number": 37295298, "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": 1625851733844.577, "dur": 29.001, + "args": { + "External id": 3719266,"Sequence number": 37295298, "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": 1625851733846.960, "dur": 6.860, + "args": { + "External id": 3719267,"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": 1625851733849.639, "dur": 3.669, + "args": { + "External id": 3719268,"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": 1625851733854.659, "dur": 18.414, + "args": { + "External id": 3719269,"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": 1625851733899.622, "dur": 3.828, + "args": { + "External id": 3719270,"Sequence number": 37295298, "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": 1625851733899.622, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::view", "pid": 1336756, "tid": 1336756, + "ts": 1625851733908.170, "dur": 1.395, + "args": { + "External id": 3719271,"Sequence number": 37295299, "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": 1625851733942.048, "dur": 43868.149, + "args": { + "External id": 3719272,"Sequence number": 37295299, "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": 1625851733942.048, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::contiguous", "pid": 1336756, "tid": 1336756, + "ts": 1625851733956.160, "dur": 27.672, + "args": { + "External id": 3719273,"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": 1625851733956.987, "dur": 26.633, + "args": { + "External id": 3719274,"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": 1625851733958.569, "dur": 7.484, + "args": { + "External id": 3719275,"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": 1625851733959.738, "dur": 5.923, + "args": { + "External id": 3719276,"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": 1625851733966.787, "dur": 16.167, + "args": { + "External id": 3719277,"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": 1625851734038.137, "dur": 32.126, + "args": { + "External id": 3719278,"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": 1625851734039.214, "dur": 8.285, + "args": { + "External id": 3719279,"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": 1625851734041.622, "dur": 5.359, + "args": { + "External id": 3719280,"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": 1625851734050.883, "dur": 19.173, + "args": { + "External id": 3719281,"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": 1625851734052.613, "dur": 17.040, + "args": { + "External id": 3719282,"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": 1625851734074.147, "dur": 19.968, + "args": { + "External id": 3719283,"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": 1625851734075.091, "dur": 4.500, + "args": { + "External id": 3719284,"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": 1625851734076.417, "dur": 2.949, + "args": { + "External id": 3719285,"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": 1625851734080.215, "dur": 13.722, + "args": { + "External id": 3719286,"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": 1625851734080.716, "dur": 12.831, + "args": { + "External id": 3719287,"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": 1625851734099.894, "dur": 20.897, + "args": { + "External id": 3719288,"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": 1625851734101.221, "dur": 3.366, + "args": { + "External id": 3719289,"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": 1625851734107.275, "dur": 13.259, + "args": { + "External id": 3719290,"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": 1625851734108.047, "dur": 12.189, + "args": { + "External id": 3719291,"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": 1625851734125.421, "dur": 22.054, + "args": { + "External id": 3719292,"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": 1625851734150.198, "dur": 51.278, + "args": { + "External id": 3719293,"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": 1625851734152.464, "dur": 48.558, + "args": { + "External id": 3719294,"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": 1625851734159.723, "dur": 0.895, + "args": { + "External id": 3719295,"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": 1625851734161.693, "dur": 23.908, + "args": { + "External id": 3719296,"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": 1625851734163.156, "dur": 22.261, + "args": { + "External id": 3719297,"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": 1625851734166.145, "dur": 3.072, + "args": { + "External id": 3719298,"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": 1625851734170.138, "dur": 14.964, + "args": { + "External id": 3719299,"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": 1625851734204.929, "dur": 37953.728, + "args": { + "External id": 3719300,"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": 1625851734206.656, "dur": 37949.525, + "args": { + "External id": 3719301,"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": 1625851772176.024, "dur": 8.381, + "args": { + "External id": 3719302,"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": 1625851772181.177, "dur": 1.085, + "args": { + "External id": 3719303,"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": 1625851772189.871, "dur": 109.443, + "args": { + "External id": 3719304,"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": 1625851772191.480, "dur": 8.946, + "args": { + "External id": 3719305,"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": 1625851772193.890, "dur": 5.605, + "args": { + "External id": 3719306,"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": 1625851772197.957, "dur": 1.288, + "args": { + "External id": 3719307,"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": 1625851772201.709, "dur": 96.938, + "args": { + "External id": 3719308,"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": 1625851772203.413, "dur": 94.354, + "args": { + "External id": 3719309,"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": 1625851772303.001, "dur": 4.758, + "args": { + "External id": 3719310,"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": 1625851772305.237, "dur": 1.117, + "args": { + "External id": 3719311,"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": 1625851772314.811, "dur": 2.792, + "args": { + "External id": 3719312,"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": 1625851772326.644, "dur": 9.046, + "args": { + "External id": 3719313,"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": 1625851772330.898, "dur": 4.520, + "args": { + "External id": 3719314,"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": 1625851772467.864, "dur": 228.892, + "args": { + "External id": 3719315,"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": 1625851772472.695, "dur": 2.365, + "args": { + "External id": 3719316,"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": 1625851772476.790, "dur": 219.519, + "args": { + "External id": 3719317,"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": 1625851772478.102, "dur": 0.415, + "args": { + "External id": 3719318,"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": 1625851772479.704, "dur": 27.919, + "args": { + "External id": 3719319,"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": 1625851772509.202, "dur": 6.226, + "args": { + "External id": 3719320,"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": 1625851772513.963, "dur": 0.885, + "args": { + "External id": 3719321,"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": 1625851772519.003, "dur": 25.844, + "args": { + "External id": 3719322,"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": 1625851772520.461, "dur": 1.867, + "args": { + "External id": 3719323,"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": 1625851772523.781, "dur": 20.812, + "args": { + "External id": 3719324,"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": 1625851772527.320, "dur": 3.400, + "args": { + "External id": 3719325,"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": 1625851772546.493, "dur": 25.285, + "args": { + "External id": 3719326,"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": 1625851772573.802, "dur": 15.895, + "args": { + "External id": 3719327,"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": 1625851772592.814, "dur": 16.245, + "args": { + "External id": 3719328,"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": 1625851772610.551, "dur": 14.458, + "args": { + "External id": 3719329,"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": 1625851772626.516, "dur": 24.644, + "args": { + "External id": 3719330,"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": 1625851772630.858, "dur": 1.704, + "args": { + "External id": 3719331,"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": 1625851772634.411, "dur": 1.045, + "args": { + "External id": 3719332,"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": 1625851772652.628, "dur": 13.346, + "args": { + "External id": 3719333,"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": 1625851772667.513, "dur": 26.692, + "args": { + "External id": 3719334,"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": 1625851772705.181, "dur": 2.676, + "args": { + "External id": 3719335,"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": 1625851772715.722, "dur": 4.280, + "args": { + "External id": 3719336,"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": 1625851772717.951, "dur": 0.968, + "args": { + "External id": 3719337,"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": 1625851772802.275, "dur": 69.809, + "args": { + "External id": 3719338,"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": 1625851772877.523, "dur": 5.736, + "args": { + "External id": 3719339,"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": 1625851772880.229, "dur": 0.974, + "args": { + "External id": 3719340,"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": 1625851772884.998, "dur": 28.513, + "args": { + "External id": 3719341,"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": 1625851772919.212, "dur": 8.175, + "args": { + "External id": 3719342,"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": 1625851772921.015, "dur": 5.806, + "args": { + "External id": 3719343,"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": 1625851772925.023, "dur": 1.578, + "args": { + "External id": 3719344,"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": 1625851772930.454, "dur": 43.863, + "args": { + "External id": 3719345,"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": 1625851772931.755, "dur": 41.996, + "args": { + "External id": 3719346,"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": 1625851772978.540, "dur": 52.567, + "args": { + "External id": 3719347,"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": 1625851773040.266, "dur": 4.622, + "args": { + "External id": 3719348,"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": 1625851773042.800, "dur": 0.807, + "args": { + "External id": 3719349,"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": 1625851773049.529, "dur": 55.149, + "args": { + "External id": 3719350,"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": 1625851773052.574, "dur": 4.049, + "args": { + "External id": 3719351,"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": 1625851773053.758, "dur": 2.369, + "args": { + "External id": 3719352,"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": 1625851773055.194, "dur": 0.782, + "args": { + "External id": 3719353,"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": 1625851773057.463, "dur": 46.763, + "args": { + "External id": 3719354,"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": 1625851773058.369, "dur": 45.240, + "args": { + "External id": 3719355,"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": 1625851773108.792, "dur": 6.593, + "args": { + "External id": 3719356,"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": 1625851773110.864, "dur": 3.377, + "args": { + "External id": 3719357,"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": 1625851773124.088, "dur": 1.889, + "args": { + "External id": 3719358,"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": 1625851773134.342, "dur": 6.689, + "args": { + "External id": 3719359,"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": 1625851773136.586, "dur": 4.168, + "args": { + "External id": 3719360,"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": 1625851773236.810, "dur": 194.776, + "args": { + "External id": 3719361,"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": 1625851773238.838, "dur": 2.640, + "args": { + "External id": 3719362,"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": 1625851773245.156, "dur": 186.019, + "args": { + "External id": 3719363,"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": 1625851773246.320, "dur": 0.225, + "args": { + "External id": 3719364,"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": 1625851773247.782, "dur": 25.188, + "args": { + "External id": 3719365,"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": 1625851773274.738, "dur": 2.907, + "args": { + "External id": 3719366,"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": 1625851773276.525, "dur": 0.907, + "args": { + "External id": 3719367,"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": 1625851773278.549, "dur": 24.526, + "args": { + "External id": 3719368,"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": 1625851773279.807, "dur": 1.745, + "args": { + "External id": 3719369,"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": 1625851773282.761, "dur": 20.046, + "args": { + "External id": 3719370,"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": 1625851773287.458, "dur": 2.921, + "args": { + "External id": 3719371,"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": 1625851773306.828, "dur": 23.252, + "args": { + "External id": 3719372,"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": 1625851773331.709, "dur": 13.924, + "args": { + "External id": 3719373,"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": 1625851773348.102, "dur": 15.012, + "args": { + "External id": 3719374,"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": 1625851773364.696, "dur": 13.591, + "args": { + "External id": 3719375,"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": 1625851773379.931, "dur": 20.679, + "args": { + "External id": 3719376,"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": 1625851773382.033, "dur": 1.672, + "args": { + "External id": 3719377,"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": 1625851773385.309, "dur": 0.844, + "args": { + "External id": 3719378,"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": 1625851773402.033, "dur": 13.545, + "args": { + "External id": 3719379,"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": 1625851773418.821, "dur": 11.422, + "args": { + "External id": 3719380,"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": 1625851773437.473, "dur": 1.523, + "args": { + "External id": 3719381,"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": 1625851773447.264, "dur": 3.365, + "args": { + "External id": 3719382,"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": 1625851773449.335, "dur": 0.599, + "args": { + "External id": 3719383,"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": 1625851773515.172, "dur": 51.040, + "args": { + "External id": 3719384,"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": 1625851773570.763, "dur": 4.905, + "args": { + "External id": 3719385,"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": 1625851773573.286, "dur": 1.123, + "args": { + "External id": 3719386,"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": 1625851773577.173, "dur": 24.050, + "args": { + "External id": 3719387,"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": 1625851773607.816, "dur": 4.526, + "args": { + "External id": 3719388,"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": 1625851773609.203, "dur": 2.529, + "args": { + "External id": 3719389,"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": 1625851773610.653, "dur": 0.876, + "args": { + "External id": 3719390,"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": 1625851773615.119, "dur": 40.268, + "args": { + "External id": 3719391,"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": 1625851773616.029, "dur": 38.701, + "args": { + "External id": 3719392,"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": 1625851773658.957, "dur": 14.787, + "args": { + "External id": 3719393,"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": 1625851773695.338, "dur": 7.270, + "args": { + "External id": 3719394,"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": 1625851773700.155, "dur": 1.210, + "args": { + "External id": 3719395,"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": 1625851773706.931, "dur": 57.035, + "args": { + "External id": 3719396,"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": 1625851773708.040, "dur": 6.229, + "args": { + "External id": 3719397,"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": 1625851773708.822, "dur": 4.933, + "args": { + "External id": 3719398,"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": 1625851773712.800, "dur": 0.797, + "args": { + "External id": 3719399,"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": 1625851773714.908, "dur": 48.703, + "args": { + "External id": 3719400,"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": 1625851773717.594, "dur": 45.215, + "args": { + "External id": 3719401,"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": 1625851773767.974, "dur": 3.636, + "args": { + "External id": 3719402,"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": 1625851773769.761, "dur": 0.803, + "args": { + "External id": 3719403,"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": 1625851773777.204, "dur": 1.712, + "args": { + "External id": 3719404,"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": 1625851773785.710, "dur": 6.039, + "args": { + "External id": 3719405,"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": 1625851773787.479, "dur": 4.018, + "args": { + "External id": 3719406,"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": 1625851773878.132, "dur": 230.976, + "args": { + "External id": 3719407,"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": 1625851773880.270, "dur": 2.250, + "args": { + "External id": 3719408,"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": 1625851773884.173, "dur": 224.530, + "args": { + "External id": 3719409,"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": 1625851773888.058, "dur": 0.276, + "args": { + "External id": 3719410,"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": 1625851773889.444, "dur": 24.511, + "args": { + "External id": 3719411,"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": 1625851773915.750, "dur": 3.485, + "args": { + "External id": 3719412,"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": 1625851773917.771, "dur": 1.246, + "args": { + "External id": 3719413,"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": 1625851773920.161, "dur": 25.928, + "args": { + "External id": 3719414,"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": 1625851773923.561, "dur": 1.504, + "args": { + "External id": 3719415,"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": 1625851773926.302, "dur": 19.383, + "args": { + "External id": 3719416,"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": 1625851773929.063, "dur": 3.087, + "args": { + "External id": 3719417,"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": 1625851773949.785, "dur": 20.145, + "args": { + "External id": 3719418,"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": 1625851773971.348, "dur": 49.156, + "args": { + "External id": 3719419,"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": 1625851774024.584, "dur": 16.490, + "args": { + "External id": 3719420,"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": 1625851774042.391, "dur": 14.048, + "args": { + "External id": 3719421,"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": 1625851774058.204, "dur": 21.184, + "args": { + "External id": 3719422,"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": 1625851774060.632, "dur": 1.791, + "args": { + "External id": 3719423,"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": 1625851774064.297, "dur": 0.765, + "args": { + "External id": 3719424,"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": 1625851774083.273, "dur": 12.324, + "args": { + "External id": 3719425,"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": 1625851774096.616, "dur": 11.010, + "args": { + "External id": 3719426,"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": 1625851774116.727, "dur": 2.107, + "args": { + "External id": 3719427,"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": 1625851774127.597, "dur": 3.376, + "args": { + "External id": 3719428,"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": 1625851774129.786, "dur": 0.414, + "args": { + "External id": 3719429,"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": 1625851774207.053, "dur": 87.070, + "args": { + "External id": 3719430,"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": 1625851774298.851, "dur": 6.337, + "args": { + "External id": 3719431,"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": 1625851774301.353, "dur": 2.834, + "args": { + "External id": 3719432,"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": 1625851774309.317, "dur": 36.707, + "args": { + "External id": 3719433,"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": 1625851774350.439, "dur": 5.463, + "args": { + "External id": 3719434,"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": 1625851774351.945, "dur": 3.190, + "args": { + "External id": 3719435,"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": 1625851774353.628, "dur": 1.120, + "args": { + "External id": 3719436,"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": 1625851774358.328, "dur": 53.184, + "args": { + "External id": 3719437,"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": 1625851774359.293, "dur": 51.704, + "args": { + "External id": 3719438,"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": 1625851774415.337, "dur": 14.746, + "args": { + "External id": 3719439,"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": 1625851774437.511, "dur": 3.859, + "args": { + "External id": 3719440,"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": 1625851774439.740, "dur": 0.867, + "args": { + "External id": 3719441,"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": 1625851774444.989, "dur": 49.128, + "args": { + "External id": 3719442,"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": 1625851774445.766, "dur": 3.297, + "args": { + "External id": 3719443,"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": 1625851774446.402, "dur": 2.155, + "args": { + "External id": 3719444,"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": 1625851774447.577, "dur": 0.860, + "args": { + "External id": 3719445,"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": 1625851774451.837, "dur": 41.878, + "args": { + "External id": 3719446,"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": 1625851774452.470, "dur": 40.591, + "args": { + "External id": 3719447,"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": 1625851774498.115, "dur": 3.746, + "args": { + "External id": 3719448,"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": 1625851774499.868, "dur": 0.936, + "args": { + "External id": 3719449,"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": 1625851774506.447, "dur": 1.428, + "args": { + "External id": 3719450,"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": 1625851774515.178, "dur": 8.447, + "args": { + "External id": 3719451,"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": 1625851774518.924, "dur": 4.461, + "args": { + "External id": 3719452,"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": 1625851774601.471, "dur": 225.393, + "args": { + "External id": 3719453,"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": 1625851774603.261, "dur": 4.148, + "args": { + "External id": 3719454,"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": 1625851774609.136, "dur": 217.043, + "args": { + "External id": 3719455,"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": 1625851774610.383, "dur": 0.274, + "args": { + "External id": 3719456,"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": 1625851774626.327, "dur": 21.193, + "args": { + "External id": 3719457,"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": 1625851774649.276, "dur": 5.371, + "args": { + "External id": 3719458,"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": 1625851774653.580, "dur": 0.826, + "args": { + "External id": 3719459,"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": 1625851774657.742, "dur": 37.327, + "args": { + "External id": 3719460,"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": 1625851774659.129, "dur": 1.402, + "args": { + "External id": 3719461,"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": 1625851774661.601, "dur": 32.843, + "args": { + "External id": 3719462,"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": 1625851774663.985, "dur": 2.427, + "args": { + "External id": 3719463,"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": 1625851774697.011, "dur": 24.697, + "args": { + "External id": 3719464,"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": 1625851774723.084, "dur": 16.468, + "args": { + "External id": 3719465,"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": 1625851774742.335, "dur": 16.062, + "args": { + "External id": 3719466,"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": 1625851774759.600, "dur": 13.488, + "args": { + "External id": 3719467,"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": 1625851774774.640, "dur": 22.825, + "args": { + "External id": 3719468,"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": 1625851774779.042, "dur": 1.473, + "args": { + "External id": 3719469,"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": 1625851774782.087, "dur": 1.167, + "args": { + "External id": 3719470,"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": 1625851774798.751, "dur": 13.568, + "args": { + "External id": 3719471,"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": 1625851774813.379, "dur": 11.765, + "args": { + "External id": 3719472,"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": 1625851774833.424, "dur": 2.411, + "args": { + "External id": 3719473,"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": 1625851774844.277, "dur": 3.533, + "args": { + "External id": 3719474,"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": 1625851774846.623, "dur": 0.500, + "args": { + "External id": 3719475,"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": 1625851774909.482, "dur": 54.102, + "args": { + "External id": 3719476,"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": 1625851774971.248, "dur": 4.346, + "args": { + "External id": 3719477,"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": 1625851774973.725, "dur": 0.860, + "args": { + "External id": 3719478,"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": 1625851774976.917, "dur": 60.051, + "args": { + "External id": 3719479,"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": 1625851775043.453, "dur": 6.425, + "args": { + "External id": 3719480,"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": 1625851775044.760, "dur": 4.253, + "args": { + "External id": 3719481,"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": 1625851775046.962, "dur": 1.853, + "args": { + "External id": 3719482,"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": 1625851775055.405, "dur": 44.013, + "args": { + "External id": 3719483,"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": 1625851775056.664, "dur": 42.273, + "args": { + "External id": 3719484,"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": 1625851775103.206, "dur": 15.967, + "args": { + "External id": 3719485,"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": 1625851775125.313, "dur": 4.075, + "args": { + "External id": 3719486,"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": 1625851775127.473, "dur": 1.085, + "args": { + "External id": 3719487,"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": 1625851775133.190, "dur": 48.917, + "args": { + "External id": 3719488,"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": 1625851775134.140, "dur": 5.860, + "args": { + "External id": 3719489,"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": 1625851775137.151, "dur": 2.382, + "args": { + "External id": 3719490,"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": 1625851775138.460, "dur": 0.947, + "args": { + "External id": 3719491,"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": 1625851775140.493, "dur": 41.211, + "args": { + "External id": 3719492,"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": 1625851775141.068, "dur": 40.025, + "args": { + "External id": 3719493,"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": 1625851775186.096, "dur": 4.123, + "args": { + "External id": 3719494,"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": 1625851775188.264, "dur": 0.924, + "args": { + "External id": 3719495,"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": 1625851775195.984, "dur": 1.644, + "args": { + "External id": 3719496,"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": 1625851775207.064, "dur": 8.743, + "args": { + "External id": 3719497,"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": 1625851775208.970, "dur": 6.575, + "args": { + "External id": 3719498,"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": 1625851775298.573, "dur": 191.988, + "args": { + "External id": 3719499,"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": 1625851775300.697, "dur": 2.419, + "args": { + "External id": 3719500,"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": 1625851775304.700, "dur": 185.409, + "args": { + "External id": 3719501,"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": 1625851775305.945, "dur": 0.296, + "args": { + "External id": 3719502,"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": 1625851775307.309, "dur": 24.251, + "args": { + "External id": 3719503,"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": 1625851775335.552, "dur": 3.275, + "args": { + "External id": 3719504,"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": 1625851775337.604, "dur": 0.981, + "args": { + "External id": 3719505,"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": 1625851775344.872, "dur": 25.023, + "args": { + "External id": 3719506,"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": 1625851775346.875, "dur": 3.908, + "args": { + "External id": 3719507,"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": 1625851775351.789, "dur": 17.862, + "args": { + "External id": 3719508,"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": 1625851775354.583, "dur": 2.725, + "args": { + "External id": 3719509,"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": 1625851775371.056, "dur": 21.223, + "args": { + "External id": 3719510,"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": 1625851775393.708, "dur": 14.830, + "args": { + "External id": 3719511,"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": 1625851775410.993, "dur": 13.862, + "args": { + "External id": 3719512,"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": 1625851775426.198, "dur": 13.435, + "args": { + "External id": 3719513,"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": 1625851775443.651, "dur": 19.699, + "args": { + "External id": 3719514,"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": 1625851775445.628, "dur": 1.349, + "args": { + "External id": 3719515,"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": 1625851775448.646, "dur": 0.785, + "args": { + "External id": 3719516,"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": 1625851775464.484, "dur": 13.144, + "args": { + "External id": 3719517,"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": 1625851775478.539, "dur": 10.800, + "args": { + "External id": 3719518,"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": 1625851775496.527, "dur": 1.698, + "args": { + "External id": 3719519,"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": 1625851775506.501, "dur": 3.422, + "args": { + "External id": 3719520,"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": 1625851775508.615, "dur": 0.513, + "args": { + "External id": 3719521,"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": 1625851775573.445, "dur": 50.116, + "args": { + "External id": 3719522,"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": 1625851775628.267, "dur": 4.940, + "args": { + "External id": 3719523,"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": 1625851775630.861, "dur": 1.348, + "args": { + "External id": 3719524,"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": 1625851775634.454, "dur": 22.215, + "args": { + "External id": 3719525,"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": 1625851775660.766, "dur": 8.805, + "args": { + "External id": 3719526,"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": 1625851775661.789, "dur": 7.096, + "args": { + "External id": 3719527,"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": 1625851775665.519, "dur": 3.155, + "args": { + "External id": 3719528,"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": 1625851775671.795, "dur": 64.437, + "args": { + "External id": 3719529,"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": 1625851775672.647, "dur": 62.402, + "args": { + "External id": 3719530,"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": 1625851775741.699, "dur": 15.602, + "args": { + "External id": 3719531,"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": 1625851775763.520, "dur": 4.576, + "args": { + "External id": 3719532,"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": 1625851775766.093, "dur": 1.029, + "args": { + "External id": 3719533,"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": 1625851775771.585, "dur": 50.029, + "args": { + "External id": 3719534,"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": 1625851775774.878, "dur": 4.066, + "args": { + "External id": 3719535,"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": 1625851775775.927, "dur": 2.546, + "args": { + "External id": 3719536,"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": 1625851775777.391, "dur": 0.942, + "args": { + "External id": 3719537,"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": 1625851775779.478, "dur": 41.739, + "args": { + "External id": 3719538,"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": 1625851775780.110, "dur": 40.611, + "args": { + "External id": 3719539,"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": 1625851775825.893, "dur": 3.339, + "args": { + "External id": 3719540,"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": 1625851775827.771, "dur": 0.566, + "args": { + "External id": 3719541,"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": 1625851775836.931, "dur": 1.707, + "args": { + "External id": 3719542,"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": 1625851775846.436, "dur": 6.327, + "args": { + "External id": 3719543,"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": 1625851775848.121, "dur": 4.391, + "args": { + "External id": 3719544,"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": 1625851775937.648, "dur": 233.617, + "args": { + "External id": 3719545,"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": 1625851775939.554, "dur": 2.276, + "args": { + "External id": 3719546,"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": 1625851775947.591, "dur": 223.188, + "args": { + "External id": 3719547,"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": 1625851775948.630, "dur": 0.486, + "args": { + "External id": 3719548,"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": 1625851775949.914, "dur": 21.197, + "args": { + "External id": 3719549,"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": 1625851775972.806, "dur": 4.654, + "args": { + "External id": 3719550,"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": 1625851775974.510, "dur": 2.666, + "args": { + "External id": 3719551,"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": 1625851775978.476, "dur": 61.957, + "args": { + "External id": 3719552,"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": 1625851775979.607, "dur": 36.471, + "args": { + "External id": 3719553,"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": 1625851776018.354, "dur": 21.805, + "args": { + "External id": 3719554,"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": 1625851776021.823, "dur": 3.214, + "args": { + "External id": 3719555,"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": 1625851776041.750, "dur": 21.894, + "args": { + "External id": 3719556,"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": 1625851776065.120, "dur": 14.597, + "args": { + "External id": 3719557,"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": 1625851776084.734, "dur": 15.557, + "args": { + "External id": 3719558,"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": 1625851776101.605, "dur": 13.701, + "args": { + "External id": 3719559,"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": 1625851776116.692, "dur": 22.872, + "args": { + "External id": 3719560,"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": 1625851776118.646, "dur": 1.812, + "args": { + "External id": 3719561,"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": 1625851776122.173, "dur": 2.716, + "args": { + "External id": 3719562,"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": 1625851776140.857, "dur": 13.380, + "args": { + "External id": 3719563,"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": 1625851776157.309, "dur": 12.461, + "args": { + "External id": 3719564,"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": 1625851776178.450, "dur": 1.912, + "args": { + "External id": 3719565,"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": 1625851776189.709, "dur": 3.348, + "args": { + "External id": 3719566,"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": 1625851776191.878, "dur": 0.357, + "args": { + "External id": 3719567,"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": 1625851776259.652, "dur": 55.433, + "args": { + "External id": 3719568,"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": 1625851776319.723, "dur": 4.659, + "args": { + "External id": 3719569,"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": 1625851776322.212, "dur": 1.266, + "args": { + "External id": 3719570,"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": 1625851776325.668, "dur": 25.570, + "args": { + "External id": 3719571,"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": 1625851776358.026, "dur": 5.529, + "args": { + "External id": 3719572,"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": 1625851776359.502, "dur": 3.455, + "args": { + "External id": 3719573,"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": 1625851776361.330, "dur": 1.449, + "args": { + "External id": 3719574,"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": 1625851776366.006, "dur": 39.538, + "args": { + "External id": 3719575,"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": 1625851776366.911, "dur": 38.056, + "args": { + "External id": 3719576,"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": 1625851776409.202, "dur": 15.172, + "args": { + "External id": 3719577,"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": 1625851776429.489, "dur": 6.008, + "args": { + "External id": 3719578,"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": 1625851776434.025, "dur": 0.794, + "args": { + "External id": 3719579,"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": 1625851776438.804, "dur": 49.527, + "args": { + "External id": 3719580,"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": 1625851776439.689, "dur": 3.736, + "args": { + "External id": 3719581,"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": 1625851776440.341, "dur": 2.603, + "args": { + "External id": 3719582,"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": 1625851776441.973, "dur": 0.821, + "args": { + "External id": 3719583,"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": 1625851776443.894, "dur": 44.013, + "args": { + "External id": 3719584,"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": 1625851776447.130, "dur": 40.287, + "args": { + "External id": 3719585,"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": 1625851776492.125, "dur": 3.633, + "args": { + "External id": 3719586,"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": 1625851776494.328, "dur": 0.558, + "args": { + "External id": 3719587,"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": 1625851776500.215, "dur": 1.472, + "args": { + "External id": 3719588,"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": 1625851776508.745, "dur": 5.679, + "args": { + "External id": 3719589,"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": 1625851776510.432, "dur": 3.720, + "args": { + "External id": 3719590,"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": 1625851776592.223, "dur": 211.135, + "args": { + "External id": 3719591,"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": 1625851776596.400, "dur": 2.010, + "args": { + "External id": 3719592,"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": 1625851776599.607, "dur": 203.252, + "args": { + "External id": 3719593,"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": 1625851776600.870, "dur": 0.391, + "args": { + "External id": 3719594,"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": 1625851776602.616, "dur": 20.520, + "args": { + "External id": 3719595,"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": 1625851776624.806, "dur": 5.520, + "args": { + "External id": 3719596,"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": 1625851776628.924, "dur": 1.208, + "args": { + "External id": 3719597,"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": 1625851776631.254, "dur": 22.644, + "args": { + "External id": 3719598,"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": 1625851776632.440, "dur": 1.616, + "args": { + "External id": 3719599,"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": 1625851776635.000, "dur": 18.653, + "args": { + "External id": 3719600,"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": 1625851776639.504, "dur": 2.263, + "args": { + "External id": 3719601,"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": 1625851776655.185, "dur": 19.471, + "args": { + "External id": 3719602,"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": 1625851776675.605, "dur": 40.051, + "args": { + "External id": 3719603,"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": 1625851776719.183, "dur": 14.825, + "args": { + "External id": 3719604,"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": 1625851776735.194, "dur": 13.104, + "args": { + "External id": 3719605,"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": 1625851776750.047, "dur": 22.737, + "args": { + "External id": 3719606,"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": 1625851776753.929, "dur": 1.454, + "args": { + "External id": 3719607,"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": 1625851776757.541, "dur": 0.814, + "args": { + "External id": 3719608,"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": 1625851776776.298, "dur": 14.047, + "args": { + "External id": 3719609,"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": 1625851776791.291, "dur": 10.553, + "args": { + "External id": 3719610,"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": 1625851776809.847, "dur": 1.919, + "args": { + "External id": 3719611,"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": 1625851776819.477, "dur": 3.510, + "args": { + "External id": 3719612,"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": 1625851776821.844, "dur": 0.325, + "args": { + "External id": 3719613,"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": 1625851776883.656, "dur": 50.167, + "args": { + "External id": 3719614,"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": 1625851776938.437, "dur": 3.938, + "args": { + "External id": 3719615,"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": 1625851776940.842, "dur": 0.633, + "args": { + "External id": 3719616,"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": 1625851776946.062, "dur": 22.201, + "args": { + "External id": 3719617,"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": 1625851776972.360, "dur": 5.959, + "args": { + "External id": 3719618,"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": 1625851776973.765, "dur": 3.997, + "args": { + "External id": 3719619,"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": 1625851776975.964, "dur": 1.587, + "args": { + "External id": 3719620,"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": 1625851777014.592, "dur": 48.392, + "args": { + "External id": 3719621,"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": 1625851777015.713, "dur": 46.346, + "args": { + "External id": 3719622,"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": 1625851777067.379, "dur": 16.407, + "args": { + "External id": 3719623,"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": 1625851777091.975, "dur": 4.488, + "args": { + "External id": 3719624,"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": 1625851777094.355, "dur": 1.186, + "args": { + "External id": 3719625,"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": 1625851777099.927, "dur": 48.866, + "args": { + "External id": 3719626,"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": 1625851777100.916, "dur": 3.669, + "args": { + "External id": 3719627,"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": 1625851777101.753, "dur": 2.320, + "args": { + "External id": 3719628,"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": 1625851777103.260, "dur": 0.680, + "args": { + "External id": 3719629,"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": 1625851777107.444, "dur": 40.893, + "args": { + "External id": 3719630,"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": 1625851777107.914, "dur": 39.950, + "args": { + "External id": 3719631,"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": 1625851777152.725, "dur": 3.500, + "args": { + "External id": 3719632,"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": 1625851777154.476, "dur": 0.800, + "args": { + "External id": 3719633,"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": 1625851777161.960, "dur": 1.626, + "args": { + "External id": 3719634,"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": 1625851777170.540, "dur": 8.901, + "args": { + "External id": 3719635,"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": 1625851777174.803, "dur": 4.389, + "args": { + "External id": 3719636,"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": 1625851777258.701, "dur": 187.609, + "args": { + "External id": 3719637,"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": 1625851777262.701, "dur": 2.107, + "args": { + "External id": 3719638,"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": 1625851777265.881, "dur": 180.038, + "args": { + "External id": 3719639,"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": 1625851777267.065, "dur": 0.285, + "args": { + "External id": 3719640,"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": 1625851777268.400, "dur": 22.016, + "args": { + "External id": 3719641,"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": 1625851777292.021, "dur": 5.248, + "args": { + "External id": 3719642,"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": 1625851777296.079, "dur": 0.957, + "args": { + "External id": 3719643,"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": 1625851777300.413, "dur": 21.853, + "args": { + "External id": 3719644,"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": 1625851777301.446, "dur": 1.664, + "args": { + "External id": 3719645,"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": 1625851777304.161, "dur": 17.887, + "args": { + "External id": 3719646,"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": 1625851777306.814, "dur": 2.521, + "args": { + "External id": 3719647,"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": 1625851777323.481, "dur": 21.309, + "args": { + "External id": 3719648,"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": 1625851777345.904, "dur": 16.505, + "args": { + "External id": 3719649,"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": 1625851777364.774, "dur": 14.942, + "args": { + "External id": 3719650,"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": 1625851777380.854, "dur": 13.537, + "args": { + "External id": 3719651,"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": 1625851777395.687, "dur": 22.866, + "args": { + "External id": 3719652,"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": 1625851777400.116, "dur": 1.282, + "args": { + "External id": 3719653,"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": 1625851777403.381, "dur": 0.881, + "args": { + "External id": 3719654,"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": 1625851777419.689, "dur": 12.860, + "args": { + "External id": 3719655,"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": 1625851777433.521, "dur": 11.526, + "args": { + "External id": 3719656,"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": 1625851777451.385, "dur": 1.776, + "args": { + "External id": 3719657,"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": 1625851777460.549, "dur": 3.129, + "args": { + "External id": 3719658,"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": 1625851777462.391, "dur": 0.560, + "args": { + "External id": 3719659,"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": 1625851777522.706, "dur": 48.599, + "args": { + "External id": 3719660,"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": 1625851777578.468, "dur": 4.435, + "args": { + "External id": 3719661,"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": 1625851777580.979, "dur": 0.966, + "args": { + "External id": 3719662,"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": 1625851777584.219, "dur": 25.097, + "args": { + "External id": 3719663,"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": 1625851777613.489, "dur": 4.810, + "args": { + "External id": 3719664,"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": 1625851777614.857, "dur": 2.957, + "args": { + "External id": 3719665,"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": 1625851777616.483, "dur": 1.125, + "args": { + "External id": 3719666,"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": 1625851777622.627, "dur": 38.146, + "args": { + "External id": 3719667,"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": 1625851777623.736, "dur": 36.420, + "args": { + "External id": 3719668,"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": 1625851777664.137, "dur": 31.589, + "args": { + "External id": 3719669,"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": 1625851777702.152, "dur": 28.292, + "args": { + "External id": 3719670,"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": 1625851777704.729, "dur": 25.291, + "args": { + "External id": 3719671,"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": 1625851777709.998, "dur": 2.780, + "args": { + "External id": 3719672,"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": 1625851777735.104, "dur": 32.150, + "args": { + "External id": 3719673,"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": 1625851777736.880, "dur": 30.156, + "args": { + "External id": 3719674,"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": 1625851777741.491, "dur": 4.349, + "args": { + "External id": 3719675,"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": 1625851777749.718, "dur": 16.833, + "args": { + "External id": 3719676,"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": 1625851777780.808, "dur": 5.286, + "args": { + "External id": 3719677,"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": 1625851777782.894, "dur": 2.943, + "args": { + "External id": 3719678,"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": 1625851777787.071, "dur": 1.106, + "args": { + "External id": 3719679,"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": 1625851777787.558, "dur": 0.540, + "args": { + "External id": 3719680,"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": 1625851777867.249, "dur": 26.240, + "args": { + "External id": 3719681,"Sequence number": 37295300, "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": 1625851777895.414, "dur": 14.161, + "args": { + "External id": 3719682,"Sequence number": 37295301, "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": 1625851777895.414, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "user_annotation", "name": "FSDP::post_forward", "pid": 1336756, "tid": 1336756, + "ts": 1625851778057.327, "dur": 43.694, + "args": { + "External id": 3719683,"Record function id": 0, "Ev Idx": 10394 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::div", "pid": 1336756, "tid": 1336756, + "ts": 1625851778233.745, "dur": 40.058, + "args": { + "External id": 3719684,"Sequence number": 37295302, "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": 1625851778233.745, + "cat": "fwdbwd", "name": "fwdbwd" + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::ones_like", "pid": 1336756, "tid": 1336756, + "ts": 1625851778310.746, "dur": 27.201, + "args": { + "External id": 3719685,"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": 1625851778312.240, "dur": 8.300, + "args": { + "External id": 3719686,"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": 1625851778315.713, "dur": 4.241, + "args": { + "External id": 3719687,"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": 1625851778321.913, "dur": 15.679, + "args": { + "External id": 3719688,"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": 1625853102059.313, "dur": 51.887, + "args": { + "External id": 3719689,"Sequence number": 37295303, "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": 1625853102120.824, "dur": 19.460, + "args": { + "External id": 3719690,"Sequence number": 37295304, "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": 1625853102147.929, "dur": 25.725, + "args": { + "External id": 3719691,"Sequence number": 37295305, "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": 1625853102798.632, "dur": 27.972, + "args": { + "External id": 3719692,"Sequence number": 37295306, "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": 1625853102833.093, "dur": 14.919, + "args": { + "External id": 3719693,"Sequence number": 37295307, "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": 1625853104927.555, "dur": 3034.885, + "args": { + "External id": 3719694,"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": 1625853105517.364, "dur": 979.321, + "args": { + "External id": 3719695,"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": 1625853105536.329, "dur": 59.292, + "args": { + "External id": 3719696,"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": 1625853105539.560, "dur": 11.210, + "args": { + "External id": 3719697,"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": 1625853105553.251, "dur": 42.089, + "args": { + "External id": 3719698,"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": 1625853105555.542, "dur": 38.904, + "args": { + "External id": 3719699,"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": 1625853108018.198, "dur": 3.474, + "args": { + "External id": 3719700,"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": 1625853108024.051, "dur": 0.501, + "args": { + "External id": 3719701,"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": 1625853108025.717, "dur": 0.424, + "args": { + "External id": 3719702,"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": 1625853108027.423, "dur": 0.396, + "args": { + "External id": 3719703,"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": 1625853108028.879, "dur": 0.534, + "args": { + "External id": 3719704,"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": 1625853108033.783, "dur": 0.480, + "args": { + "External id": 3719705,"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": 1625853108035.363, "dur": 0.366, + "args": { + "External id": 3719706,"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": 1625853108039.199, "dur": 0.363, + "args": { + "External id": 3719707,"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": 1625853108040.555, "dur": 0.337, + "args": { + "External id": 3719708,"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": 1625853108042.010, "dur": 0.320, + "args": { + "External id": 3719709,"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": 1625853108043.577, "dur": 0.406, + "args": { + "External id": 3719710,"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": 1625853108044.995, "dur": 0.353, + "args": { + "External id": 3719711,"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": 1625853108046.467, "dur": 0.365, + "args": { + "External id": 3719712,"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": 1625853108047.839, "dur": 0.540, + "args": { + "External id": 3719713,"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": 1625853108049.379, "dur": 0.251, + "args": { + "External id": 3719714,"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": 1625853108052.762, "dur": 0.240, + "args": { + "External id": 3719715,"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": 1625853108053.827, "dur": 0.517, + "args": { + "External id": 3719716,"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": 1625853108055.631, "dur": 0.218, + "args": { + "External id": 3719717,"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": 1625853108056.708, "dur": 0.230, + "args": { + "External id": 3719718,"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": 1625853108057.896, "dur": 0.229, + "args": { + "External id": 3719719,"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": 1625853108059.059, "dur": 0.224, + "args": { + "External id": 3719720,"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": 1625853108060.241, "dur": 0.224, + "args": { + "External id": 3719721,"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": 1625853108061.743, "dur": 0.242, + "args": { + "External id": 3719722,"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": 1625853108065.376, "dur": 0.249, + "args": { + "External id": 3719723,"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": 1625853108066.643, "dur": 0.239, + "args": { + "External id": 3719724,"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": 1625853108068.132, "dur": 0.429, + "args": { + "External id": 3719725,"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": 1625853108069.321, "dur": 0.320, + "args": { + "External id": 3719726,"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": 1625853108070.627, "dur": 0.214, + "args": { + "External id": 3719727,"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": 1625853108071.591, "dur": 0.323, + "args": { + "External id": 3719728,"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": 1625853108072.656, "dur": 0.345, + "args": { + "External id": 3719729,"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": 1625853108074.109, "dur": 0.337, + "args": { + "External id": 3719730,"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": 1625853108077.306, "dur": 0.352, + "args": { + "External id": 3719731,"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": 1625853108078.518, "dur": 0.230, + "args": { + "External id": 3719732,"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": 1625853108079.995, "dur": 0.440, + "args": { + "External id": 3719733,"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": 1625853108081.302, "dur": 0.372, + "args": { + "External id": 3719734,"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": 1625853108082.628, "dur": 0.215, + "args": { + "External id": 3719735,"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": 1625853108083.656, "dur": 0.220, + "args": { + "External id": 3719736,"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": 1625853108084.619, "dur": 0.213, + "args": { + "External id": 3719737,"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": 1625853108085.744, "dur": 0.218, + "args": { + "External id": 3719738,"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": 1625853108089.071, "dur": 0.225, + "args": { + "External id": 3719739,"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": 1625853108090.044, "dur": 0.221, + "args": { + "External id": 3719740,"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": 1625853108091.324, "dur": 0.217, + "args": { + "External id": 3719741,"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": 1625853108092.344, "dur": 0.220, + "args": { + "External id": 3719742,"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": 1625853108093.448, "dur": 0.222, + "args": { + "External id": 3719743,"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": 1625853108094.560, "dur": 0.218, + "args": { + "External id": 3719744,"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": 1625853108095.563, "dur": 0.248, + "args": { + "External id": 3719745,"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": 1625853108096.688, "dur": 0.224, + "args": { + "External id": 3719746,"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": 1625853108100.076, "dur": 0.218, + "args": { + "External id": 3719747,"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": 1625853108101.056, "dur": 0.223, + "args": { + "External id": 3719748,"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": 1625853108102.191, "dur": 0.232, + "args": { + "External id": 3719749,"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": 1625853108107.201, "dur": 0.226, + "args": { + "External id": 3719750,"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": 1625853108108.241, "dur": 0.203, + "args": { + "External id": 3719751,"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": 1625853108109.452, "dur": 0.234, + "args": { + "External id": 3719752,"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": 1625853108110.709, "dur": 0.218, + "args": { + "External id": 3719753,"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": 1625853108111.674, "dur": 0.226, + "args": { + "External id": 3719754,"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": 1625853108114.830, "dur": 0.220, + "args": { + "External id": 3719755,"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": 1625853108115.786, "dur": 0.226, + "args": { + "External id": 3719756,"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": 1625853108116.758, "dur": 0.214, + "args": { + "External id": 3719757,"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": 1625853108117.980, "dur": 0.226, + "args": { + "External id": 3719758,"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": 1625853108118.940, "dur": 0.217, + "args": { + "External id": 3719759,"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": 1625853108119.928, "dur": 0.219, + "args": { + "External id": 3719760,"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": 1625853108120.879, "dur": 0.311, + "args": { + "External id": 3719761,"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": 1625853108121.980, "dur": 0.215, + "args": { + "External id": 3719762,"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": 1625853108125.081, "dur": 0.332, + "args": { + "External id": 3719763,"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": 1625853108126.211, "dur": 0.399, + "args": { + "External id": 3719764,"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": 1625853108127.715, "dur": 0.351, + "args": { + "External id": 3719765,"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": 1625853108128.931, "dur": 0.367, + "args": { + "External id": 3719766,"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": 1625853108130.165, "dur": 0.214, + "args": { + "External id": 3719767,"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": 1625853108131.459, "dur": 0.222, + "args": { + "External id": 3719768,"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": 1625853108132.646, "dur": 0.179, + "args": { + "External id": 3719769,"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": 1625853108133.691, "dur": 0.367, + "args": { + "External id": 3719770,"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": 1625853108137.122, "dur": 0.230, + "args": { + "External id": 3719771,"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": 1625853108138.240, "dur": 0.223, + "args": { + "External id": 3719772,"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": 1625853108139.412, "dur": 0.229, + "args": { + "External id": 3719773,"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": 1625853108140.513, "dur": 0.245, + "args": { + "External id": 3719774,"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": 1625853108141.606, "dur": 0.219, + "args": { + "External id": 3719775,"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": 1625853108142.769, "dur": 0.223, + "args": { + "External id": 3719776,"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": 1625853108144.505, "dur": 0.213, + "args": { + "External id": 3719777,"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": 1625853108145.572, "dur": 0.221, + "args": { + "External id": 3719778,"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": 1625853108148.653, "dur": 0.225, + "args": { + "External id": 3719779,"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": 1625853108149.641, "dur": 0.222, + "args": { + "External id": 3719780,"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": 1625853108150.594, "dur": 0.218, + "args": { + "External id": 3719781,"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": 1625853108151.576, "dur": 0.225, + "args": { + "External id": 3719782,"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": 1625853108152.542, "dur": 0.216, + "args": { + "External id": 3719783,"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": 1625853108153.563, "dur": 0.229, + "args": { + "External id": 3719784,"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": 1625853108154.530, "dur": 0.214, + "args": { + "External id": 3719785,"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": 1625853108155.491, "dur": 0.220, + "args": { + "External id": 3719786,"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": 1625853108158.711, "dur": 0.217, + "args": { + "External id": 3719787,"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": 1625853108159.670, "dur": 0.253, + "args": { + "External id": 3719788,"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": 1625853108160.711, "dur": 0.218, + "args": { + "External id": 3719789,"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": 1625853108161.699, "dur": 0.221, + "args": { + "External id": 3719790,"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": 1625853108162.836, "dur": 0.218, + "args": { + "External id": 3719791,"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": 1625853108163.803, "dur": 0.222, + "args": { + "External id": 3719792,"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": 1625853108165.730, "dur": 0.215, + "args": { + "External id": 3719793,"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": 1625853108166.691, "dur": 0.226, + "args": { + "External id": 3719794,"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": 1625853108169.928, "dur": 0.223, + "args": { + "External id": 3719795,"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": 1625853108170.870, "dur": 0.223, + "args": { + "External id": 3719796,"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": 1625853108171.884, "dur": 0.214, + "args": { + "External id": 3719797,"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": 1625853108172.961, "dur": 0.315, + "args": { + "External id": 3719798,"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": 1625853108174.014, "dur": 0.217, + "args": { + "External id": 3719799,"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": 1625853108174.968, "dur": 0.352, + "args": { + "External id": 3719800,"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": 1625853108176.650, "dur": 0.176, + "args": { + "External id": 3719801,"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": 1625853108177.630, "dur": 0.321, + "args": { + "External id": 3719802,"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": 1625853108181.031, "dur": 0.221, + "args": { + "External id": 3719803,"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": 1625853108181.988, "dur": 0.323, + "args": { + "External id": 3719804,"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": 1625853108183.303, "dur": 0.347, + "args": { + "External id": 3719805,"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": 1625853108184.402, "dur": 0.345, + "args": { + "External id": 3719806,"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": 1625853108185.511, "dur": 0.216, + "args": { + "External id": 3719807,"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": 1625853108186.458, "dur": 0.350, + "args": { + "External id": 3719808,"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": 1625853108188.387, "dur": 0.405, + "args": { + "External id": 3719809,"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": 1625853108189.620, "dur": 0.572, + "args": { + "External id": 3719810,"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": 1625853108193.346, "dur": 0.224, + "args": { + "External id": 3719811,"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": 1625853108194.303, "dur": 0.221, + "args": { + "External id": 3719812,"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": 1625853108195.391, "dur": 0.227, + "args": { + "External id": 3719813,"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": 1625853108196.583, "dur": 0.226, + "args": { + "External id": 3719814,"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": 1625853108197.834, "dur": 0.216, + "args": { + "External id": 3719815,"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": 1625853108198.866, "dur": 0.228, + "args": { + "External id": 3719816,"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": 1625853108199.814, "dur": 0.220, + "args": { + "External id": 3719817,"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": 1625853108200.761, "dur": 0.230, + "args": { + "External id": 3719818,"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": 1625853108203.964, "dur": 0.216, + "args": { + "External id": 3719819,"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": 1625853108205.046, "dur": 0.222, + "args": { + "External id": 3719820,"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": 1625853108206.020, "dur": 0.222, + "args": { + "External id": 3719821,"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": 1625853108206.977, "dur": 0.222, + "args": { + "External id": 3719822,"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": 1625853108207.998, "dur": 0.219, + "args": { + "External id": 3719823,"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": 1625853108208.960, "dur": 0.222, + "args": { + "External id": 3719824,"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": 1625853108209.983, "dur": 0.219, + "args": { + "External id": 3719825,"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": 1625853108210.938, "dur": 0.224, + "args": { + "External id": 3719826,"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": 1625853108214.092, "dur": 0.223, + "args": { + "External id": 3719827,"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": 1625853108215.056, "dur": 0.222, + "args": { + "External id": 3719828,"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": 1625853108216.453, "dur": 0.212, + "args": { + "External id": 3719829,"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": 1625853108217.640, "dur": 0.252, + "args": { + "External id": 3719830,"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": 1625853108218.910, "dur": 0.237, + "args": { + "External id": 3719831,"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": 1625853108219.902, "dur": 0.220, + "args": { + "External id": 3719832,"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": 1625853108220.875, "dur": 0.313, + "args": { + "External id": 3719833,"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": 1625853108221.915, "dur": 0.328, + "args": { + "External id": 3719834,"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": 1625853108225.153, "dur": 0.222, + "args": { + "External id": 3719835,"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": 1625853108226.109, "dur": 0.322, + "args": { + "External id": 3719836,"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": 1625853108227.358, "dur": 0.239, + "args": { + "External id": 3719837,"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": 1625853108228.333, "dur": 0.234, + "args": { + "External id": 3719838,"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": 1625853108229.305, "dur": 0.217, + "args": { + "External id": 3719839,"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": 1625853108230.301, "dur": 0.333, + "args": { + "External id": 3719840,"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": 1625853108231.366, "dur": 0.218, + "args": { + "External id": 3719841,"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": 1625853108232.405, "dur": 0.218, + "args": { + "External id": 3719842,"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": 1625853108235.701, "dur": 0.232, + "args": { + "External id": 3719843,"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": 1625853108236.944, "dur": 0.252, + "args": { + "External id": 3719844,"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": 1625853108237.922, "dur": 0.219, + "args": { + "External id": 3719845,"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": 1625853108238.882, "dur": 0.222, + "args": { + "External id": 3719846,"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": 1625853108240.101, "dur": 0.218, + "args": { + "External id": 3719847,"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": 1625853108241.096, "dur": 0.219, + "args": { + "External id": 3719848,"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": 1625853108242.447, "dur": 0.420, + "args": { + "External id": 3719849,"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": 1625853108243.612, "dur": 0.222, + "args": { + "External id": 3719850,"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": 1625853108246.968, "dur": 0.217, + "args": { + "External id": 3719851,"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": 1625853108247.920, "dur": 0.222, + "args": { + "External id": 3719852,"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": 1625853108248.878, "dur": 0.214, + "args": { + "External id": 3719853,"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": 1625853108249.891, "dur": 0.223, + "args": { + "External id": 3719854,"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": 1625853108250.848, "dur": 0.216, + "args": { + "External id": 3719855,"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": 1625853108251.829, "dur": 0.231, + "args": { + "External id": 3719856,"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": 1625853108252.784, "dur": 0.219, + "args": { + "External id": 3719857,"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": 1625853108253.884, "dur": 0.226, + "args": { + "External id": 3719858,"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": 1625853108257.292, "dur": 0.219, + "args": { + "External id": 3719859,"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": 1625853108258.335, "dur": 0.225, + "args": { + "External id": 3719860,"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": 1625853108259.360, "dur": 0.219, + "args": { + "External id": 3719861,"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": 1625853108260.425, "dur": 0.222, + "args": { + "External id": 3719862,"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": 1625853108261.493, "dur": 0.216, + "args": { + "External id": 3719863,"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": 1625853108263.555, "dur": 0.241, + "args": { + "External id": 3719864,"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": 1625853108264.552, "dur": 0.203, + "args": { + "External id": 3719865,"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": 1625853108265.536, "dur": 0.203, + "args": { + "External id": 3719866,"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": 1625853108268.609, "dur": 0.217, + "args": { + "External id": 3719867,"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": 1625853108269.589, "dur": 0.226, + "args": { + "External id": 3719868,"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": 1625853108270.593, "dur": 0.213, + "args": { + "External id": 3719869,"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": 1625853108271.550, "dur": 0.244, + "args": { + "External id": 3719870,"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": 1625853108272.527, "dur": 0.211, + "args": { + "External id": 3719871,"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": 1625853108273.468, "dur": 0.450, + "args": { + "External id": 3719872,"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": 1625853108275.050, "dur": 0.341, + "args": { + "External id": 3719873,"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": 1625853108276.347, "dur": 0.329, + "args": { + "External id": 3719874,"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": 1625853108279.646, "dur": 0.309, + "args": { + "External id": 3719875,"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": 1625853108280.730, "dur": 0.338, + "args": { + "External id": 3719876,"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": 1625853108281.798, "dur": 0.326, + "args": { + "External id": 3719877,"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": 1625853108282.848, "dur": 0.331, + "args": { + "External id": 3719878,"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": 1625853108284.115, "dur": 0.402, + "args": { + "External id": 3719879,"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": 1625853108285.285, "dur": 0.351, + "args": { + "External id": 3719880,"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": 1625853108286.367, "dur": 0.330, + "args": { + "External id": 3719881,"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": 1625853108287.609, "dur": 0.351, + "args": { + "External id": 3719882,"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": 1625853108291.098, "dur": 0.247, + "args": { + "External id": 3719883,"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": 1625853108292.093, "dur": 0.225, + "args": { + "External id": 3719884,"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": 1625853108293.285, "dur": 0.230, + "args": { + "External id": 3719885,"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": 1625853108294.269, "dur": 0.220, + "args": { + "External id": 3719886,"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": 1625853108295.385, "dur": 0.224, + "args": { + "External id": 3719887,"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": 1625853108296.498, "dur": 0.233, + "args": { + "External id": 3719888,"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": 1625853108297.493, "dur": 0.220, + "args": { + "External id": 3719889,"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": 1625853108298.467, "dur": 0.224, + "args": { + "External id": 3719890,"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": 1625853108301.789, "dur": 0.215, + "args": { + "External id": 3719891,"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": 1625853108302.797, "dur": 0.220, + "args": { + "External id": 3719892,"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": 1625853108303.745, "dur": 0.217, + "args": { + "External id": 3719893,"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": 1625853108304.914, "dur": 0.223, + "args": { + "External id": 3719894,"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": 1625853108305.906, "dur": 0.218, + "args": { + "External id": 3719895,"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": 1625853108306.855, "dur": 0.221, + "args": { + "External id": 3719896,"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": 1625853108307.828, "dur": 0.218, + "args": { + "External id": 3719897,"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": 1625853108308.820, "dur": 0.223, + "args": { + "External id": 3719898,"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": 1625853108312.045, "dur": 0.216, + "args": { + "External id": 3719899,"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": 1625853108313.145, "dur": 0.218, + "args": { + "External id": 3719900,"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": 1625853108314.605, "dur": 0.217, + "args": { + "External id": 3719901,"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": 1625853108315.677, "dur": 0.217, + "args": { + "External id": 3719902,"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": 1625853108316.691, "dur": 0.216, + "args": { + "External id": 3719903,"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": 1625853108317.897, "dur": 0.218, + "args": { + "External id": 3719904,"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": 1625853108318.927, "dur": 0.226, + "args": { + "External id": 3719905,"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": 1625853108320.098, "dur": 0.272, + "args": { + "External id": 3719906,"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": 1625853108323.176, "dur": 0.229, + "args": { + "External id": 3719907,"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": 1625853108324.212, "dur": 0.241, + "args": { + "External id": 3719908,"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": 1625853108325.239, "dur": 0.218, + "args": { + "External id": 3719909,"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": 1625853108326.216, "dur": 0.226, + "args": { + "External id": 3719910,"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": 1625853108327.358, "dur": 0.224, + "args": { + "External id": 3719911,"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": 1625853108328.497, "dur": 0.229, + "args": { + "External id": 3719912,"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": 1625853108329.453, "dur": 0.215, + "args": { + "External id": 3719913,"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": 1625853108330.575, "dur": 0.228, + "args": { + "External id": 3719914,"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": 1625853108333.828, "dur": 0.225, + "args": { + "External id": 3719915,"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": 1625853108334.920, "dur": 0.222, + "args": { + "External id": 3719916,"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": 1625853108336.043, "dur": 0.216, + "args": { + "External id": 3719917,"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": 1625853108337.043, "dur": 0.219, + "args": { + "External id": 3719918,"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": 1625853108338.082, "dur": 0.223, + "args": { + "External id": 3719919,"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": 1625853108339.042, "dur": 0.471, + "args": { + "External id": 3719920,"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": 1625853108340.246, "dur": 0.313, + "args": { + "External id": 3719921,"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": 1625853108341.330, "dur": 0.357, + "args": { + "External id": 3719922,"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": 1625853108344.568, "dur": 0.380, + "args": { + "External id": 3719923,"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": 1625853108345.742, "dur": 0.356, + "args": { + "External id": 3719924,"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": 1625853108346.835, "dur": 0.353, + "args": { + "External id": 3719925,"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": 1625853108347.913, "dur": 0.354, + "args": { + "External id": 3719926,"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": 1625853108348.995, "dur": 0.213, + "args": { + "External id": 3719927,"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": 1625853108349.948, "dur": 0.395, + "args": { + "External id": 3719928,"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": 1625853108351.070, "dur": 0.353, + "args": { + "External id": 3719929,"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": 1625853108352.157, "dur": 0.351, + "args": { + "External id": 3719930,"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": 1625853108355.538, "dur": 0.220, + "args": { + "External id": 3719931,"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": 1625853108356.515, "dur": 0.221, + "args": { + "External id": 3719932,"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": 1625853108357.808, "dur": 0.215, + "args": { + "External id": 3719933,"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": 1625853108358.789, "dur": 0.232, + "args": { + "External id": 3719934,"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": 1625853108359.831, "dur": 0.220, + "args": { + "External id": 3719935,"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": 1625853108360.779, "dur": 0.221, + "args": { + "External id": 3719936,"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": 1625853108361.728, "dur": 0.215, + "args": { + "External id": 3719937,"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": 1625853108362.694, "dur": 0.226, + "args": { + "External id": 3719938,"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": 1625853108365.488, "dur": 0.222, + "args": { + "External id": 3719939,"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": 1625853108366.499, "dur": 0.227, + "args": { + "External id": 3719940,"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": 1625853108367.451, "dur": 0.212, + "args": { + "External id": 3719941,"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": 1625853108368.387, "dur": 0.220, + "args": { + "External id": 3719942,"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": 1625853108369.379, "dur": 0.215, + "args": { + "External id": 3719943,"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": 1625853108370.476, "dur": 0.245, + "args": { + "External id": 3719944,"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": 1625853108371.610, "dur": 0.569, + "args": { + "External id": 3719945,"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": 1625853108373.170, "dur": 0.218, + "args": { + "External id": 3719946,"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": 1625853108376.502, "dur": 0.221, + "args": { + "External id": 3719947,"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": 1625853108377.568, "dur": 0.364, + "args": { + "External id": 3719948,"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": 1625853108378.691, "dur": 0.356, + "args": { + "External id": 3719949,"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": 1625853108379.769, "dur": 0.347, + "args": { + "External id": 3719950,"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": 1625853108381.065, "dur": 0.216, + "args": { + "External id": 3719951,"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": 1625853108382.006, "dur": 0.556, + "args": { + "External id": 3719952,"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": 1625853108383.288, "dur": 0.645, + "args": { + "External id": 3719953,"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": 1625853108384.847, "dur": 0.233, + "args": { + "External id": 3719954,"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": 1625853108387.770, "dur": 0.212, + "args": { + "External id": 3719955,"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": 1625853108388.710, "dur": 0.224, + "args": { + "External id": 3719956,"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": 1625853108389.710, "dur": 0.213, + "args": { + "External id": 3719957,"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": 1625853108390.843, "dur": 0.223, + "args": { + "External id": 3719958,"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": 1625853108391.993, "dur": 0.213, + "args": { + "External id": 3719959,"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": 1625853108392.982, "dur": 0.224, + "args": { + "External id": 3719960,"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": 1625853108398.244, "dur": 0.213, + "args": { + "External id": 3719961,"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": 1625853108399.332, "dur": 0.301, + "args": { + "External id": 3719962,"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": 1625853108402.635, "dur": 0.211, + "args": { + "External id": 3719963,"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": 1625853108403.588, "dur": 0.222, + "args": { + "External id": 3719964,"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": 1625853108404.630, "dur": 0.233, + "args": { + "External id": 3719965,"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": 1625853108405.618, "dur": 0.223, + "args": { + "External id": 3719966,"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": 1625853108406.753, "dur": 0.215, + "args": { + "External id": 3719967,"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": 1625853108407.690, "dur": 0.227, + "args": { + "External id": 3719968,"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": 1625853108415.001, "dur": 0.294, + "args": { + "External id": 3719969,"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": 1625853108416.105, "dur": 0.221, + "args": { + "External id": 3719970,"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": 1625853108419.327, "dur": 0.219, + "args": { + "External id": 3719971,"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": 1625853108420.270, "dur": 0.221, + "args": { + "External id": 3719972,"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": 1625853108421.258, "dur": 0.216, + "args": { + "External id": 3719973,"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": 1625853108422.277, "dur": 0.225, + "args": { + "External id": 3719974,"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": 1625853108423.232, "dur": 0.221, + "args": { + "External id": 3719975,"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": 1625853108424.176, "dur": 0.227, + "args": { + "External id": 3719976,"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": 1625853108426.521, "dur": 0.229, + "args": { + "External id": 3719977,"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": 1625853108427.545, "dur": 0.220, + "args": { + "External id": 3719978,"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": 1625853108430.891, "dur": 0.317, + "args": { + "External id": 3719979,"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": 1625853108432.095, "dur": 0.353, + "args": { + "External id": 3719980,"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": 1625853108433.248, "dur": 0.357, + "args": { + "External id": 3719981,"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": 1625853108434.464, "dur": 0.343, + "args": { + "External id": 3719982,"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": 1625853108435.563, "dur": 0.216, + "args": { + "External id": 3719983,"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": 1625853108436.507, "dur": 0.353, + "args": { + "External id": 3719984,"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": 1625853108437.587, "dur": 0.340, + "args": { + "External id": 3719985,"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": 1625853108438.965, "dur": 0.226, + "args": { + "External id": 3719986,"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": 1625853108442.094, "dur": 0.213, + "args": { + "External id": 3719987,"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": 1625853108443.174, "dur": 0.222, + "args": { + "External id": 3719988,"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": 1625853108444.354, "dur": 0.223, + "args": { + "External id": 3719989,"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": 1625853108445.450, "dur": 0.224, + "args": { + "External id": 3719990,"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": 1625853108502.854, "dur": 1709.536, + "args": { + "External id": 3719991,"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": 1625853108963.333, "dur": 1173.287, + "args": { + "External id": 3719992,"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": 1625853108972.215, "dur": 7.168, + "args": { + "External id": 3719993,"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": 1625853108975.877, "dur": 2.961, + "args": { + "External id": 3719994,"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": 1625853108980.125, "dur": 30.318, + "args": { + "External id": 3719995,"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": 1625853108980.936, "dur": 28.779, + "args": { + "External id": 3719996,"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": 1625853109011.939, "dur": 3.596, + "args": { + "External id": 3719997,"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": 1625853109014.597, "dur": 0.870, + "args": { + "External id": 3719998,"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": 1625853109016.242, "dur": 1.844, + "args": { + "External id": 3719999,"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": 1625853109017.061, "dur": 0.961, + "args": { + "External id": 3720000,"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": 1625853109020.703, "dur": 5.924, + "args": { + "External id": 3720001,"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": 1625853109025.375, "dur": 1.180, + "args": { + "External id": 3720002,"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": 1625853109027.154, "dur": 1.533, + "args": { + "External id": 3720003,"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": 1625853109027.773, "dur": 0.844, + "args": { + "External id": 3720004,"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": 1625853109029.056, "dur": 1.948, + "args": { + "External id": 3720005,"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": 1625853109029.814, "dur": 1.126, + "args": { + "External id": 3720006,"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": 1625853109031.357, "dur": 4.793, + "args": { + "External id": 3720007,"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": 1625853109035.461, "dur": 0.625, + "args": { + "External id": 3720008,"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": 1625853109036.525, "dur": 1.907, + "args": { + "External id": 3720009,"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": 1625853109037.353, "dur": 1.015, + "args": { + "External id": 3720010,"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": 1625853109038.652, "dur": 2.895, + "args": { + "External id": 3720011,"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": 1625853109038.996, "dur": 2.461, + "args": { + "External id": 3720012,"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": 1625853109041.773, "dur": 3.261, + "args": { + "External id": 3720013,"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": 1625853109044.068, "dur": 0.904, + "args": { + "External id": 3720014,"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": 1625853109045.254, "dur": 1.295, + "args": { + "External id": 3720015,"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": 1625853109045.617, "dur": 0.868, + "args": { + "External id": 3720016,"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": 1625853109048.837, "dur": 4.945, + "args": { + "External id": 3720017,"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": 1625853109052.901, "dur": 0.812, + "args": { + "External id": 3720018,"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": 1625853109054.054, "dur": 1.072, + "args": { + "External id": 3720019,"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": 1625853109054.533, "dur": 0.526, + "args": { + "External id": 3720020,"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": 1625853109055.367, "dur": 1.352, + "args": { + "External id": 3720021,"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": 1625853109055.930, "dur": 0.723, + "args": { + "External id": 3720022,"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": 1625853109057.037, "dur": 4.032, + "args": { + "External id": 3720023,"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": 1625853109060.427, "dur": 0.573, + "args": { + "External id": 3720024,"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": 1625853109061.387, "dur": 1.672, + "args": { + "External id": 3720025,"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": 1625853109062.159, "dur": 0.831, + "args": { + "External id": 3720026,"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": 1625853109063.282, "dur": 2.777, + "args": { + "External id": 3720027,"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": 1625853109063.632, "dur": 2.178, + "args": { + "External id": 3720028,"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": 1625853109066.376, "dur": 3.272, + "args": { + "External id": 3720029,"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": 1625853109068.863, "dur": 0.721, + "args": { + "External id": 3720030,"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": 1625853109069.985, "dur": 1.321, + "args": { + "External id": 3720031,"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": 1625853109070.506, "dur": 0.739, + "args": { + "External id": 3720032,"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": 1625853109073.965, "dur": 4.601, + "args": { + "External id": 3720033,"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": 1625853109077.743, "dur": 0.758, + "args": { + "External id": 3720034,"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": 1625853109078.809, "dur": 1.208, + "args": { + "External id": 3720035,"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": 1625853109079.306, "dur": 0.644, + "args": { + "External id": 3720036,"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": 1625853109080.371, "dur": 1.273, + "args": { + "External id": 3720037,"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": 1625853109080.834, "dur": 0.749, + "args": { + "External id": 3720038,"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": 1625853109081.969, "dur": 3.300, + "args": { + "External id": 3720039,"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": 1625853109084.582, "dur": 0.612, + "args": { + "External id": 3720040,"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": 1625853109085.745, "dur": 1.105, + "args": { + "External id": 3720041,"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": 1625853109086.217, "dur": 0.569, + "args": { + "External id": 3720042,"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": 1625853109087.070, "dur": 2.306, + "args": { + "External id": 3720043,"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": 1625853109087.431, "dur": 1.876, + "args": { + "External id": 3720044,"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": 1625853109089.605, "dur": 3.306, + "args": { + "External id": 3720045,"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": 1625853109092.018, "dur": 0.824, + "args": { + "External id": 3720046,"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": 1625853109093.131, "dur": 1.243, + "args": { + "External id": 3720047,"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": 1625853109093.479, "dur": 0.830, + "args": { + "External id": 3720048,"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": 1625853109097.078, "dur": 5.167, + "args": { + "External id": 3720049,"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": 1625853109101.381, "dur": 0.796, + "args": { + "External id": 3720050,"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": 1625853109102.613, "dur": 1.197, + "args": { + "External id": 3720051,"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": 1625853109103.129, "dur": 0.617, + "args": { + "External id": 3720052,"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": 1625853109104.132, "dur": 1.453, + "args": { + "External id": 3720053,"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": 1625853109104.703, "dur": 0.820, + "args": { + "External id": 3720054,"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": 1625853109106.157, "dur": 4.239, + "args": { + "External id": 3720055,"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": 1625853109109.410, "dur": 0.908, + "args": { + "External id": 3720056,"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": 1625853109110.641, "dur": 1.081, + "args": { + "External id": 3720057,"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": 1625853109111.101, "dur": 0.558, + "args": { + "External id": 3720058,"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": 1625853109112.058, "dur": 3.185, + "args": { + "External id": 3720059,"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": 1625853109112.514, "dur": 2.659, + "args": { + "External id": 3720060,"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": 1625853109115.585, "dur": 2.611, + "args": { + "External id": 3720061,"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": 1625853109117.541, "dur": 0.591, + "args": { + "External id": 3720062,"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": 1625853109118.823, "dur": 1.446, + "args": { + "External id": 3720063,"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": 1625853109119.184, "dur": 1.025, + "args": { + "External id": 3720064,"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": 1625853109123.092, "dur": 5.184, + "args": { + "External id": 3720065,"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": 1625853109127.340, "dur": 0.871, + "args": { + "External id": 3720066,"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": 1625853109128.517, "dur": 1.176, + "args": { + "External id": 3720067,"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": 1625853109128.895, "dur": 0.733, + "args": { + "External id": 3720068,"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": 1625853109130.109, "dur": 1.211, + "args": { + "External id": 3720069,"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": 1625853109130.478, "dur": 0.773, + "args": { + "External id": 3720070,"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": 1625853109131.535, "dur": 5.690, + "args": { + "External id": 3720071,"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": 1625853109136.336, "dur": 0.822, + "args": { + "External id": 3720072,"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": 1625853109137.547, "dur": 1.578, + "args": { + "External id": 3720073,"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": 1625853109138.208, "dur": 0.855, + "args": { + "External id": 3720074,"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": 1625853109139.449, "dur": 2.899, + "args": { + "External id": 3720075,"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": 1625853109139.940, "dur": 2.341, + "args": { + "External id": 3720076,"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": 1625853109142.713, "dur": 2.241, + "args": { + "External id": 3720077,"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": 1625853109144.268, "dur": 0.617, + "args": { + "External id": 3720078,"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": 1625853109145.172, "dur": 1.159, + "args": { + "External id": 3720079,"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": 1625853109145.538, "dur": 0.731, + "args": { + "External id": 3720080,"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": 1625853109148.641, "dur": 4.791, + "args": { + "External id": 3720081,"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": 1625853109152.628, "dur": 0.737, + "args": { + "External id": 3720082,"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": 1625853109153.691, "dur": 1.044, + "args": { + "External id": 3720083,"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": 1625853109154.054, "dur": 0.615, + "args": { + "External id": 3720084,"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": 1625853109154.954, "dur": 1.502, + "args": { + "External id": 3720085,"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": 1625853109155.307, "dur": 1.085, + "args": { + "External id": 3720086,"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": 1625853109156.803, "dur": 4.079, + "args": { + "External id": 3720087,"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": 1625853109159.630, "dur": 1.191, + "args": { + "External id": 3720088,"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": 1625853109161.201, "dur": 1.453, + "args": { + "External id": 3720089,"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": 1625853109161.824, "dur": 0.764, + "args": { + "External id": 3720090,"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": 1625853109163.169, "dur": 3.239, + "args": { + "External id": 3720091,"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": 1625853109163.980, "dur": 2.184, + "args": { + "External id": 3720092,"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": 1625853109166.654, "dur": 1.709, + "args": { + "External id": 3720093,"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": 1625853109167.656, "dur": 0.642, + "args": { + "External id": 3720094,"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": 1625853109168.582, "dur": 2.171, + "args": { + "External id": 3720095,"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": 1625853109169.804, "dur": 0.884, + "args": { + "External id": 3720096,"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": 1625853109173.352, "dur": 3.803, + "args": { + "External id": 3720097,"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": 1625853109176.312, "dur": 0.780, + "args": { + "External id": 3720098,"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": 1625853109177.416, "dur": 2.069, + "args": { + "External id": 3720099,"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": 1625853109178.915, "dur": 0.508, + "args": { + "External id": 3720100,"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": 1625853109179.912, "dur": 1.486, + "args": { + "External id": 3720101,"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": 1625853109180.626, "dur": 0.706, + "args": { + "External id": 3720102,"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": 1625853109181.742, "dur": 4.204, + "args": { + "External id": 3720103,"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": 1625853109184.973, "dur": 0.908, + "args": { + "External id": 3720104,"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": 1625853109186.667, "dur": 2.095, + "args": { + "External id": 3720105,"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": 1625853109187.878, "dur": 0.820, + "args": { + "External id": 3720106,"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": 1625853109189.101, "dur": 3.886, + "args": { + "External id": 3720107,"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": 1625853109190.345, "dur": 2.568, + "args": { + "External id": 3720108,"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": 1625853109193.227, "dur": 1.551, + "args": { + "External id": 3720109,"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": 1625853109193.858, "dur": 0.854, + "args": { + "External id": 3720110,"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": 1625853109195.194, "dur": 1.870, + "args": { + "External id": 3720111,"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": 1625853109196.311, "dur": 0.690, + "args": { + "External id": 3720112,"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": 1625853109199.214, "dur": 3.735, + "args": { + "External id": 3720113,"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": 1625853109202.138, "dur": 0.747, + "args": { + "External id": 3720114,"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": 1625853109203.511, "dur": 1.705, + "args": { + "External id": 3720115,"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": 1625853109204.599, "dur": 0.555, + "args": { + "External id": 3720116,"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": 1625853109205.572, "dur": 1.813, + "args": { + "External id": 3720117,"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": 1625853109206.585, "dur": 0.735, + "args": { + "External id": 3720118,"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": 1625853109207.699, "dur": 4.412, + "args": { + "External id": 3720119,"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": 1625853109211.345, "dur": 0.704, + "args": { + "External id": 3720120,"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": 1625853109212.403, "dur": 2.140, + "args": { + "External id": 3720121,"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": 1625853109213.613, "dur": 0.868, + "args": { + "External id": 3720122,"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": 1625853109214.762, "dur": 4.176, + "args": { + "External id": 3720123,"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": 1625853109216.326, "dur": 2.365, + "args": { + "External id": 3720124,"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": 1625853109219.191, "dur": 1.776, + "args": { + "External id": 3720125,"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": 1625853109220.078, "dur": 0.830, + "args": { + "External id": 3720126,"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": 1625853109221.187, "dur": 2.632, + "args": { + "External id": 3720127,"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": 1625853109222.876, "dur": 0.881, + "args": { + "External id": 3720128,"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": 1625853109226.054, "dur": 3.669, + "args": { + "External id": 3720129,"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": 1625853109228.836, "dur": 0.827, + "args": { + "External id": 3720130,"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": 1625853109230.082, "dur": 2.096, + "args": { + "External id": 3720131,"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": 1625853109231.273, "dur": 0.837, + "args": { + "External id": 3720132,"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": 1625853109232.647, "dur": 2.131, + "args": { + "External id": 3720133,"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": 1625853109233.816, "dur": 0.901, + "args": { + "External id": 3720134,"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": 1625853109235.123, "dur": 4.281, + "args": { + "External id": 3720135,"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": 1625853109238.557, "dur": 0.782, + "args": { + "External id": 3720136,"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": 1625853109239.755, "dur": 1.984, + "args": { + "External id": 3720137,"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": 1625853109240.769, "dur": 0.891, + "args": { + "External id": 3720138,"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": 1625853109242.138, "dur": 3.713, + "args": { + "External id": 3720139,"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": 1625853109243.513, "dur": 2.267, + "args": { + "External id": 3720140,"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": 1625853109246.090, "dur": 1.580, + "args": { + "External id": 3720141,"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": 1625853109246.976, "dur": 0.629, + "args": { + "External id": 3720142,"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": 1625853109248.076, "dur": 2.155, + "args": { + "External id": 3720143,"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": 1625853109249.055, "dur": 1.114, + "args": { + "External id": 3720144,"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": 1625853109252.328, "dur": 3.592, + "args": { + "External id": 3720145,"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": 1625853109255.201, "dur": 0.655, + "args": { + "External id": 3720146,"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": 1625853109256.160, "dur": 1.789, + "args": { + "External id": 3720147,"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": 1625853109257.264, "dur": 0.612, + "args": { + "External id": 3720148,"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": 1625853109258.293, "dur": 1.939, + "args": { + "External id": 3720149,"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": 1625853109259.276, "dur": 0.892, + "args": { + "External id": 3720150,"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": 1625853109260.592, "dur": 4.528, + "args": { + "External id": 3720151,"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": 1625853109264.263, "dur": 0.563, + "args": { + "External id": 3720152,"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": 1625853109265.404, "dur": 2.043, + "args": { + "External id": 3720153,"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": 1625853109266.415, "dur": 0.967, + "args": { + "External id": 3720154,"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": 1625853109267.687, "dur": 3.241, + "args": { + "External id": 3720155,"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": 1625853109268.882, "dur": 1.981, + "args": { + "External id": 3720156,"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": 1625853109271.274, "dur": 1.397, + "args": { + "External id": 3720157,"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": 1625853109272.069, "dur": 0.538, + "args": { + "External id": 3720158,"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": 1625853109272.982, "dur": 2.395, + "args": { + "External id": 3720159,"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": 1625853109274.241, "dur": 1.072, + "args": { + "External id": 3720160,"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": 1625853109277.777, "dur": 4.341, + "args": { + "External id": 3720161,"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": 1625853109281.118, "dur": 0.935, + "args": { + "External id": 3720162,"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": 1625853109282.380, "dur": 2.714, + "args": { + "External id": 3720163,"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": 1625853109283.807, "dur": 1.023, + "args": { + "External id": 3720164,"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": 1625853109285.457, "dur": 2.010, + "args": { + "External id": 3720165,"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": 1625853109286.528, "dur": 0.867, + "args": { + "External id": 3720166,"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": 1625853109287.825, "dur": 4.553, + "args": { + "External id": 3720167,"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": 1625853109291.557, "dur": 0.759, + "args": { + "External id": 3720168,"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": 1625853109292.755, "dur": 2.189, + "args": { + "External id": 3720169,"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": 1625853109293.950, "dur": 0.721, + "args": { + "External id": 3720170,"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": 1625853109295.172, "dur": 3.945, + "args": { + "External id": 3720171,"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": 1625853109296.523, "dur": 2.525, + "args": { + "External id": 3720172,"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": 1625853109299.375, "dur": 1.841, + "args": { + "External id": 3720173,"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": 1625853109300.343, "dur": 0.600, + "args": { + "External id": 3720174,"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": 1625853109301.429, "dur": 2.216, + "args": { + "External id": 3720175,"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": 1625853109302.744, "dur": 0.837, + "args": { + "External id": 3720176,"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": 1625853109305.976, "dur": 4.024, + "args": { + "External id": 3720177,"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": 1625853109308.966, "dur": 0.971, + "args": { + "External id": 3720178,"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": 1625853109310.256, "dur": 2.046, + "args": { + "External id": 3720179,"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": 1625853109311.631, "dur": 0.609, + "args": { + "External id": 3720180,"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": 1625853109312.580, "dur": 1.573, + "args": { + "External id": 3720181,"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": 1625853109313.285, "dur": 0.805, + "args": { + "External id": 3720182,"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": 1625853109314.373, "dur": 4.196, + "args": { + "External id": 3720183,"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": 1625853109317.879, "dur": 0.625, + "args": { + "External id": 3720184,"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": 1625853109318.982, "dur": 1.615, + "args": { + "External id": 3720185,"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": 1625853109319.913, "dur": 0.625, + "args": { + "External id": 3720186,"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": 1625853109321.106, "dur": 3.793, + "args": { + "External id": 3720187,"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": 1625853109322.305, "dur": 2.334, + "args": { + "External id": 3720188,"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": 1625853109325.274, "dur": 1.514, + "args": { + "External id": 3720189,"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": 1625853109326.088, "dur": 0.639, + "args": { + "External id": 3720190,"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": 1625853109327.319, "dur": 2.058, + "args": { + "External id": 3720191,"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": 1625853109328.527, "dur": 0.788, + "args": { + "External id": 3720192,"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": 1625853109357.974, "dur": 3.210, + "args": { + "External id": 3726337,"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": 1625853109360.701, "dur": 0.414, + "args": { + "External id": 3726338,"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": 1625853109361.512, "dur": 1.524, + "args": { + "External id": 3726339,"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": 1625853109362.509, "dur": 0.459, + "args": { + "External id": 3726340,"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": 1625853109363.322, "dur": 1.644, + "args": { + "External id": 3726341,"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": 1625853109364.257, "dur": 0.641, + "args": { + "External id": 3726342,"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": 1625853109365.207, "dur": 3.775, + "args": { + "External id": 3726343,"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": 1625853109368.295, "dur": 0.623, + "args": { + "External id": 3726344,"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": 1625853109369.232, "dur": 1.545, + "args": { + "External id": 3726345,"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": 1625853109369.892, "dur": 0.825, + "args": { + "External id": 3726346,"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": 1625853109370.999, "dur": 3.687, + "args": { + "External id": 3726347,"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": 1625853109371.974, "dur": 2.445, + "args": { + "External id": 3726348,"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": 1625853109374.930, "dur": 1.206, + "args": { + "External id": 3726349,"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": 1625853109375.597, "dur": 0.469, + "args": { + "External id": 3726350,"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": 1625853109376.543, "dur": 1.907, + "args": { + "External id": 3726351,"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": 1625853109377.583, "dur": 0.598, + "args": { + "External id": 3726352,"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": 1625853109380.736, "dur": 3.873, + "args": { + "External id": 3726353,"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": 1625853109383.736, "dur": 0.810, + "args": { + "External id": 3726354,"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": 1625853109384.851, "dur": 2.057, + "args": { + "External id": 3726355,"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": 1625853109385.938, "dur": 0.596, + "args": { + "External id": 3726356,"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": 1625853109387.192, "dur": 1.627, + "args": { + "External id": 3726357,"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": 1625853109387.911, "dur": 0.840, + "args": { + "External id": 3726358,"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": 1625853109389.040, "dur": 3.669, + "args": { + "External id": 3726359,"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": 1625853109391.975, "dur": 0.663, + "args": { + "External id": 3726360,"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": 1625853109392.947, "dur": 1.249, + "args": { + "External id": 3726361,"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": 1625853109393.570, "dur": 0.566, + "args": { + "External id": 3726362,"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": 1625853109394.417, "dur": 3.601, + "args": { + "External id": 3726363,"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": 1625853109395.456, "dur": 2.303, + "args": { + "External id": 3726364,"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": 1625853109398.279, "dur": 1.529, + "args": { + "External id": 3726365,"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": 1625853109398.973, "dur": 0.770, + "args": { + "External id": 3726366,"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": 1625853109400.095, "dur": 2.020, + "args": { + "External id": 3726367,"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": 1625853109401.308, "dur": 0.640, + "args": { + "External id": 3726368,"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": 1625853109404.552, "dur": 3.423, + "args": { + "External id": 3726369,"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": 1625853109407.298, "dur": 0.608, + "args": { + "External id": 3726370,"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": 1625853109408.247, "dur": 1.894, + "args": { + "External id": 3726371,"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": 1625853109409.342, "dur": 0.618, + "args": { + "External id": 3726372,"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": 1625853109410.400, "dur": 1.608, + "args": { + "External id": 3726373,"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": 1625853109411.062, "dur": 0.710, + "args": { + "External id": 3726374,"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": 1625853109412.296, "dur": 3.912, + "args": { + "External id": 3726375,"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": 1625853109415.593, "dur": 0.550, + "args": { + "External id": 3726376,"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": 1625853109416.446, "dur": 1.490, + "args": { + "External id": 3726377,"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": 1625853109417.088, "dur": 0.789, + "args": { + "External id": 3726378,"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": 1625853109418.179, "dur": 3.320, + "args": { + "External id": 3726379,"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": 1625853109419.304, "dur": 2.123, + "args": { + "External id": 3726380,"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": 1625853109421.741, "dur": 1.859, + "args": { + "External id": 3726381,"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": 1625853109422.565, "dur": 0.765, + "args": { + "External id": 3726382,"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": 1625853109423.820, "dur": 1.978, + "args": { + "External id": 3726383,"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": 1625853109424.890, "dur": 0.663, + "args": { + "External id": 3726384,"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": 1625853109428.142, "dur": 3.404, + "args": { + "External id": 3726385,"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": 1625853109430.914, "dur": 0.568, + "args": { + "External id": 3726386,"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": 1625853109431.853, "dur": 2.208, + "args": { + "External id": 3726387,"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": 1625853109433.175, "dur": 0.609, + "args": { + "External id": 3726388,"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": 1625853109434.349, "dur": 1.695, + "args": { + "External id": 3726389,"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": 1625853109435.186, "dur": 0.790, + "args": { + "External id": 3726390,"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": 1625853109436.293, "dur": 4.165, + "args": { + "External id": 3726391,"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": 1625853109439.576, "dur": 0.633, + "args": { + "External id": 3726392,"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": 1625853109440.697, "dur": 1.477, + "args": { + "External id": 3726393,"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": 1625853109441.502, "dur": 0.611, + "args": { + "External id": 3726394,"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": 1625853109442.416, "dur": 4.536, + "args": { + "External id": 3726395,"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": 1625853109443.548, "dur": 3.331, + "args": { + "External id": 3726396,"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": 1625853109447.192, "dur": 1.522, + "args": { + "External id": 3726397,"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": 1625853109447.842, "dur": 0.634, + "args": { + "External id": 3726398,"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": 1625853109448.931, "dur": 2.208, + "args": { + "External id": 3726399,"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": 1625853109450.187, "dur": 0.885, + "args": { + "External id": 3726400,"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": 1625853109453.492, "dur": 3.465, + "args": { + "External id": 3726401,"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": 1625853109456.336, "dur": 0.558, + "args": { + "External id": 3726402,"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": 1625853109457.196, "dur": 2.173, + "args": { + "External id": 3726403,"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": 1625853109458.483, "dur": 0.602, + "args": { + "External id": 3726404,"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": 1625853109459.611, "dur": 1.879, + "args": { + "External id": 3726405,"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": 1625853109460.445, "dur": 0.977, + "args": { + "External id": 3726406,"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": 1625853109461.734, "dur": 4.258, + "args": { + "External id": 3726407,"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": 1625853109464.922, "dur": 0.818, + "args": { + "External id": 3726408,"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": 1625853109466.252, "dur": 1.363, + "args": { + "External id": 3726409,"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": 1625853109466.936, "dur": 0.617, + "args": { + "External id": 3726410,"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": 1625853109467.836, "dur": 3.204, + "args": { + "External id": 3726411,"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": 1625853109468.934, "dur": 2.034, + "args": { + "External id": 3726412,"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": 1625853109471.278, "dur": 1.306, + "args": { + "External id": 3726413,"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": 1625853109471.957, "dur": 0.562, + "args": { + "External id": 3726414,"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": 1625853109472.809, "dur": 2.267, + "args": { + "External id": 3726415,"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": 1625853109474.058, "dur": 0.952, + "args": { + "External id": 3726416,"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": 1625853109477.431, "dur": 3.890, + "args": { + "External id": 3726417,"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": 1625853109480.533, "dur": 0.724, + "args": { + "External id": 3726418,"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": 1625853109481.599, "dur": 1.985, + "args": { + "External id": 3726419,"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": 1625853109482.944, "dur": 0.577, + "args": { + "External id": 3726420,"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": 1625853109483.841, "dur": 1.581, + "args": { + "External id": 3726421,"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": 1625853109484.674, "dur": 0.682, + "args": { + "External id": 3726422,"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": 1625853109485.644, "dur": 4.480, + "args": { + "External id": 3726423,"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": 1625853109489.204, "dur": 0.639, + "args": { + "External id": 3726424,"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": 1625853109490.378, "dur": 1.373, + "args": { + "External id": 3726425,"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": 1625853109491.038, "dur": 0.649, + "args": { + "External id": 3726426,"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": 1625853109491.970, "dur": 3.893, + "args": { + "External id": 3726427,"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": 1625853109493.423, "dur": 2.363, + "args": { + "External id": 3726428,"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": 1625853109496.103, "dur": 1.831, + "args": { + "External id": 3726429,"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": 1625853109497.010, "dur": 0.615, + "args": { + "External id": 3726430,"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": 1625853109498.156, "dur": 1.821, + "args": { + "External id": 3726431,"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": 1625853109499.159, "dur": 0.752, + "args": { + "External id": 3726432,"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": 1625853109502.636, "dur": 3.293, + "args": { + "External id": 3726433,"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": 1625853109505.261, "dur": 0.602, + "args": { + "External id": 3726434,"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": 1625853109506.382, "dur": 2.049, + "args": { + "External id": 3726435,"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": 1625853109507.703, "dur": 0.662, + "args": { + "External id": 3726436,"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": 1625853109508.672, "dur": 1.481, + "args": { + "External id": 3726437,"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": 1625853109509.345, "dur": 0.743, + "args": { + "External id": 3726438,"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": 1625853109510.372, "dur": 3.777, + "args": { + "External id": 3726439,"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": 1625853109513.465, "dur": 0.620, + "args": { + "External id": 3726440,"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": 1625853109514.394, "dur": 1.439, + "args": { + "External id": 3726441,"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": 1625853109515.068, "dur": 0.702, + "args": { + "External id": 3726442,"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": 1625853109516.134, "dur": 3.695, + "args": { + "External id": 3726443,"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": 1625853109517.249, "dur": 2.513, + "args": { + "External id": 3726444,"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": 1625853109520.076, "dur": 1.792, + "args": { + "External id": 3726445,"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": 1625853109521.106, "dur": 0.696, + "args": { + "External id": 3726446,"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": 1625853109522.084, "dur": 2.212, + "args": { + "External id": 3726447,"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": 1625853109523.419, "dur": 0.813, + "args": { + "External id": 3726448,"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": 1625853109526.617, "dur": 3.805, + "args": { + "External id": 3726449,"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": 1625853109529.271, "dur": 1.076, + "args": { + "External id": 3726450,"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": 1625853109530.667, "dur": 1.947, + "args": { + "External id": 3726451,"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": 1625853109531.780, "dur": 0.558, + "args": { + "External id": 3726452,"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": 1625853109532.876, "dur": 1.900, + "args": { + "External id": 3726453,"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": 1625853109533.998, "dur": 0.710, + "args": { + "External id": 3726454,"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": 1625853109534.998, "dur": 4.244, + "args": { + "External id": 3726455,"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": 1625853109538.273, "dur": 0.802, + "args": { + "External id": 3726456,"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": 1625853109539.477, "dur": 1.425, + "args": { + "External id": 3726457,"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": 1625853109540.161, "dur": 0.679, + "args": { + "External id": 3726458,"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": 1625853109541.137, "dur": 3.219, + "args": { + "External id": 3726459,"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": 1625853109542.142, "dur": 2.140, + "args": { + "External id": 3726460,"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": 1625853109544.611, "dur": 1.520, + "args": { + "External id": 3726461,"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": 1625853109545.248, "dur": 0.822, + "args": { + "External id": 3726462,"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": 1625853109546.534, "dur": 2.080, + "args": { + "External id": 3726463,"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": 1625853109547.634, "dur": 0.913, + "args": { + "External id": 3726464,"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": 1625853109550.752, "dur": 3.987, + "args": { + "External id": 3726465,"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": 1625853109554.016, "dur": 0.657, + "args": { + "External id": 3726466,"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": 1625853109555.010, "dur": 1.828, + "args": { + "External id": 3726467,"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": 1625853109556.107, "dur": 0.665, + "args": { + "External id": 3726468,"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": 1625853109557.122, "dur": 1.598, + "args": { + "External id": 3726469,"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": 1625853109557.974, "dur": 0.680, + "args": { + "External id": 3726470,"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": 1625853109558.940, "dur": 4.776, + "args": { + "External id": 3726471,"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": 1625853109563.025, "dur": 0.626, + "args": { + "External id": 3726472,"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": 1625853109563.958, "dur": 1.569, + "args": { + "External id": 3726473,"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": 1625853109564.745, "dur": 0.713, + "args": { + "External id": 3726474,"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": 1625853109565.796, "dur": 3.544, + "args": { + "External id": 3726475,"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": 1625853109567.123, "dur": 2.150, + "args": { + "External id": 3726476,"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": 1625853109569.580, "dur": 1.565, + "args": { + "External id": 3726477,"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": 1625853109570.229, "dur": 0.645, + "args": { + "External id": 3726478,"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": 1625853109571.369, "dur": 2.190, + "args": { + "External id": 3726479,"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": 1625853109572.606, "dur": 0.889, + "args": { + "External id": 3726480,"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": 1625853109576.169, "dur": 3.329, + "args": { + "External id": 3726481,"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": 1625853109578.806, "dur": 0.625, + "args": { + "External id": 3726482,"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": 1625853109579.939, "dur": 2.047, + "args": { + "External id": 3726483,"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": 1625853109581.353, "dur": 0.567, + "args": { + "External id": 3726484,"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": 1625853109582.227, "dur": 1.334, + "args": { + "External id": 3726485,"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": 1625853109582.862, "dur": 0.633, + "args": { + "External id": 3726486,"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": 1625853109583.779, "dur": 3.782, + "args": { + "External id": 3726487,"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": 1625853109586.525, "dur": 0.873, + "args": { + "External id": 3726488,"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": 1625853109587.820, "dur": 1.899, + "args": { + "External id": 3726489,"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": 1625853109588.682, "dur": 0.783, + "args": { + "External id": 3726490,"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": 1625853109589.934, "dur": 3.826, + "args": { + "External id": 3726491,"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": 1625853109591.171, "dur": 2.521, + "args": { + "External id": 3726492,"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": 1625853109594.020, "dur": 1.765, + "args": { + "External id": 3726493,"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": 1625853109594.904, "dur": 0.615, + "args": { + "External id": 3726494,"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": 1625853109596.000, "dur": 2.055, + "args": { + "External id": 3726495,"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": 1625853109597.077, "dur": 0.908, + "args": { + "External id": 3726496,"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": 1625853109600.525, "dur": 3.793, + "args": { + "External id": 3726497,"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": 1625853109603.665, "dur": 0.580, + "args": { + "External id": 3726498,"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": 1625853109604.555, "dur": 1.770, + "args": { + "External id": 3726499,"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": 1625853109605.726, "dur": 0.538, + "args": { + "External id": 3726500,"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": 1625853109606.561, "dur": 1.385, + "args": { + "External id": 3726501,"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": 1625853109607.204, "dur": 0.679, + "args": { + "External id": 3726502,"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": 1625853109608.162, "dur": 4.416, + "args": { + "External id": 3726503,"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": 1625853109611.941, "dur": 0.574, + "args": { + "External id": 3726504,"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": 1625853109612.831, "dur": 1.341, + "args": { + "External id": 3726505,"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": 1625853109613.517, "dur": 0.583, + "args": { + "External id": 3726506,"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": 1625853109614.389, "dur": 3.449, + "args": { + "External id": 3726507,"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": 1625853109615.417, "dur": 2.347, + "args": { + "External id": 3726508,"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": 1625853109618.078, "dur": 1.968, + "args": { + "External id": 3726509,"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": 1625853109619.091, "dur": 0.684, + "args": { + "External id": 3726510,"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": 1625853109620.262, "dur": 1.680, + "args": { + "External id": 3726511,"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": 1625853109621.233, "dur": 0.644, + "args": { + "External id": 3726512,"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": 1625853109624.299, "dur": 3.731, + "args": { + "External id": 3726513,"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": 1625853109627.364, "dur": 0.600, + "args": { + "External id": 3726514,"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": 1625853109628.315, "dur": 1.560, + "args": { + "External id": 3726515,"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": 1625853109629.238, "dur": 0.572, + "args": { + "External id": 3726516,"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": 1625853109630.114, "dur": 1.769, + "args": { + "External id": 3726517,"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": 1625853109630.728, "dur": 0.734, + "args": { + "External id": 3726518,"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": 1625853109632.100, "dur": 3.610, + "args": { + "External id": 3726519,"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": 1625853109635.044, "dur": 0.599, + "args": { + "External id": 3726520,"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": 1625853109635.946, "dur": 1.572, + "args": { + "External id": 3726521,"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": 1625853109636.834, "dur": 0.619, + "args": { + "External id": 3726522,"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": 1625853109637.739, "dur": 3.690, + "args": { + "External id": 3726523,"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": 1625853109639.015, "dur": 2.346, + "args": { + "External id": 3726524,"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": 1625853109641.666, "dur": 2.480, + "args": { + "External id": 3726525,"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": 1625853109642.512, "dur": 1.556, + "args": { + "External id": 3726526,"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": 1625853109644.364, "dur": 2.105, + "args": { + "External id": 3726527,"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": 1625853109645.555, "dur": 0.849, + "args": { + "External id": 3726528,"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": 1625853109648.822, "dur": 3.427, + "args": { + "External id": 3726529,"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": 1625853109651.582, "dur": 0.602, + "args": { + "External id": 3726530,"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": 1625853109652.489, "dur": 1.791, + "args": { + "External id": 3726531,"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": 1625853109653.628, "dur": 0.576, + "args": { + "External id": 3726532,"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": 1625853109654.517, "dur": 1.905, + "args": { + "External id": 3726533,"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": 1625853109655.889, "dur": 0.469, + "args": { + "External id": 3726534,"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": 1625853109656.642, "dur": 3.727, + "args": { + "External id": 3726535,"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": 1625853109659.695, "dur": 0.611, + "args": { + "External id": 3726536,"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": 1625853109660.604, "dur": 1.963, + "args": { + "External id": 3726537,"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": 1625853109661.724, "dur": 0.666, + "args": { + "External id": 3726538,"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": 1625853109662.787, "dur": 3.273, + "args": { + "External id": 3726539,"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": 1625853109663.780, "dur": 2.214, + "args": { + "External id": 3726540,"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": 1625853109666.346, "dur": 1.460, + "args": { + "External id": 3726541,"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": 1625853109667.068, "dur": 0.674, + "args": { + "External id": 3726542,"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": 1625853109668.198, "dur": 1.845, + "args": { + "External id": 3726543,"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": 1625853109669.260, "dur": 0.720, + "args": { + "External id": 3726544,"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": 1625853109672.367, "dur": 3.403, + "args": { + "External id": 3726545,"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": 1625853109675.134, "dur": 0.563, + "args": { + "External id": 3726546,"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": 1625853109676.024, "dur": 14.039, + "args": { + "External id": 3726547,"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": 1625853109688.708, "dur": 0.707, + "args": { + "External id": 3726548,"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": 1625853109690.573, "dur": 1.865, + "args": { + "External id": 3726549,"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": 1625853109691.694, "dur": 0.675, + "args": { + "External id": 3726550,"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": 1625853109692.681, "dur": 4.096, + "args": { + "External id": 3726551,"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": 1625853109696.061, "dur": 0.651, + "args": { + "External id": 3726552,"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": 1625853109697.040, "dur": 2.939, + "args": { + "External id": 3726553,"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": 1625853109697.695, "dur": 2.029, + "args": { + "External id": 3726554,"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": 1625853109700.409, "dur": 3.284, + "args": { + "External id": 3726555,"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": 1625853109701.771, "dur": 1.846, + "args": { + "External id": 3726556,"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": 1625853109703.951, "dur": 1.581, + "args": { + "External id": 3726557,"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": 1625853109704.685, "dur": 0.589, + "args": { + "External id": 3726558,"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": 1625853109706.073, "dur": 2.232, + "args": { + "External id": 3726559,"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": 1625853109707.581, "dur": 0.649, + "args": { + "External id": 3726560,"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": 1625853109710.943, "dur": 3.828, + "args": { + "External id": 3726561,"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": 1625853109714.105, "dur": 0.603, + "args": { + "External id": 3726562,"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": 1625853109715.037, "dur": 2.268, + "args": { + "External id": 3726563,"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": 1625853109716.181, "dur": 1.060, + "args": { + "External id": 3726564,"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": 1625853109717.552, "dur": 1.684, + "args": { + "External id": 3726565,"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": 1625853109718.515, "dur": 0.655, + "args": { + "External id": 3726566,"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": 1625853109719.469, "dur": 4.170, + "args": { + "External id": 3726567,"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": 1625853109722.748, "dur": 0.684, + "args": { + "External id": 3726568,"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": 1625853109723.952, "dur": 1.298, + "args": { + "External id": 3726569,"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": 1625853109724.586, "dur": 0.602, + "args": { + "External id": 3726570,"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": 1625853109725.487, "dur": 3.713, + "args": { + "External id": 3726571,"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": 1625853109726.619, "dur": 2.312, + "args": { + "External id": 3726572,"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": 1625853109729.452, "dur": 1.538, + "args": { + "External id": 3726573,"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": 1625853109730.314, "dur": 0.611, + "args": { + "External id": 3726574,"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": 1625853109731.221, "dur": 2.114, + "args": { + "External id": 3726575,"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": 1625853109732.592, "dur": 0.679, + "args": { + "External id": 3726576,"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": 1625853109735.688, "dur": 3.520, + "args": { + "External id": 3726577,"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": 1625853109738.567, "dur": 0.578, + "args": { + "External id": 3726578,"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": 1625853109739.474, "dur": 2.255, + "args": { + "External id": 3726579,"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": 1625853109740.835, "dur": 0.621, + "args": { + "External id": 3726580,"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": 1625853109741.971, "dur": 1.610, + "args": { + "External id": 3726581,"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": 1625853109742.678, "dur": 0.638, + "args": { + "External id": 3726582,"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": 1625853109743.804, "dur": 4.386, + "args": { + "External id": 3726583,"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": 1625853109747.288, "dur": 0.636, + "args": { + "External id": 3726584,"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": 1625853109748.434, "dur": 1.498, + "args": { + "External id": 3726585,"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": 1625853109749.270, "dur": 0.598, + "args": { + "External id": 3726586,"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": 1625853109750.331, "dur": 3.577, + "args": { + "External id": 3726587,"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": 1625853109751.578, "dur": 2.261, + "args": { + "External id": 3726588,"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": 1625853109754.157, "dur": 1.741, + "args": { + "External id": 3726589,"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": 1625853109755.096, "dur": 0.550, + "args": { + "External id": 3726590,"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": 1625853109756.134, "dur": 2.291, + "args": { + "External id": 3726591,"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": 1625853109757.614, "dur": 0.744, + "args": { + "External id": 3726592,"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": 1625853109760.590, "dur": 3.393, + "args": { + "External id": 3726593,"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": 1625853109763.331, "dur": 0.578, + "args": { + "External id": 3726594,"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": 1625853109764.232, "dur": 1.965, + "args": { + "External id": 3726595,"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": 1625853109765.545, "dur": 0.578, + "args": { + "External id": 3726596,"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": 1625853109766.460, "dur": 1.637, + "args": { + "External id": 3726597,"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": 1625853109767.158, "dur": 0.772, + "args": { + "External id": 3726598,"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": 1625853109768.321, "dur": 4.035, + "args": { + "External id": 3726599,"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": 1625853109771.614, "dur": 0.682, + "args": { + "External id": 3726600,"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": 1625853109772.637, "dur": 1.545, + "args": { + "External id": 3726601,"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": 1625853109773.484, "dur": 0.633, + "args": { + "External id": 3726602,"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": 1625853109774.596, "dur": 3.705, + "args": { + "External id": 3726603,"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": 1625853109775.823, "dur": 2.210, + "args": { + "External id": 3726604,"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": 1625853109778.548, "dur": 1.448, + "args": { + "External id": 3726605,"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": 1625853109779.285, "dur": 0.647, + "args": { + "External id": 3726606,"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": 1625853109780.433, "dur": 2.255, + "args": { + "External id": 3726607,"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": 1625853109781.741, "dur": 0.882, + "args": { + "External id": 3726608,"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": 1625853109784.982, "dur": 3.423, + "args": { + "External id": 3726609,"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": 1625853109787.729, "dur": 0.610, + "args": { + "External id": 3726610,"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": 1625853109788.655, "dur": 2.247, + "args": { + "External id": 3726611,"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": 1625853109790.020, "dur": 0.818, + "args": { + "External id": 3726612,"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": 1625853109791.166, "dur": 1.762, + "args": { + "External id": 3726613,"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": 1625853109792.084, "dur": 0.665, + "args": { + "External id": 3726614,"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": 1625853109793.174, "dur": 3.975, + "args": { + "External id": 3726615,"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": 1625853109796.542, "dur": 0.546, + "args": { + "External id": 3726616,"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": 1625853109797.419, "dur": 1.543, + "args": { + "External id": 3726617,"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": 1625853109798.245, "dur": 0.651, + "args": { + "External id": 3726618,"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": 1625853109799.186, "dur": 3.857, + "args": { + "External id": 3726619,"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": 1625853109800.487, "dur": 2.199, + "args": { + "External id": 3726620,"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": 1625853109803.285, "dur": 1.829, + "args": { + "External id": 3726621,"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": 1625853109804.454, "dur": 0.591, + "args": { + "External id": 3726622,"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": 1625853109805.341, "dur": 2.038, + "args": { + "External id": 3726623,"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": 1625853109806.635, "dur": 0.679, + "args": { + "External id": 3726624,"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": 1625853109809.619, "dur": 3.551, + "args": { + "External id": 3726625,"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": 1625853109812.421, "dur": 0.682, + "args": { + "External id": 3726626,"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": 1625853109813.434, "dur": 2.215, + "args": { + "External id": 3726627,"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": 1625853109814.604, "dur": 0.981, + "args": { + "External id": 3726628,"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": 1625853109815.928, "dur": 1.883, + "args": { + "External id": 3726629,"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": 1625853109816.899, "dur": 0.842, + "args": { + "External id": 3726630,"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": 1625853109818.038, "dur": 3.985, + "args": { + "External id": 3726631,"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": 1625853109821.016, "dur": 0.724, + "args": { + "External id": 3726632,"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": 1625853109822.290, "dur": 1.460, + "args": { + "External id": 3726633,"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": 1625853109823.085, "dur": 0.591, + "args": { + "External id": 3726634,"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": 1625853109823.974, "dur": 3.230, + "args": { + "External id": 3726635,"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": 1625853109825.084, "dur": 2.052, + "args": { + "External id": 3726636,"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": 1625853109827.469, "dur": 1.593, + "args": { + "External id": 3726637,"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": 1625853109828.200, "dur": 0.603, + "args": { + "External id": 3726638,"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": 1625853109829.287, "dur": 1.862, + "args": { + "External id": 3726639,"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": 1625853109830.416, "dur": 0.670, + "args": { + "External id": 3726640,"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": 1625853109833.411, "dur": 3.372, + "args": { + "External id": 3726641,"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": 1625853109836.134, "dur": 0.585, + "args": { + "External id": 3726642,"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": 1625853109837.033, "dur": 2.220, + "args": { + "External id": 3726643,"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": 1625853109838.342, "dur": 0.668, + "args": { + "External id": 3726644,"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": 1625853109839.499, "dur": 1.915, + "args": { + "External id": 3726645,"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": 1625853109840.383, "dur": 0.759, + "args": { + "External id": 3726646,"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": 1625853109841.674, "dur": 4.005, + "args": { + "External id": 3726647,"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": 1625853109844.893, "dur": 0.723, + "args": { + "External id": 3726648,"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": 1625853109845.949, "dur": 1.448, + "args": { + "External id": 3726649,"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": 1625853109846.783, "dur": 0.548, + "args": { + "External id": 3726650,"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": 1625853109847.619, "dur": 3.893, + "args": { + "External id": 3726651,"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": 1625853109848.826, "dur": 2.498, + "args": { + "External id": 3726652,"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": 1625853109851.760, "dur": 1.565, + "args": { + "External id": 3726653,"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": 1625853109852.495, "dur": 0.646, + "args": { + "External id": 3726654,"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": 1625853109853.550, "dur": 2.093, + "args": { + "External id": 3726655,"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": 1625853109854.830, "dur": 0.750, + "args": { + "External id": 3726656,"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": 1625853109858.384, "dur": 3.692, + "args": { + "External id": 3726657,"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": 1625853109861.244, "dur": 0.771, + "args": { + "External id": 3726658,"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": 1625853109862.343, "dur": 1.927, + "args": { + "External id": 3726659,"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": 1625853109863.490, "dur": 0.594, + "args": { + "External id": 3726660,"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": 1625853109864.514, "dur": 2.124, + "args": { + "External id": 3726661,"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": 1625853109865.581, "dur": 0.984, + "args": { + "External id": 3726662,"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": 1625853109866.866, "dur": 3.365, + "args": { + "External id": 3726663,"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": 1625853109869.558, "dur": 0.612, + "args": { + "External id": 3726664,"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": 1625853109870.478, "dur": 1.515, + "args": { + "External id": 3726665,"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": 1625853109871.147, "dur": 0.604, + "args": { + "External id": 3726666,"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": 1625853109872.220, "dur": 3.998, + "args": { + "External id": 3726667,"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": 1625853109873.578, "dur": 2.424, + "args": { + "External id": 3726668,"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": 1625853109876.466, "dur": 1.594, + "args": { + "External id": 3726669,"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": 1625853109877.159, "dur": 0.835, + "args": { + "External id": 3726670,"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": 1625853109878.306, "dur": 2.195, + "args": { + "External id": 3726671,"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": 1625853109879.454, "dur": 0.777, + "args": { + "External id": 3726672,"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": 1625853109882.912, "dur": 3.325, + "args": { + "External id": 3726673,"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": 1625853109885.537, "dur": 0.634, + "args": { + "External id": 3726674,"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": 1625853109886.496, "dur": 2.283, + "args": { + "External id": 3726675,"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": 1625853109888.115, "dur": 0.602, + "args": { + "External id": 3726676,"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": 1625853109889.049, "dur": 1.688, + "args": { + "External id": 3726677,"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": 1625853109889.915, "dur": 0.754, + "args": { + "External id": 3726678,"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": 1625853109890.959, "dur": 3.341, + "args": { + "External id": 3726679,"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": 1625853109893.593, "dur": 0.644, + "args": { + "External id": 3726680,"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": 1625853109894.561, "dur": 1.727, + "args": { + "External id": 3726681,"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": 1625853109895.609, "dur": 0.619, + "args": { + "External id": 3726682,"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": 1625853109896.515, "dur": 3.663, + "args": { + "External id": 3726683,"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": 1625853109897.685, "dur": 2.236, + "args": { + "External id": 3726684,"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": 1625853109900.449, "dur": 1.796, + "args": { + "External id": 3726685,"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": 1625853109901.560, "dur": 0.616, + "args": { + "External id": 3726686,"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": 1625853109902.667, "dur": 2.202, + "args": { + "External id": 3726687,"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": 1625853109903.836, "dur": 0.767, + "args": { + "External id": 3726688,"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": 1625853109907.129, "dur": 3.479, + "args": { + "External id": 3726689,"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": 1625853109909.934, "dur": 0.605, + "args": { + "External id": 3726690,"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": 1625853109910.881, "dur": 1.939, + "args": { + "External id": 3726691,"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": 1625853109912.089, "dur": 0.668, + "args": { + "External id": 3726692,"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": 1625853109913.060, "dur": 1.634, + "args": { + "External id": 3726693,"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": 1625853109913.961, "dur": 0.669, + "args": { + "External id": 3726694,"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": 1625853109914.922, "dur": 3.524, + "args": { + "External id": 3726695,"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": 1625853109917.788, "dur": 0.582, + "args": { + "External id": 3726696,"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": 1625853109918.711, "dur": 1.651, + "args": { + "External id": 3726697,"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": 1625853109919.591, "dur": 0.709, + "args": { + "External id": 3726698,"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": 1625853109920.629, "dur": 3.245, + "args": { + "External id": 3726699,"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": 1625853109921.718, "dur": 2.081, + "args": { + "External id": 3726700,"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": 1625853109924.127, "dur": 1.746, + "args": { + "External id": 3726701,"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": 1625853109925.186, "dur": 0.624, + "args": { + "External id": 3726702,"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": 1625853109926.098, "dur": 1.998, + "args": { + "External id": 3726703,"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": 1625853109927.238, "dur": 0.794, + "args": { + "External id": 3726704,"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": 1625853109930.541, "dur": 3.491, + "args": { + "External id": 3726705,"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": 1625853109933.467, "dur": 0.499, + "args": { + "External id": 3726706,"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": 1625853109934.278, "dur": 2.227, + "args": { + "External id": 3726707,"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": 1625853109935.753, "dur": 0.689, + "args": { + "External id": 3726708,"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": 1625853109936.747, "dur": 1.951, + "args": { + "External id": 3726709,"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": 1625853109937.624, "dur": 1.011, + "args": { + "External id": 3726710,"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": 1625853109938.921, "dur": 3.810, + "args": { + "External id": 3726711,"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": 1625853109942.027, "dur": 0.640, + "args": { + "External id": 3726712,"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": 1625853109942.990, "dur": 1.290, + "args": { + "External id": 3726713,"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": 1625853109943.654, "dur": 0.564, + "args": { + "External id": 3726714,"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": 1625853109944.505, "dur": 3.471, + "args": { + "External id": 3726715,"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": 1625853109945.567, "dur": 2.340, + "args": { + "External id": 3726716,"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": 1625853109948.218, "dur": 1.718, + "args": { + "External id": 3726717,"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": 1625853109949.260, "dur": 0.614, + "args": { + "External id": 3726718,"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": 1625853109971.193, "dur": 153.079, + "args": { + "External id": 3726719,"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": 1625853110226.134, "dur": 136.252, + "args": { + "External id": 3726720,"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": 1625853110290.717, "dur": 52.154, + "args": { + "External id": 3726721,"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": 1625853110305.600, "dur": 1.035, + "args": { + "External id": 3726722,"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": 1625853110782.578, "dur": 1098.504, + "args": { + "External id": 3726723,"Sequence number": 37295308, "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": 1625853110839.796, "dur": 63.258, + "args": { + "External id": 3726724,"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": 1625853110844.822, "dur": 1.500, + "args": { + "External id": 3726725,"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": 1625853110848.278, "dur": 0.703, + "args": { + "External id": 3726726,"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": 1625853110927.006, "dur": 468.592, + "args": { + "External id": 3726727,"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": 1625853110933.259, "dur": 45.305, + "args": { + "External id": 3726728,"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": 1625853110937.314, "dur": 8.750, + "args": { + "External id": 3726729,"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": 1625853110941.181, "dur": 4.088, + "args": { + "External id": 3726730,"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": 1625853110947.377, "dur": 30.729, + "args": { + "External id": 3726731,"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": 1625853111021.689, "dur": 370.164, + "args": { + "External id": 3726732,"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": 1625853111053.572, "dur": 332.049, + "args": { + "External id": 3726733,"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": 1625853111073.757, "dur": 304.724, + "args": { + "External id": 3726734,"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": 1625853111583.109, "dur": 248.310, + "args": { + "External id": 3726735,"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": 1625853111704.948, "dur": 39.796, + "args": { + "External id": 3726736,"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": 1625853111727.792, "dur": 6.302, + "args": { + "External id": 3726737,"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": 1625853111777.921, "dur": 47.132, + "args": { + "External id": 3726738,"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": 1625853111780.731, "dur": 1.209, + "args": { + "External id": 3726739,"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": 1625853111783.176, "dur": 0.680, + "args": { + "External id": 3726740,"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": 1625853111899.025, "dur": 22.984, + "args": { + "External id": 3726741,"Sequence number": 37295309, "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": 1625853111910.974, "dur": 7.807, + "args": { + "External id": 3726742,"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": 1625853111913.231, "dur": 5.397, + "args": { + "External id": 3726743,"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": 1625853112295.280, "dur": 36.109, + "args": { + "External id": 3726744,"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": 1625853112340.953, "dur": 30.153, + "args": { + "External id": 3726745,"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": 1625853112388.352, "dur": 25.952, + "args": { + "External id": 3726746,"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": 1625853112428.252, "dur": 27.702, + "args": { + "External id": 3726747,"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": 1625853112431.477, "dur": 0.609, + "args": { + "External id": 3726748,"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": 1625853112474.652, "dur": 0.583, + "args": { + "External id": 3726749,"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": 1625853112590.154, "dur": 750.848, + "args": { + "External id": 3726750,"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": 1625853113141.163, "dur": 167.987, + "args": { + "External id": 3726751,"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": 1625853113385.586, "dur": 29.486, + "args": { + "External id": 3726752,"Sequence number": 37295310, "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": 1625853113389.686, "dur": 24.791, + "args": { + "External id": 3726753,"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": 1625853113418.896, "dur": 559.753, + "args": { + "External id": 3726754,"Sequence number": 37295310, "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": 1625853113420.534, "dur": 557.903, + "args": { + "External id": 3726755,"Sequence number": 37295310, "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": 1625853113422.679, "dur": 554.981, + "args": { + "External id": 3726756,"Sequence number": 37295310, "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": 1625853114011.582, "dur": 72.230, + "args": { + "External id": 3726757,"Sequence number": 37295310, "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": 1625853114015.371, "dur": 40.708, + "args": { + "External id": 3726758,"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": 1625853114023.201, "dur": 3.796, + "args": { + "External id": 3726759,"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": 1625853114029.341, "dur": 26.413, + "args": { + "External id": 3726760,"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": 1625853114034.367, "dur": 3.245, + "args": { + "External id": 3726761,"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": 1625853114059.356, "dur": 23.529, + "args": { + "External id": 3726762,"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": 1625853114086.263, "dur": 37.738, + "args": { + "External id": 3726763,"Sequence number": 37295310, "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": 1625853114089.464, "dur": 34.386, + "args": { + "External id": 3726764,"Sequence number": 37295310, "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": 1625853114090.503, "dur": 32.919, + "args": { + "External id": 3726765,"Sequence number": 37295310, "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": 1625853114156.921, "dur": 5877.076, + "args": { + "External id": 3726766,"Record function id": 0, "Ev Idx": 11333 + } + }, + { + "ph": "X", "cat": "user_annotation", "name": "Optimizer.step#AdamW.step", "pid": 1336756, "tid": 1336756, + "ts": 1625853114188.085, "dur": 5788.207, + "args": { + "External id": 3726767,"Record function id": 0, "Ev Idx": 11334 + } + }, + { + "ph": "X", "cat": "cpu_op", "name": "aten::_foreach_add_", "pid": 1336756, "tid": 1336756, + "ts": 1625853115520.439, "dur": 302.142, + "args": { + "External id": 3726768,"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": 1625853115540.985, "dur": 1.087, + "args": { + "External id": 3726769,"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": 1625853115543.337, "dur": 0.074, + "args": { + "External id": 3726770,"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": 1625853115543.869, "dur": 0.048, + "args": { + "External id": 3726771,"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": 1625853115544.444, "dur": 0.064, + "args": { + "External id": 3726772,"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": 1625853115545.026, "dur": 0.064, + "args": { + "External id": 3726773,"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": 1625853115545.519, "dur": 0.064, + "args": { + "External id": 3726774,"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": 1625853115546.023, "dur": 0.072, + "args": { + "External id": 3726775,"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": 1625853115546.522, "dur": 0.071, + "args": { + "External id": 3726776,"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": 1625853115547.042, "dur": 0.054, + "args": { + "External id": 3726777,"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": 1625853115547.598, "dur": 0.078, + "args": { + "External id": 3726778,"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": 1625853115548.030, "dur": 0.078, + "args": { + "External id": 3726779,"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": 1625853115548.691, "dur": 0.048, + "args": { + "External id": 3726780,"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": 1625853115549.064, "dur": 0.063, + "args": { + "External id": 3726781,"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": 1625853115549.751, "dur": 0.056, + "args": { + "External id": 3726782,"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": 1625853115550.231, "dur": 0.047, + "args": { + "External id": 3726783,"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": 1625853115550.830, "dur": 0.057, + "args": { + "External id": 3726784,"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": 1625853115551.283, "dur": 0.052, + "args": { + "External id": 3726785,"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": 1625853115551.713, "dur": 0.059, + "args": { + "External id": 3726786,"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": 1625853115552.100, "dur": 0.054, + "args": { + "External id": 3726787,"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": 1625853115552.523, "dur": 0.084, + "args": { + "External id": 3726788,"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": 1625853115552.960, "dur": 0.056, + "args": { + "External id": 3726789,"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": 1625853115553.396, "dur": 0.055, + "args": { + "External id": 3726790,"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": 1625853115553.783, "dur": 0.053, + "args": { + "External id": 3726791,"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": 1625853115554.234, "dur": 0.067, + "args": { + "External id": 3726792,"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": 1625853115554.588, "dur": 0.066, + "args": { + "External id": 3726793,"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": 1625853115555.001, "dur": 0.054, + "args": { + "External id": 3726794,"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": 1625853115555.399, "dur": 0.058, + "args": { + "External id": 3726795,"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": 1625853115555.823, "dur": 0.054, + "args": { + "External id": 3726796,"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": 1625853115556.226, "dur": 0.065, + "args": { + "External id": 3726797,"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": 1625853115556.657, "dur": 0.319, + "args": { + "External id": 3726798,"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": 1625853115557.297, "dur": 0.099, + "args": { + "External id": 3726799,"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": 1625853115557.743, "dur": 0.068, + "args": { + "External id": 3726800,"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": 1625853115558.144, "dur": 0.059, + "args": { + "External id": 3726801,"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": 1625853115558.573, "dur": 0.059, + "args": { + "External id": 3726802,"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": 1625853115558.931, "dur": 0.054, + "args": { + "External id": 3726803,"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": 1625853115559.363, "dur": 0.243, + "args": { + "External id": 3726804,"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": 1625853115559.952, "dur": 0.238, + "args": { + "External id": 3726805,"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": 1625853115560.571, "dur": 0.275, + "args": { + "External id": 3726806,"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": 1625853115561.186, "dur": 0.245, + "args": { + "External id": 3726807,"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": 1625853115561.983, "dur": 0.058, + "args": { + "External id": 3726808,"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": 1625853115562.396, "dur": 0.058, + "args": { + "External id": 3726809,"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": 1625853115562.789, "dur": 0.052, + "args": { + "External id": 3726810,"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": 1625853115563.271, "dur": 0.062, + "args": { + "External id": 3726811,"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": 1625853115563.694, "dur": 0.068, + "args": { + "External id": 3726812,"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": 1625853115564.204, "dur": 0.063, + "args": { + "External id": 3726813,"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": 1625853115564.582, "dur": 0.054, + "args": { + "External id": 3726814,"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": 1625853115564.941, "dur": 0.055, + "args": { + "External id": 3726815,"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": 1625853115565.454, "dur": 0.056, + "args": { + "External id": 3726816,"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": 1625853115565.983, "dur": 0.049, + "args": { + "External id": 3726817,"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": 1625853115566.503, "dur": 0.060, + "args": { + "External id": 3726818,"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": 1625853115567.022, "dur": 0.055, + "args": { + "External id": 3726819,"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": 1625853115567.496, "dur": 0.060, + "args": { + "External id": 3726820,"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": 1625853115567.855, "dur": 0.061, + "args": { + "External id": 3726821,"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": 1625853115568.317, "dur": 0.050, + "args": { + "External id": 3726822,"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": 1625853115568.716, "dur": 0.054, + "args": { + "External id": 3726823,"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": 1625853115569.271, "dur": 0.065, + "args": { + "External id": 3726824,"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": 1625853115569.666, "dur": 0.061, + "args": { + "External id": 3726825,"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": 1625853115570.093, "dur": 0.068, + "args": { + "External id": 3726826,"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": 1625853115570.469, "dur": 0.070, + "args": { + "External id": 3726827,"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": 1625853115570.863, "dur": 0.061, + "args": { + "External id": 3726828,"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": 1625853115571.271, "dur": 0.060, + "args": { + "External id": 3726829,"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": 1625853115571.654, "dur": 0.062, + "args": { + "External id": 3726830,"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": 1625853115572.011, "dur": 0.060, + "args": { + "External id": 3726831,"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": 1625853115572.396, "dur": 0.058, + "args": { + "External id": 3726832,"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": 1625853115572.789, "dur": 0.058, + "args": { + "External id": 3726833,"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": 1625853115573.195, "dur": 0.060, + "args": { + "External id": 3726834,"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": 1625853115573.585, "dur": 0.060, + "args": { + "External id": 3726835,"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": 1625853115573.994, "dur": 0.061, + "args": { + "External id": 3726836,"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": 1625853115574.415, "dur": 0.254, + "args": { + "External id": 3726837,"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": 1625853115575.039, "dur": 0.070, + "args": { + "External id": 3726838,"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": 1625853115575.700, "dur": 0.266, + "args": { + "External id": 3726839,"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": 1625853115576.408, "dur": 0.070, + "args": { + "External id": 3726840,"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": 1625853115576.914, "dur": 0.055, + "args": { + "External id": 3726841,"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": 1625853115577.507, "dur": 0.071, + "args": { + "External id": 3726842,"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": 1625853115578.011, "dur": 0.076, + "args": { + "External id": 3726843,"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": 1625853115578.407, "dur": 0.062, + "args": { + "External id": 3726844,"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": 1625853115578.976, "dur": 0.353, + "args": { + "External id": 3726845,"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": 1625853115579.718, "dur": 0.058, + "args": { + "External id": 3726846,"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": 1625853115580.510, "dur": 0.059, + "args": { + "External id": 3726847,"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": 1625853115580.855, "dur": 0.094, + "args": { + "External id": 3726848,"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": 1625853115609.254, "dur": 0.069, + "args": { + "External id": 3726849,"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": 1625853115609.814, "dur": 0.053, + "args": { + "External id": 3726850,"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": 1625853115610.258, "dur": 0.067, + "args": { + "External id": 3726851,"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": 1625853115610.721, "dur": 0.064, + "args": { + "External id": 3726852,"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": 1625853115611.103, "dur": 0.068, + "args": { + "External id": 3726853,"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": 1625853115611.661, "dur": 0.056, + "args": { + "External id": 3726854,"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": 1625853115612.099, "dur": 0.056, + "args": { + "External id": 3726855,"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": 1625853115612.554, "dur": 0.051, + "args": { + "External id": 3726856,"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": 1625853115613.009, "dur": 0.046, + "args": { + "External id": 3726857,"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": 1625853115613.363, "dur": 0.057, + "args": { + "External id": 3726858,"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": 1625853115613.820, "dur": 0.048, + "args": { + "External id": 3726859,"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": 1625853115614.207, "dur": 0.059, + "args": { + "External id": 3726860,"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": 1625853115614.604, "dur": 0.058, + "args": { + "External id": 3726861,"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": 1625853115614.996, "dur": 0.059, + "args": { + "External id": 3726862,"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": 1625853115615.409, "dur": 0.053, + "args": { + "External id": 3726863,"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": 1625853115615.761, "dur": 0.059, + "args": { + "External id": 3726864,"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": 1625853115616.187, "dur": 0.057, + "args": { + "External id": 3726865,"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": 1625853115616.580, "dur": 0.060, + "args": { + "External id": 3726866,"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": 1625853115616.992, "dur": 0.057, + "args": { + "External id": 3726867,"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": 1625853115617.396, "dur": 0.050, + "args": { + "External id": 3726868,"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": 1625853115617.814, "dur": 0.058, + "args": { + "External id": 3726869,"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": 1625853115618.194, "dur": 0.058, + "args": { + "External id": 3726870,"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": 1625853115618.575, "dur": 0.060, + "args": { + "External id": 3726871,"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": 1625853115618.998, "dur": 0.058, + "args": { + "External id": 3726872,"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": 1625853115619.307, "dur": 0.068, + "args": { + "External id": 3726873,"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": 1625853115619.731, "dur": 0.059, + "args": { + "External id": 3726874,"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": 1625853115620.091, "dur": 0.069, + "args": { + "External id": 3726875,"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": 1625853115620.512, "dur": 0.065, + "args": { + "External id": 3726876,"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": 1625853115620.996, "dur": 0.065, + "args": { + "External id": 3726877,"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": 1625853115621.460, "dur": 0.054, + "args": { + "External id": 3726878,"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": 1625853115621.767, "dur": 0.060, + "args": { + "External id": 3726879,"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": 1625853115622.225, "dur": 0.057, + "args": { + "External id": 3726880,"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": 1625853115622.620, "dur": 0.059, + "args": { + "External id": 3726881,"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": 1625853115623.020, "dur": 0.061, + "args": { + "External id": 3726882,"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": 1625853115623.464, "dur": 0.050, + "args": { + "External id": 3726883,"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": 1625853115623.807, "dur": 0.060, + "args": { + "External id": 3726884,"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": 1625853115624.453, "dur": 0.059, + "args": { + "External id": 3726885,"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": 1625853115624.860, "dur": 0.055, + "args": { + "External id": 3726886,"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": 1625853115625.340, "dur": 0.049, + "args": { + "External id": 3726887,"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": 1625853115625.873, "dur": 0.060, + "args": { + "External id": 3726888,"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": 1625853115626.322, "dur": 0.058, + "args": { + "External id": 3726889,"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": 1625853115626.674, "dur": 0.055, + "args": { + "External id": 3726890,"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": 1625853115627.068, "dur": 0.059, + "args": { + "External id": 3726891,"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": 1625853115627.496, "dur": 0.058, + "args": { + "External id": 3726892,"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": 1625853115627.894, "dur": 0.059, + "args": { + "External id": 3726893,"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": 1625853115628.386, "dur": 0.056, + "args": { + "External id": 3726894,"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": 1625853115628.788, "dur": 0.057, + "args": { + "External id": 3726895,"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": 1625853115629.217, "dur": 0.049, + "args": { + "External id": 3726896,"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": 1625853115629.642, "dur": 0.059, + "args": { + "External id": 3726897,"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": 1625853115630.282, "dur": 0.064, + "args": { + "External id": 3726898,"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": 1625853115638.333, "dur": 0.075, + "args": { + "External id": 3726899,"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": 1625853115639.873, "dur": 0.058, + "args": { + "External id": 3726900,"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": 1625853115640.335, "dur": 0.058, + "args": { + "External id": 3726901,"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": 1625853115640.769, "dur": 0.058, + "args": { + "External id": 3726902,"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": 1625853115641.150, "dur": 0.061, + "args": { + "External id": 3726903,"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": 1625853115641.573, "dur": 0.059, + "args": { + "External id": 3726904,"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": 1625853115642.000, "dur": 0.060, + "args": { + "External id": 3726905,"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": 1625853115642.538, "dur": 0.048, + "args": { + "External id": 3726906,"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": 1625853115642.920, "dur": 0.061, + "args": { + "External id": 3726907,"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": 1625853115643.333, "dur": 0.059, + "args": { + "External id": 3726908,"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": 1625853115643.803, "dur": 0.059, + "args": { + "External id": 3726909,"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": 1625853115644.215, "dur": 0.053, + "args": { + "External id": 3726910,"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": 1625853115644.598, "dur": 0.060, + "args": { + "External id": 3726911,"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": 1625853115644.960, "dur": 0.056, + "args": { + "External id": 3726912,"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": 1625853115645.353, "dur": 0.059, + "args": { + "External id": 3726913,"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": 1625853115645.759, "dur": 0.059, + "args": { + "External id": 3726914,"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": 1625853115646.168, "dur": 0.061, + "args": { + "External id": 3726915,"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": 1625853115646.554, "dur": 0.058, + "args": { + "External id": 3726916,"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": 1625853115647.020, "dur": 0.058, + "args": { + "External id": 3726917,"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": 1625853115647.398, "dur": 0.063, + "args": { + "External id": 3726918,"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": 1625853115647.864, "dur": 0.069, + "args": { + "External id": 3726919,"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": 1625853115648.387, "dur": 0.068, + "args": { + "External id": 3726920,"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": 1625853115648.792, "dur": 0.053, + "args": { + "External id": 3726921,"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": 1625853115649.318, "dur": 0.055, + "args": { + "External id": 3726922,"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": 1625853115649.781, "dur": 0.051, + "args": { + "External id": 3726923,"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": 1625853115650.155, "dur": 0.063, + "args": { + "External id": 3726924,"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": 1625853115650.572, "dur": 0.054, + "args": { + "External id": 3726925,"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": 1625853115651.386, "dur": 0.067, + "args": { + "External id": 3726926,"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": 1625853115651.763, "dur": 0.053, + "args": { + "External id": 3726927,"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": 1625853115652.327, "dur": 0.084, + "args": { + "External id": 3726928,"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": 1625853115652.709, "dur": 0.058, + "args": { + "External id": 3726929,"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": 1625853115653.122, "dur": 0.060, + "args": { + "External id": 3726930,"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": 1625853115653.538, "dur": 0.060, + "args": { + "External id": 3726931,"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": 1625853115653.902, "dur": 0.060, + "args": { + "External id": 3726932,"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": 1625853115654.338, "dur": 0.055, + "args": { + "External id": 3726933,"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": 1625853115654.693, "dur": 0.051, + "args": { + "External id": 3726934,"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": 1625853115655.078, "dur": 0.060, + "args": { + "External id": 3726935,"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": 1625853115655.486, "dur": 0.060, + "args": { + "External id": 3726936,"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": 1625853115655.926, "dur": 0.057, + "args": { + "External id": 3726937,"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": 1625853115656.232, "dur": 0.054, + "args": { + "External id": 3726938,"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": 1625853115656.538, "dur": 0.062, + "args": { + "External id": 3726939,"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": 1625853115656.976, "dur": 0.058, + "args": { + "External id": 3726940,"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": 1625853115657.423, "dur": 0.059, + "args": { + "External id": 3726941,"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": 1625853115657.828, "dur": 0.057, + "args": { + "External id": 3726942,"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": 1625853115658.189, "dur": 0.060, + "args": { + "External id": 3726943,"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": 1625853115658.592, "dur": 0.059, + "args": { + "External id": 3726944,"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": 1625853115659.117, "dur": 0.065, + "args": { + "External id": 3726945,"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": 1625853115659.522, "dur": 0.059, + "args": { + "External id": 3726946,"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": 1625853115659.939, "dur": 0.070, + "args": { + "External id": 3726947,"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": 1625853115660.347, "dur": 0.066, + "args": { + "External id": 3726948,"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": 1625853115660.715, "dur": 0.056, + "args": { + "External id": 3726949,"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": 1625853115661.193, "dur": 0.048, + "args": { + "External id": 3726950,"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": 1625853115661.505, "dur": 0.057, + "args": { + "External id": 3726951,"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": 1625853115661.914, "dur": 0.058, + "args": { + "External id": 3726952,"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": 1625853115662.300, "dur": 0.057, + "args": { + "External id": 3726953,"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": 1625853115662.682, "dur": 0.054, + "args": { + "External id": 3726954,"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": 1625853115663.098, "dur": 0.082, + "args": { + "External id": 3726955,"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": 1625853115663.505, "dur": 0.057, + "args": { + "External id": 3726956,"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": 1625853115663.929, "dur": 0.056, + "args": { + "External id": 3726957,"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": 1625853115664.254, "dur": 0.048, + "args": { + "External id": 3726958,"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": 1625853115664.622, "dur": 0.060, + "args": { + "External id": 3726959,"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": 1625853115664.963, "dur": 0.059, + "args": { + "External id": 3726960,"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": 1625853115665.374, "dur": 0.057, + "args": { + "External id": 3726961,"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": 1625853115665.815, "dur": 0.063, + "args": { + "External id": 3726962,"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": 1625853115666.125, "dur": 0.059, + "args": { + "External id": 3726963,"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": 1625853115666.550, "dur": 0.059, + "args": { + "External id": 3726964,"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": 1625853115666.934, "dur": 0.070, + "args": { + "External id": 3726965,"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": 1625853115667.364, "dur": 0.078, + "args": { + "External id": 3726966,"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": 1625853115667.711, "dur": 0.060, + "args": { + "External id": 3726967,"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": 1625853115668.113, "dur": 0.062, + "args": { + "External id": 3726968,"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": 1625853115668.514, "dur": 0.060, + "args": { + "External id": 3726969,"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": 1625853115668.886, "dur": 0.059, + "args": { + "External id": 3726970,"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": 1625853115669.378, "dur": 0.057, + "args": { + "External id": 3726971,"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": 1625853115669.755, "dur": 0.067, + "args": { + "External id": 3726972,"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": 1625853115670.094, "dur": 0.054, + "args": { + "External id": 3726973,"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": 1625853115670.566, "dur": 0.055, + "args": { + "External id": 3726974,"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": 1625853115670.988, "dur": 0.067, + "args": { + "External id": 3726975,"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": 1625853115671.330, "dur": 0.056, + "args": { + "External id": 3726976,"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": 1625853115671.677, "dur": 0.055, + "args": { + "External id": 3726977,"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": 1625853115672.091, "dur": 0.060, + "args": { + "External id": 3726978,"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": 1625853115672.620, "dur": 0.055, + "args": { + "External id": 3726979,"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": 1625853115672.962, "dur": 0.055, + "args": { + "External id": 3726980,"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": 1625853115673.346, "dur": 0.063, + "args": { + "External id": 3726981,"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": 1625853115691.947, "dur": 0.467, + "args": { + "External id": 3726982,"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": 1625853115693.623, "dur": 0.048, + "args": { + "External id": 3726983,"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": 1625853115694.144, "dur": 0.052, + "args": { + "External id": 3726984,"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": 1625853115694.695, "dur": 0.061, + "args": { + "External id": 3726985,"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": 1625853115695.040, "dur": 0.052, + "args": { + "External id": 3726986,"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": 1625853115695.448, "dur": 0.057, + "args": { + "External id": 3726987,"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": 1625853115695.910, "dur": 0.052, + "args": { + "External id": 3726988,"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": 1625853115696.322, "dur": 0.051, + "args": { + "External id": 3726989,"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": 1625853115696.688, "dur": 0.049, + "args": { + "External id": 3726990,"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": 1625853115697.086, "dur": 0.056, + "args": { + "External id": 3726991,"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": 1625853115697.506, "dur": 0.054, + "args": { + "External id": 3726992,"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": 1625853115698.013, "dur": 0.047, + "args": { + "External id": 3726993,"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": 1625853115698.429, "dur": 0.061, + "args": { + "External id": 3726994,"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": 1625853115698.794, "dur": 0.059, + "args": { + "External id": 3726995,"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": 1625853115699.238, "dur": 0.061, + "args": { + "External id": 3726996,"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": 1625853115699.626, "dur": 0.064, + "args": { + "External id": 3726997,"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": 1625853115700.085, "dur": 0.053, + "args": { + "External id": 3726998,"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": 1625853115700.469, "dur": 0.057, + "args": { + "External id": 3726999,"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": 1625853115700.994, "dur": 0.052, + "args": { + "External id": 3727000,"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": 1625853115701.421, "dur": 0.055, + "args": { + "External id": 3727001,"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": 1625853115701.840, "dur": 0.057, + "args": { + "External id": 3727002,"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": 1625853115702.274, "dur": 0.065, + "args": { + "External id": 3727003,"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": 1625853115702.643, "dur": 0.066, + "args": { + "External id": 3727004,"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": 1625853115703.049, "dur": 0.064, + "args": { + "External id": 3727005,"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": 1625853115703.415, "dur": 0.061, + "args": { + "External id": 3727006,"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": 1625853115703.862, "dur": 0.066, + "args": { + "External id": 3727007,"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": 1625853115704.821, "dur": 0.059, + "args": { + "External id": 3727008,"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": 1625853115705.253, "dur": 0.050, + "args": { + "External id": 3727009,"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": 1625853115705.637, "dur": 0.056, + "args": { + "External id": 3727010,"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": 1625853115706.116, "dur": 0.045, + "args": { + "External id": 3727011,"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": 1625853115706.509, "dur": 0.064, + "args": { + "External id": 3727012,"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": 1625853115706.963, "dur": 0.052, + "args": { + "External id": 3727013,"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": 1625853115707.364, "dur": 0.066, + "args": { + "External id": 3727014,"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": 1625853115708.038, "dur": 0.052, + "args": { + "External id": 3727015,"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": 1625853115708.564, "dur": 0.055, + "args": { + "External id": 3727016,"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": 1625853115709.002, "dur": 0.055, + "args": { + "External id": 3727017,"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": 1625853115709.724, "dur": 0.057, + "args": { + "External id": 3727018,"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": 1625853115710.131, "dur": 0.050, + "args": { + "External id": 3727019,"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": 1625853115710.944, "dur": 0.066, + "args": { + "External id": 3727020,"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": 1625853115711.274, "dur": 0.044, + "args": { + "External id": 3727021,"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": 1625853115712.133, "dur": 0.049, + "args": { + "External id": 3727022,"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": 1625853115712.423, "dur": 0.047, + "args": { + "External id": 3727023,"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": 1625853115713.193, "dur": 0.058, + "args": { + "External id": 3727024,"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": 1625853115713.490, "dur": 0.052, + "args": { + "External id": 3727025,"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": 1625853115714.303, "dur": 0.066, + "args": { + "External id": 3727026,"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": 1625853115714.613, "dur": 0.050, + "args": { + "External id": 3727027,"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": 1625853115715.475, "dur": 0.065, + "args": { + "External id": 3727028,"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": 1625853115715.782, "dur": 0.051, + "args": { + "External id": 3727029,"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": 1625853115716.589, "dur": 0.056, + "args": { + "External id": 3727030,"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": 1625853115716.888, "dur": 0.046, + "args": { + "External id": 3727031,"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": 1625853115717.673, "dur": 0.057, + "args": { + "External id": 3727032,"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": 1625853115717.976, "dur": 0.052, + "args": { + "External id": 3727033,"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": 1625853115718.528, "dur": 0.067, + "args": { + "External id": 3727034,"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": 1625853115718.836, "dur": 0.050, + "args": { + "External id": 3727035,"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": 1625853115719.653, "dur": 0.052, + "args": { + "External id": 3727036,"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": 1625853115719.960, "dur": 0.048, + "args": { + "External id": 3727037,"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": 1625853115720.725, "dur": 0.058, + "args": { + "External id": 3727038,"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": 1625853115721.057, "dur": 0.047, + "args": { + "External id": 3727039,"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": 1625853115721.816, "dur": 0.056, + "args": { + "External id": 3727040,"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": 1625853115722.122, "dur": 0.044, + "args": { + "External id": 3727041,"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": 1625853115722.843, "dur": 0.059, + "args": { + "External id": 3727042,"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": 1625853115723.142, "dur": 0.044, + "args": { + "External id": 3727043,"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": 1625853115723.945, "dur": 0.080, + "args": { + "External id": 3727044,"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": 1625853115724.269, "dur": 0.046, + "args": { + "External id": 3727045,"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": 1625853115724.988, "dur": 0.061, + "args": { + "External id": 3727046,"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": 1625853115725.297, "dur": 0.050, + "args": { + "External id": 3727047,"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": 1625853115726.100, "dur": 0.058, + "args": { + "External id": 3727048,"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": 1625853115726.400, "dur": 0.046, + "args": { + "External id": 3727049,"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": 1625853115727.157, "dur": 0.069, + "args": { + "External id": 3727050,"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": 1625853115727.473, "dur": 0.048, + "args": { + "External id": 3727051,"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": 1625853115728.264, "dur": 0.065, + "args": { + "External id": 3727052,"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": 1625853115728.613, "dur": 0.055, + "args": { + "External id": 3727053,"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": 1625853115729.523, "dur": 0.054, + "args": { + "External id": 3727054,"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": 1625853115729.828, "dur": 0.048, + "args": { + "External id": 3727055,"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": 1625853115730.607, "dur": 0.069, + "args": { + "External id": 3727056,"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": 1625853115730.922, "dur": 0.050, + "args": { + "External id": 3727057,"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": 1625853115731.694, "dur": 0.060, + "args": { + "External id": 3727058,"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": 1625853115732.001, "dur": 0.044, + "args": { + "External id": 3727059,"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": 1625853116359.924, "dur": 3523.604, + "args": { + "External id": 3727060,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "4.1856239316233545e-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": 1625853119366.419, "dur": 348.204, + "args": { + "External id": 3727061,"Record function id": 0, "Concrete Inputs": ["", "", "", "", "", "", "4.1856239316233545e-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 + } + }, + { + "name": "process_name", "ph": "M", "ts": 1625851009761.905, "pid": 1336756, "tid": 0, + "args": { + "name": "python3.12" + } + }, + { + "name": "process_labels", "ph": "M", "ts": 1625851009761.905, "pid": 1336756, "tid": 0, + "args": { + "labels": "CPU" + } + }, + { + "name": "process_sort_index", "ph": "M", "ts": 1625851009761.905, "pid": 1336756, "tid": 0, + "args": { + "sort_index": 1336756 + } + }, + { + "name": "thread_name", "ph": "M", "ts": 1625851009761.905, "pid": 1336756, "tid": 1381189, + "args": { + "name": "thread 1381189 (pt_autograd_3)" + } + }, + { + "name": "thread_sort_index", "ph": "M", "ts": 1625851009761.905, "pid": 1336756, "tid": 1381189, + "args": { + "sort_index": 1381189 + } + }, + { + "name": "thread_name", "ph": "M", "ts": 1625851009761.905, "pid": 1336756, "tid": 1381189, + "args": { + "name": "thread 1381189 (python3.12)" + } + }, + { + "name": "thread_sort_index", "ph": "M", "ts": 1625851009761.905, "pid": 1336756, "tid": 1381189, + "args": { + "sort_index": 1381189 + } + }, + { + "name": "thread_name", "ph": "M", "ts": 1625851009761.905, "pid": 1336756, "tid": 1336756, + "args": { + "name": "thread 1336756 (python3.12)" + } + }, + { + "name": "thread_sort_index", "ph": "M", "ts": 1625851009761.905, "pid": 1336756, "tid": 1336756, + "args": { + "sort_index": 1336756 + } + }, + { + "ph": "X", "cat": "Trace", "ts": 1625851009695.854, "dur": 2111923.668, + "pid": "Spans", "tid": "PyTorch Profiler", + "name": "PyTorch Profiler (0)", + "args": { + "Op count": 0 + } + }, + { + "name": "process_sort_index", "ph": "M", "ts": 1625851009695.854, + "pid": "Spans", "tid": 0, + "args": { + "sort_index": 536870912 + } + }, + { + "name": "Iteration Start: PyTorch Profiler", "ph": "i", "s": "g", + "pid": "Traces", "tid": "Trace PyTorch Profiler", "ts": 1625851009695.854 + }, + { + "name": "Record Window End", "ph": "i", "s": "g", + "pid": "", "tid": "", "ts": 1625853198754.012 + } + ], + "traceName": "exp/mtp.1B.batch16.seqlen4096.context4096.warmup2000.update1.steps200000.lr2e-4.cosine/profile_trace/iteration_155136/rank3_trace.json", + "displayTimeUnit": "ms", + "baseTimeNanoseconds": 1751410836000000000 +} \ No newline at end of file